-------------------------------------------------------------------------------------------------------------------
      name:  <unnamed>
       log:  C:\ian\git\artbin\testing\artbin_test_every_option.log
  log type:  text
 opened on:   4 Jan 2024, 19:03:45

. which artbin`ver'
c:\ian\git\artbin\package\artbin.ado
*!version 2.1.0 IW     04jan2024

. local returns 1

. 
. // UTILITIES
. cap prog drop dicmd

. prog def dicmd
  1. noi di as input `"`0'"'
  2. `0'
  3. end

. 
. 
. // 2 arms
. local command artbin`ver', pr(.4 .2)

. dicmd `command'
artbin, pr(.4 .2)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         164

Sample size per group (calculated)     82 82
Expected total number of events        49.2
Expected number of events per group    32.8 16.4
------------------------------------------------------------------------------

. local n=r(n)

. * options expected to increase SS
. foreach opt in "margin(-.1)" "alpha(0.01)" "aratios(1 2)" "local" "ccorrect(1)"  "ccorrect" "power(.9)" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) > `n'
  7. }


artbin, pr(.4 .2) margin(-.1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          substantial-superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= -.1
Alternative hypothesis                 H1: pi2 - pi1 < -.1

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         640

Sample size per group (calculated)     320 320
Expected total number of events        192
Expected number of events per group    128 64
------------------------------------------------------------------------------

scalars:
                  r(D) =  192
                  r(n) =  640
              r(power) =  .8
                 r(D2) =  64
                 r(n2) =  320
                 r(D1) =  128
                 r(n1) =  320


artbin, pr(.4 .2) alpha(0.01)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.010 (two-sided)
                                        (taken as .005 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         244

Sample size per group (calculated)     122 122
Expected total number of events        73.2
Expected number of events per group    48.8 24.4
------------------------------------------------------------------------------

scalars:
                  r(D) =  73.19999999999999
                  r(n) =  244
              r(power) =  .8
                 r(D2) =  24.4
                 r(n2) =  122
                 r(D1) =  48.8
                 r(n1) =  122


artbin, pr(.4 .2) aratios(1 2)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       1:2
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         179

Sample size per group (calculated)     60 119
Expected total number of events        47.8
Expected number of events per group    24 23.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  47.8
                  r(n) =  179
              r(power) =  .8
                 r(D2) =  23.8
                 r(n2) =  119
                 r(D1) =  24
                 r(n1) =  60


artbin, pr(.4 .2) local

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       local
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         166

Sample size per group (calculated)     83 83
Expected total number of events        49.8
Expected number of events per group    33.2 16.6
------------------------------------------------------------------------------

scalars:
                  r(D) =  49.8
                  r(n) =  166
              r(power) =  .8
                 r(D2) =  16.6
                 r(n2) =  83
                 r(D1) =  33.2
                 r(n1) =  83


artbin, pr(.4 .2) ccorrect(1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  yes

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         182

Sample size per group (calculated)     91 91
Expected total number of events        54.6
Expected number of events per group    36.4 18.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  54.59999999999999
                  r(n) =  182
              r(power) =  .8
                 r(D2) =  18.2
                 r(n2) =  91
                 r(D1) =  36.4
                 r(n1) =  91


artbin, pr(.4 .2) ccorrect

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  yes

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         182

Sample size per group (calculated)     91 91
Expected total number of events        54.6
Expected number of events per group    36.4 18.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  54.59999999999999
                  r(n) =  182
              r(power) =  .8
                 r(D2) =  18.2
                 r(n2) =  91
                 r(D1) =  36.4
                 r(n1) =  91


artbin, pr(.4 .2) power(.9)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.900

Total sample size (calculated)         218

Sample size per group (calculated)     109 109
Expected total number of events        65.4
Expected number of events per group    43.6 21.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  65.40000000000001
                  r(n) =  218
              r(power) =  .9
                 r(D2) =  21.8
                 r(n2) =  109
                 r(D1) =  43.6
                 r(n1) =  109

. * options expected to decrease SS
. foreach opt in "margin(.1)" "alpha(0.1)" "condit" "onesided(1)" "onesided" "wald"  "noround" "power(.7)" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) < `n'
  7. }


artbin, pr(.4 .2) margin(.1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         74

Sample size per group (calculated)     37 37
Expected total number of events        22.2
Expected number of events per group    14.8 7.4
------------------------------------------------------------------------------

scalars:
                  r(D) =  22.2
                  r(n) =  74
              r(power) =  .8
                 r(D2) =  7.4
                 r(n2) =  37
                 r(D1) =  14.8
                 r(n1) =  37


artbin, pr(.4 .2) alpha(0.1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.100 (two-sided)
                                        (taken as .05 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         128

Sample size per group (calculated)     64 64
Expected total number of events        38.4
Expected number of events per group    25.6 12.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  38.40000000000001
                  r(n) =  128
              r(power) =  .8
                 r(D2) =  12.8
                 r(n2) =  64
                 r(D1) =  25.6
                 r(n1) =  64


artbin, pr(.4 .2) condit
 NOTE: As conditional has been selected local will be used.

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               Conditional test using Peto's
                                        approximation to the odds ratio
                                        using the score test
Local or distant                       local
Continuity correction                  no

Anticipated event probabilities        0.400 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         156

Sample size per group (calculated)     78 78
Expected total number of events        46.8
Expected number of events per group    31.2 15.6
------------------------------------------------------------------------------

scalars:
                  r(D) =  46.8
                  r(n) =  156
              r(power) =  .8
                 r(D2) =  15.6
                 r(n2) =  78
                 r(D1) =  31.2
                 r(n1) =  78


artbin, pr(.4 .2) onesided(1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (one-sided)
Power (designed)                       0.800

Total sample size (calculated)         128

Sample size per group (calculated)     64 64
Expected total number of events        38.4
Expected number of events per group    25.6 12.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  38.40000000000001
                  r(n) =  128
              r(power) =  .8
                 r(D2) =  12.8
                 r(n2) =  64
                 r(D1) =  25.6
                 r(n1) =  64


artbin, pr(.4 .2) onesided

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (one-sided)
Power (designed)                       0.800

Total sample size (calculated)         128

Sample size per group (calculated)     64 64
Expected total number of events        38.4
Expected number of events per group    25.6 12.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  38.40000000000001
                  r(n) =  128
              r(power) =  .8
                 r(D2) =  12.8
                 r(n2) =  64
                 r(D1) =  25.6
                 r(n1) =  64


artbin, pr(.4 .2) wald

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the wald test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         158

Sample size per group (calculated)     79 79
Expected total number of events        47.4
Expected number of events per group    31.6 15.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  47.40000000000001
                  r(n) =  158
              r(power) =  .8
                 r(D2) =  15.8
                 r(n2) =  79
                 r(D1) =  31.6
                 r(n1) =  79


artbin, pr(.4 .2) noround

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         162.45

Sample size per group (calculated)     81.22 81.22
Expected total number of events        48.73
Expected number of events per group    32.49 16.24
------------------------------------------------------------------------------

scalars:
                  r(D) =  48.73454441727327
                  r(n) =  162.4484813909109
              r(power) =  .8
                 r(D2) =  16.24484813909109
                 r(n2) =  81.22424069545545
                 r(D1) =  32.48969627818218
                 r(n1) =  81.22424069545545


artbin, pr(.4 .2) power(.7)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.700

Total sample size (calculated)         130

Sample size per group (calculated)     65 65
Expected total number of events        39
Expected number of events per group    26 13
------------------------------------------------------------------------------

scalars:
                  r(D) =  39
                  r(n) =  130
              r(power) =  .7
                 r(D2) =  13
                 r(n2) =  65
                 r(D1) =  26
                 r(n1) =  65

. * options expected not to change SS 
. foreach opt in "power(.8)" "unfavourable" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) == `n'
  7. }


artbin, pr(.4 .2) power(.8)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         164

Sample size per group (calculated)     82 82
Expected total number of events        49.2
Expected number of events per group    32.8 16.4
------------------------------------------------------------------------------

scalars:
                  r(D) =  49.2
                  r(n) =  164
              r(power) =  .8
                 r(D2) =  16.4
                 r(n2) =  82
                 r(D1) =  32.8
                 r(n1) =  82


artbin, pr(.4 .2) unfavourable

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         164

Sample size per group (calculated)     82 82
Expected total number of events        49.2
Expected number of events per group    32.8 16.4
------------------------------------------------------------------------------

scalars:
                  r(D) =  49.2
                  r(n) =  164
              r(power) =  .8
                 r(D2) =  16.4
                 r(n2) =  82
                 r(D1) =  32.8
                 r(n1) =  82

. * options expected to cause error
. foreach opt in "trend" /* "favourable" */ {
  2.         di _n
  3.         dicmd cap noi `command' `opt'
  4.         assert _rc
  5. }


cap noi artbin, pr(.4 .2) trend
Can not select trend option for a 2-arm trial

. 
. 
. 
. 
. // 2 arms, NI
. local command artbin`ver', pr(.2 .2) margin(.1)

. dicmd `command'
artbin, pr(.2 .2) margin(.1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         510

Sample size per group (calculated)     255 255
Expected total number of events        102
Expected number of events per group    51 51
------------------------------------------------------------------------------

. local n=r(n)

. * options expected to increase SS
. foreach opt in "alpha(0.01)" "aratios(1 2)" "local" "ccorrect(1)"  "ccorrect" "power(.9)" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) > `n'
  7. }


artbin, pr(.2 .2) margin(.1) alpha(0.01)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.010 (two-sided)
                                        (taken as .005 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         758

Sample size per group (calculated)     379 379
Expected total number of events        151.6
Expected number of events per group    75.8 75.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  151.6
                  r(n) =  758
              r(power) =  .8
                 r(D2) =  75.8
                 r(n2) =  379
                 r(D1) =  75.8
                 r(n1) =  379


artbin, pr(.2 .2) margin(.1) aratios(1 2)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       1:2
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         524

Sample size per group (calculated)     175 349
Expected total number of events        104.8
Expected number of events per group    35 69.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  104.8
                  r(n) =  524
              r(power) =  .8
                 r(D2) =  69.8
                 r(n2) =  349
                 r(D1) =  35
                 r(n1) =  175


artbin, pr(.2 .2) margin(.1) local

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       local
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         512

Sample size per group (calculated)     256 256
Expected total number of events        102.4
Expected number of events per group    51.2 51.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  102.4
                  r(n) =  512
              r(power) =  .8
                 r(D2) =  51.2
                 r(n2) =  256
                 r(D1) =  51.2
                 r(n1) =  256


artbin, pr(.2 .2) margin(.1) ccorrect(1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  yes
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         548

Sample size per group (calculated)     274 274
Expected total number of events        109.6
Expected number of events per group    54.8 54.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  109.6
                  r(n) =  548
              r(power) =  .8
                 r(D2) =  54.8
                 r(n2) =  274
                 r(D1) =  54.8
                 r(n1) =  274


artbin, pr(.2 .2) margin(.1) ccorrect

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  yes
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         548

Sample size per group (calculated)     274 274
Expected total number of events        109.6
Expected number of events per group    54.8 54.8
------------------------------------------------------------------------------

scalars:
                  r(D) =  109.6
                  r(n) =  548
              r(power) =  .8
                 r(D2) =  54.8
                 r(n2) =  274
                 r(D1) =  54.8
                 r(n1) =  274


artbin, pr(.2 .2) margin(.1) power(.9)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.900

Total sample size (calculated)         680

Sample size per group (calculated)     340 340
Expected total number of events        136
Expected number of events per group    68 68
------------------------------------------------------------------------------

scalars:
                  r(D) =  136
                  r(n) =  680
              r(power) =  .9
                 r(D2) =  68
                 r(n2) =  340
                 r(D1) =  68
                 r(n1) =  340

. * options expected to decrease SS
. foreach opt in "alpha(0.1)" "onesided(1)" "onesided" "wald"  "noround" "power(.7)" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) < `n'
  7. }


artbin, pr(.2 .2) margin(.1) alpha(0.1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.100 (two-sided)
                                        (taken as .05 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         402

Sample size per group (calculated)     201 201
Expected total number of events        80.4
Expected number of events per group    40.2 40.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  80.40000000000001
                  r(n) =  402
              r(power) =  .8
                 r(D2) =  40.2
                 r(n2) =  201
                 r(D1) =  40.2
                 r(n1) =  201


artbin, pr(.2 .2) margin(.1) onesided(1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (one-sided)
Power (designed)                       0.800

Total sample size (calculated)         402

Sample size per group (calculated)     201 201
Expected total number of events        80.4
Expected number of events per group    40.2 40.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  80.40000000000001
                  r(n) =  402
              r(power) =  .8
                 r(D2) =  40.2
                 r(n2) =  201
                 r(D1) =  40.2
                 r(n1) =  201


artbin, pr(.2 .2) margin(.1) onesided

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (one-sided)
Power (designed)                       0.800

Total sample size (calculated)         402

Sample size per group (calculated)     201 201
Expected total number of events        80.4
Expected number of events per group    40.2 40.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  80.40000000000001
                  r(n) =  402
              r(power) =  .8
                 r(D2) =  40.2
                 r(n2) =  201
                 r(D1) =  40.2
                 r(n1) =  201


artbin, pr(.2 .2) margin(.1) wald

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the wald test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         504

Sample size per group (calculated)     252 252
Expected total number of events        100.8
Expected number of events per group    50.4 50.4
------------------------------------------------------------------------------

scalars:
                  r(D) =  100.8
                  r(n) =  504
              r(power) =  .8
                 r(D2) =  50.40000000000001
                 r(n2) =  252
                 r(D1) =  50.40000000000001
                 r(n1) =  252


artbin, pr(.2 .2) margin(.1) noround

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         508.44

Sample size per group (calculated)     254.22 254.22
Expected total number of events        101.69
Expected number of events per group    50.84 50.84
------------------------------------------------------------------------------

scalars:
                  r(D) =  101.6870818492644
                  r(n) =  508.4354092463222
              r(power) =  .8
                 r(D2) =  50.84354092463222
                 r(n2) =  254.2177046231611
                 r(D1) =  50.84354092463222
                 r(n1) =  254.2177046231611


artbin, pr(.2 .2) margin(.1) power(.7)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.700

Total sample size (calculated)         402

Sample size per group (calculated)     201 201
Expected total number of events        80.4
Expected number of events per group    40.2 40.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  80.40000000000001
                  r(n) =  402
              r(power) =  .7
                 r(D2) =  40.2
                 r(n2) =  201
                 r(D1) =  40.2
                 r(n1) =  201

. /*
> * options expected to change SS
> foreach opt in {
>         di _n
>         dicmd `command' `opt'
>         if `returns' return list
>         assert !mi(r(n))
>         assert r(n) != `n'
> }
> */
. * options expected not to change SS 
. foreach opt in "power(.8)" "unfavourable" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) == `n'
  7. }


artbin, pr(.2 .2) margin(.1) power(.8)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
                                       Inferred by the program
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         510

Sample size per group (calculated)     255 255
Expected total number of events        102
Expected number of events per group    51 51
------------------------------------------------------------------------------

scalars:
                  r(D) =  102
                  r(n) =  510
              r(power) =  .8
                 r(D2) =  51
                 r(n2) =  255
                 r(D1) =  51
                 r(n1) =  255


artbin, pr(.2 .2) margin(.1) unfavourable

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          non-inferiority
Number of groups                       2
Favourable/unfavourable outcome        unfavourable
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 2
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Null hypothesis                        H0: pi2 - pi1 >= .1
Alternative hypothesis                 H1: pi2 - pi1 < .1

Anticipated event probabilities        0.200  0.200 

Alpha                                  0.050 (two-sided)
                                        (taken as .025 one-sided)
Power (designed)                       0.800

Total sample size (calculated)         510

Sample size per group (calculated)     255 255
Expected total number of events        102
Expected number of events per group    51 51
------------------------------------------------------------------------------

scalars:
                  r(D) =  102
                  r(n) =  510
              r(power) =  .8
                 r(D2) =  51
                 r(n2) =  255
                 r(D1) =  51
                 r(n1) =  255

. * options expected to cause error
. foreach opt in "favourable" "trend" {
  2.         di _n
  3.         dicmd cap noi `command' `opt'
  4.         assert _rc
  5.         di as input "Note: the above error message was expected"
  6. }


cap noi artbin, pr(.2 .2) margin(.1) favourable
artbin thinks your outcome is unfavourable. Please check your command. If your command is correct then consider usi
> ng the -force- option.
Note: the above error message was expected


cap noi artbin, pr(.2 .2) margin(.1) trend
Can not select trend option for a 2-arm trial
Note: the above error message was expected

. 
. 
. 
. 
. // 3 arms
. local command artbin`ver', pr(.4 .3 .2)

. dicmd `command'
artbin, pr(.4 .3 .2)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         303

Sample size per group (calculated)     101 101 101
Expected total number of events        90.9
Expected number of events per group    40.4 30.3 20.2
------------------------------------------------------------------------------

. local n=r(n)

. * options expected to increase SS
. foreach opt in "alpha(0.01)" "aratios(3 2 1)" "local" "power(.9)" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) > `n'
  7. }


artbin, pr(.4 .3 .2) alpha(0.01)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.010 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         435

Sample size per group (calculated)     145 145 145
Expected total number of events        130.5
Expected number of events per group    58 43.5 29
------------------------------------------------------------------------------

scalars:
                  r(D) =  130.5
                  r(n) =  435
              r(power) =  .8
                 r(D3) =  29
                 r(n3) =  145
                 r(D2) =  43.5
                 r(n2) =  145
                 r(D1) =  58
                 r(n1) =  145


artbin, pr(.4 .3 .2) aratios(3 2 1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       3:2:1
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         378

Sample size per group (calculated)     189 126 63
Expected total number of events        126
Expected number of events per group    75.6 37.8 12.6
------------------------------------------------------------------------------

scalars:
                  r(D) =  126
                  r(n) =  378
              r(power) =  .8
                 r(D3) =  12.6
                 r(n3) =  63
                 r(D2) =  37.8
                 r(n2) =  126
                 r(D1) =  75.60000000000001
                 r(n1) =  189


artbin, pr(.4 .3 .2) local

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       local
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         306

Sample size per group (calculated)     102 102 102
Expected total number of events        91.8
Expected number of events per group    40.8 30.6 20.4
------------------------------------------------------------------------------

scalars:
                  r(D) =  91.80000000000001
                  r(n) =  306
              r(power) =  .8
                 r(D3) =  20.4
                 r(n3) =  102
                 r(D2) =  30.6
                 r(n2) =  102
                 r(D1) =  40.8
                 r(n1) =  102


artbin, pr(.4 .3 .2) power(.9)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.900

Total sample size (calculated)         393

Sample size per group (calculated)     131 131 131
Expected total number of events        117.9
Expected number of events per group    52.4 39.3 26.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  117.9
                  r(n) =  393
              r(power) =  .9
                 r(D3) =  26.2
                 r(n3) =  131
                 r(D2) =  39.3
                 r(n2) =  131
                 r(D1) =  52.40000000000001
                 r(n1) =  131

. * options expected to decrease SS
. foreach opt in "alpha(0.1)" "condit" "wald" "noround" "trend" "doses(1 2 3)" "power(.7)" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) < `n'
  7. }


artbin, pr(.4 .3 .2) alpha(0.1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.100 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         243

Sample size per group (calculated)     81 81 81
Expected total number of events        72.9
Expected number of events per group    32.4 24.3 16.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  72.90000000000001
                  r(n) =  243
              r(power) =  .8
                 r(D3) =  16.2
                 r(n3) =  81
                 r(D2) =  24.3
                 r(n2) =  81
                 r(D1) =  32.4
                 r(n1) =  81


artbin, pr(.4 .3 .2) condit
 NOTE: As conditional has been selected local will be used.

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               Conditional test using Peto's
                                        approximation to the odds ratio
                                        using the score test
Local or distant                       local
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         285

Sample size per group (calculated)     95 95 95
Expected total number of events        85.5
Expected number of events per group    38 28.5 19
------------------------------------------------------------------------------

scalars:
                  r(D) =  85.5
                  r(n) =  285
              r(power) =  .8
                 r(D3) =  19
                 r(n3) =  95
                 r(D2) =  28.5
                 r(n2) =  95
                 r(D1) =  38
                 r(n1) =  95


artbin, pr(.4 .3 .2) wald

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the wald test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         288

Sample size per group (calculated)     96 96 96
Expected total number of events        86.4
Expected number of events per group    38.4 28.8 19.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  86.40000000000002
                  r(n) =  288
              r(power) =  .8
                 r(D3) =  19.2
                 r(n3) =  96
                 r(D2) =  28.8
                 r(n2) =  96
                 r(D1) =  38.40000000000001
                 r(n1) =  96


artbin, pr(.4 .3 .2) noround

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         300.38

Sample size per group (calculated)     100.13 100.13 100.13
Expected total number of events        90.11
Expected number of events per group    40.05 30.04 20.03
------------------------------------------------------------------------------

scalars:
                  r(D) =  90.11286822952962
                  r(n) =  300.3762274317654
              r(power) =  .8
                 r(D3) =  20.02508182878436
                 r(n3) =  100.1254091439218
                 r(D2) =  30.03762274317654
                 r(n2) =  100.1254091439218
                 r(D1) =  40.05016365756872
                 r(n1) =  100.1254091439218


artbin, pr(.4 .3 .2) trend

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Linear trend test: doses are           1, 2, 3

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         246

Sample size per group (calculated)     82 82 82
Expected total number of events        73.8
Expected number of events per group    32.8 24.6 16.4
------------------------------------------------------------------------------

scalars:
                  r(D) =  73.8
                  r(n) =  246
              r(power) =  .8
                 r(D3) =  16.4
                 r(n3) =  82
                 r(D2) =  24.6
                 r(n2) =  82
                 r(D1) =  32.8
                 r(n1) =  82


artbin, pr(.4 .3 .2) doses(1 2 3)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no
Linear trend test: doses are           1.00, 2.00, 3.00

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         246

Sample size per group (calculated)     82 82 82
Expected total number of events        73.8
Expected number of events per group    32.8 24.6 16.4
------------------------------------------------------------------------------

scalars:
                  r(D) =  73.8
                  r(n) =  246
              r(power) =  .8
                 r(D3) =  16.4
                 r(n3) =  82
                 r(D2) =  24.6
                 r(n2) =  82
                 r(D1) =  32.8
                 r(n1) =  82


artbin, pr(.4 .3 .2) power(.7)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.700

Total sample size (calculated)         243

Sample size per group (calculated)     81 81 81
Expected total number of events        72.9
Expected number of events per group    32.4 24.3 16.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  72.90000000000001
                  r(n) =  243
              r(power) =  .7
                 r(D3) =  16.2
                 r(n3) =  81
                 r(D2) =  24.3
                 r(n2) =  81
                 r(D1) =  32.4
                 r(n1) =  81

. * options expected not to change SS 
. foreach opt in "power(.8)" "unfavourable" {
  2.         di _n
  3.         dicmd `command' `opt'
  4.         if `returns' return list
  5.         assert !mi(r(n))
  6.         assert r(n) == `n'
  7. }


artbin, pr(.4 .3 .2) power(.8)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         303

Sample size per group (calculated)     101 101 101
Expected total number of events        90.9
Expected number of events per group    40.4 30.3 20.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  90.90000000000002
                  r(n) =  303
              r(power) =  .8
                 r(D3) =  20.2
                 r(n3) =  101
                 r(D2) =  30.3
                 r(n2) =  101
                 r(D1) =  40.40000000000001
                 r(n1) =  101


artbin, pr(.4 .3 .2) unfavourable

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.1.0 04jan2024)
------------------------------------------------------------------------------
A sample size program by Abdel Babiker, Patrick Royston, Friederike Barthel, 
Ella Marley-Zagar and Ian White
MRC Clinical Trials Unit at UCL, London WC1V 6LJ, UK.
------------------------------------------------------------------------------
Type of trial                          superiority
Number of groups                       3
Favourable/unfavourable outcome        not determined
Allocation ratio                       equal group sizes
Statistical test assumed               unconditional comparison of 3
                                        binomial proportions
                                        using the score test
Local or distant                       distant
Continuity correction                  no

Anticipated event probabilities        0.400 0.300 0.200

Alpha                                  0.050 (two-sided)
Power (designed)                       0.800

Total sample size (calculated)         303

Sample size per group (calculated)     101 101 101
Expected total number of events        90.9
Expected number of events per group    40.4 30.3 20.2
------------------------------------------------------------------------------

scalars:
                  r(D) =  90.90000000000002
                  r(n) =  303
              r(power) =  .8
                 r(D3) =  20.2
                 r(n3) =  101
                 r(D2) =  30.3
                 r(n2) =  101
                 r(D1) =  40.40000000000001
                 r(n1) =  101

. * options expected to cause error
. foreach opt in "margin(.1)" "ccorrect" /* "favourable" */ "onesided" {
  2.         di _n
  3.         dicmd cap noi `command' `opt'
  4.         assert _rc
  5.         di as input "Note: an error message was expected above"
  6. }


cap noi artbin, pr(.4 .3 .2) margin(.1)
Can not have margin with >2 groups
Note: an error message was expected above


cap noi artbin, pr(.4 .3 .2) ccorrect
Correction for continuity not allowed in comparison of > 2 groups
Note: an error message was expected above


cap noi artbin, pr(.4 .3 .2) onesided
One-sided not allowed in comparison of > 2 groups unless trend/doses specified
Note: an error message was expected above

. 
. 
. 
. // REPORT SUCCESS
. di as result _n "*************************************************************" ///
>         _n "*** ARTBIN HAS PASSED TESTING OF EVERY OPTION ***************" ///
>         _n "*************************************************************"

*************************************************************
*** ARTBIN HAS PASSED TESTING OF EVERY OPTION ***************
*************************************************************

. 
. 
. log close
      name:  <unnamed>
       log:  C:\ian\git\artbin\testing\artbin_test_every_option.log
  log type:  text
 closed on:   4 Jan 2024, 19:03:45
-------------------------------------------------------------------------------------------------------------------