-----------------------------------------------------------------------------------------------------------------
      name:  <unnamed>
       log:  c:\ian\git\artbin\testing\artbin_test_ltfu.log
  log type:  text
 opened on:  14 Nov 2023, 18:43:07

. /*
> artbin_test_ltfu.do
> new testing file for artbin
> IW 14/11/2023
> */
. pda

. 
. * evaluate ltfu() for power->n
. artbin, pr(.02 .02) margin(.02) noround

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.0.2 23may2023)
------------------------------------------------------------------------------
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:                    H0: pi2 - pi1 >= .02
Alternative hypothesis H1:             H1: pi2 - pi1 < .02

Anticipated event probabilities        0.020  0.020 

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

Total sample size (calculated)         1743.7366

Sample size per group (calculated)     871.86832 871.86832
Expected total number of events        34.87    
------------------------------------------------------------------------------

. local n=r(n)

. artbin, pr(.02 .02) margin(.02) noround ltfu(.1)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.0.2 23may2023)
------------------------------------------------------------------------------
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:                    H0: pi2 - pi1 >= .02
Alternative hypothesis H1:             H1: pi2 - pi1 < .02

Anticipated event probabilities        0.020  0.020 

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

Loss to follow up assumed:             10 %

Total sample size (calculated)         1937.4851

Sample size per group (calculated)     968.74257 968.74257
Expected total number of events        38.75    
------------------------------------------------------------------------------

. di r(n),`n'/0.9
1937.4851 1937.4851

. assert reldif(r(n),`n'/0.9) < 1E-7

. 
. 
. * evaluate ltfu() for n->power
. artbin, pr(.02 .02) margin(.02) noround n(1000) ltfu(.2)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.0.2 23may2023)
------------------------------------------------------------------------------
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:                    H0: pi2 - pi1 >= .02
Alternative hypothesis H1:             H1: pi2 - pi1 < .02

Anticipated event probabilities        0.020  0.020 

Alpha                                  0.050 (two-sided)
                                       (taken as .025 one-sided)
Power (calculated)                     0.547

Loss to follow up assumed:             20 %

Total sample size (designed)           1250

Sample size per group (designed)       625 625
Expected total number of events        20.00    
------------------------------------------------------------------------------

. local power=r(power)

. artbin, pr(.02 .02) margin(.02) noround n(800)

ART - ANALYSIS OF RESOURCES FOR TRIALS (binary version 2.0.2 23may2023)
------------------------------------------------------------------------------
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:                    H0: pi2 - pi1 >= .02
Alternative hypothesis H1:             H1: pi2 - pi1 < .02

Anticipated event probabilities        0.020  0.020 

Alpha                                  0.050 (two-sided)
                                       (taken as .025 one-sided)
Power (calculated)                     0.452

Total sample size (designed)           800

Sample size per group (designed)       400 400
Expected total number of events        16.00    
------------------------------------------------------------------------------

. di r(power),`power'
.45192744 .54683603

. assert reldif(r(power),`power') < 1E-7
assertion is false
r(9);

end of do-file
      name:  <unnamed>
       log:  c:\ian\git\artbin\testing\artbin_test_ltfu.log
  log type:  text
 closed on:  14 Nov 2023, 18:43:07
-----------------------------------------------------------------------------------------------------------------