*! pyramid tutor v1.02 march 1999. JM.Lauritsen
*
set output error
version 2.1
noisily tut_chk pyramid
set display page 23
set more 1
if "$S_OS"=="Windows" {
local wwait "tut_wait"
`wwait'
}
capture program drop _yesno
program define _yesno
macro define answ
while lower("%answ")!="y" & lower("%answ")!="n" {
di in gr "%_1? (" in wh "y" in gr "/" in wh "n" in gr ")" /*
*/ _col(50) _request(answ)
}
end
#delimit ;
di _n(3) in wh
" ___ ____ ____ ____ ____ tm" _n
" /__ / ____/ / ____/" _n
"___/ / /___/ / /___/ Population Pyramids and reshape" _n
"----------------------------------------------------" _n(2) ;
di in gr "Tutorial for Stata version 5+ made by "
in yel "Jens M.Lauritsen, v1.02 " _n(2)
in gre "Stata is obtaining its input from the disk," _n
" but" in wh " is " in gre "producing results as you watch."
_n(2)
_n " output presented like this: " _n in wh ". text" _n in gre " is the command stata received"_n
_n(2)
"This tutorial can be discontinued at any time by pressing "
in wh "Break" in gr "."
_n
;set more 0; more ; set more 1;
di
_n in yel " When You understand the commands in this file, You will be able to: " _n
in wh _n " - read datafile and make simple lists of contents"
_n " - define new variables "
_n " - change file format from long to wide format"
_n " - convert a string to a numerical variable"
_n " - draw population pyramids"
_n(3) in yel " NOTE " in wh "Hbar.ado developed by N.Cox"
_n in yel " must be installed for the population pyramids to be plotted"
_n(2) " fyn.dta should reside in %path " _n(3);
#delimit cr
global F5 "tutorial contents;"
global F6 "tutorial intro;"
global F7 "tutorial pyramid;"
#delimit ;
di in gr "When you are ready to continue, press the space bar." ;
set more 0; more ; set more 1;
drop _all ;
label drop _all ;
di in wh _n(4)
"Population pyramids" _n
"--------------------" _n ;
di in wh ".use fyn ,clear";
qui use fyn,clear;
di in wh _dup(79) "-" _n
in gr "We use population data from Funen County 1998"
in wh ". Lets look at some of the data" in gr " :" _n
in wh _dup(79) "-" _n(2)
;
di in wh ". list c1-c5 c52 c100 c101 c102, nodisplay";
noi list c1-c5 c52 c100 c101, nodisplay;
di _n(2) in wh _dup(79) "-" _n
in gre " We see 5 observations and a top line with variable names across. "
_n(2)
in gre " To understand data you must understand the above display - it is simple " _n
in gre " We have 5 rows of data 1 2 3 4 5 and in each variables c1 c2 c3 .... c101 "_n
_n
in yel " the value of c3 in row 3 is what ? " in yel " the answer is " in wh "3005" _n
in yel " the value of c1 in row 1 is what ? " in yel " the answer is " in wh "Age"_n
_n
in wh " This is called a " in wh "wide" in gre " format"
in wh " Notice: " in yel "many variables few observations" _n(2)
" Only some of the variables are shown. You could scroll the variables"_n
" window and see the names of the other variables" ;
set more 0 ; more ; set more 1 ;
di in wh _dup(79) "-" _n;
di in wh "Lets look at data for males: (age 2-61 omitted)" _n
in wh". list c1-c3 c63-c102";
preserve;
drop in 4/5;
drop in 1/2;
noi list c1-c3 c63-c102 ;
restore;
di in wh _dup(79) "-" _n
in gre " We see the data for males one variable for each age, c102 is the total "_n(3) ;
set more 0 ; more ; set more 1 ;
di in wh _dup(79) "-" _n "Let's look at the data again, as before and by observation " _n
in wh _dup(79) "-" _n(2);
di in wh ". list c1-c5 c52 c100-c101 in 3/4, nodisplay ";
noi list c1-c5 c50 c100 c101 in 3/4, nodisplay;
di in wh _n ". list c1-c5 c52 c100-c101 in 3/4";
noi list c1-c5 c52 c100-c101 in 3/4 ;
di in wh _dup(79) "-" _n " We only show observation 3+4: "in wh" in 3/4"
in gre " note change of display with"in wh " ,nodisplay" _n(2)
in wh _dup(79) "-";
set more 0 ; more ; set more 1 ;
di in wh _dup(79) "-" _n
in gre " We want to add a variable indicating the sex " _n
" with values 1=male and 2=female and appropriate labels: " _n
in wh _dup(79) "-" _n;
di in wh ". gen sex = 1 in 3";
noi gen sex = 1 in 3;
di in wh ". replace sex = 2 in 4";
noi replace sex = 2 in 4;
di in wh ". list sex c1-c6,nodispl";
noi list sex c1-c6,nodispl;
di in wh _dup(79) "-" _n
in yel " the value of sex in row 3 is what ? " in yel " the answer is " in wh "1" _n
in yel " the value of sex in row 1 is what ? " in yel " the answer is " in wh "."_n
in yel " Period " in whi "." in yel " is STATA's value for unknown or missing"
_n;
set more 0 ; more ; set more 1 ;
di in gre " We have the variable and wish to add " in wh " labels"_n
in wh _dup(79) "-" _n;
di in wh ". label define sexlbl 1 male 2 female";
noi label define sexlbl 1 male 2 female;
di in wh ". label value sex sexlbl";
noi label value sex sexlbl;
di in wh ". list sex c1-c6,nodispl";
noi list sex c1-c6,nodispl;
di in wh _dup(79) "-" _n
in gre " Note the change from 1 and 2 at variable sex to labelled value"_n
; set more 0 ; more ; set more 1 ;
di in yel " What is the difference between variables " in wh "sex " in yel "and"
in wh " c1 " in yel "?" _n
in wh _dup(79) "-" ;
set more 0 ; more ; set more 1 ;
* describe and variable type;
di _n in wh ". describe c1 sex " _n;
noi d c1 sex ;
di _n in wh _dup(79) "-" _n
in wh " c1" in gre " is a " in wh "string (str14 %14s)" in gre " of length 14 characters"_n(2)
in wh " Sex" in gre " is a " in wh "numeric" in gre " of type " in wh "float (%9.0g)"
in gre " values are defined by " in wh "sexlbl" _n(2) " We are also told the variable number, for sex is " in wh "103" _n(2);
di in wh _dup(79) "-" ;
di in yel " If you do not know the difference between a string and a numerical variable" _n
in yel " look in the help menu now." _n(2) " Version 5: " in wh "help datatypes" _n in yel " Version 6: " in wh "Stata Command datatypes "_n
; set more 0 ; more ; set more 1 ;
di in gre " Another check of the variable " in wh "sex" in gre " is the command " in wh "codebook"
_n in wh _dup(79) "-" _n;
di in wh ". codebook sex";
noi codebook sex;
di _n in wh _dup(79) "-"
; set more 0 ; more ; set more 1 ;
di in wh _dup(79) "-" _n(2)
in yel " Now we want to change the structure of the file. " _n(2)
in gre " Instead of one observation for all males and one observation for all females" _n(2)
" We want many observations with three variables: " in wh " sex, age and population count" _n(2)
in gre " STATA facilitates this by transposing the data from : " in wh " wide to long format " _n(2)
in gre " In long format, one has few variables and many observations" _n
in gre " In wide format, one has few observations and many variables";
di _n in wh _dup(79) "-" _n(2);
; set more 0 ; more ; set more 1 ;
di _n(2) in yel " Step " in wh " 1 " in gre ", delete all observations except the two with male and female data" _n
in wh ". drop if sex == .";
noi drop if sex == .;
di _n in wh _dup(79) "-" _n(2);
di in yel " Step " in wh " 2 " in gre ", delete the variable "in wh "c" in gre ", which contained descriptions" ;
drop c1;
di in wh ". drop c1" _n;
di in gre " Step " in wh " 3 " in gre ", generate a variable indicating observation number " ;
di in wh ". gen id = _n" _n;
noi gen id = _n;
di in wh ". list id sex c2 c3 c4 ";
noi list id sex c2 c3 c4 ;
;set more 0 ; more ; set more 1 ;
di _n(2) in yel "Before the actual reshape, assure that you have the latest version of reshape" _n
_n in yel "The syntax for the command reshape changed by mid 1998"
_n in yel "therefore we check the version of " in wh "YOUR" in yel " reshape.ado"
_n in wh _dup(79) "-" _n(2)
_n(2) in wh ". which reshape" _n;
noi which reshape;
#d cr;
di _n(2) " This version number indicates YOUR reshape.ado" _n(2)
_yesno " Please confirm that your reshape.ado is at least version 4.0.3" in wh " y " in yel "or" in wh " n"
if lower("%answ")!="y" {
di in yel "Update your version of Stata from www.stata.com, and restart this tutorial"_n
di in yel "Try " in wh "help update lookup update search update" _n
exit
capture }
di _n(3)
#d ;
;set more 0 ; more ; set more 1 ;
di _n in yel " Step " in wh " 4 " in gre ", reshape data. Two new variables, c with counts and j for age" _n(2)
in yel " Note the change (soon) in the variables window" _n;
di in wh ". reshape long c, i(id) j(age)" ;
noi reshape long c, i(id) j(age) ;
noi sort sex age;
di in wh _dup(79) "-" _n(2)
in gre " Data has been changed to few variables and many observations " in wh " how many ? " _n
;set more 0 ; more ; set more 1 ;
di in wh ". list in 1/4";
noi list in 1/4;
di _n in wh ". list in 1/4, nolabel";
noi list in 1/4,nolabel;
di in wh _dup(79) "-" _n
in yel " the value of sex in row 3 is what ? " in yel " the answer is " in wh "1" _n
in yel _n " this value has the label " in wh "male" _n
in yel " by " in whi ",nolabel" in yel " we see the value not the label"
_n;
set more 0 ; more ; set more 1 ;
di in wh _dup(79) "-" _n
in gre " Let us look at the data again - how many variables ? " _n
_n in wh ". describe";
noi d;
di _n in gre " We notice that variable " in wh "c" in gre " is string " _n
; set more 0 ; more ; set more 1 ;
#d cr;
di in wh _dup(79) "-"
di in yel " Step " in wh " 5 " in gre ", age should be 0 in first and 99 in last observation" _n(2)
di in wh ". list if age < 5 | age > 99 "
noi list if age < 5 | age > 99
set more 0
more
set more 1
di in wh ". replace age = age-2"
noi replace age = age-2
di in wh _n ". list if age < 3 | age > 97"
noi list if age > 97 | age < 3
di _n in gre "Note that age is correct, but observation 101 and 202 contain totals " _n
#d ;
set more 0 ; more ; set more 1 ;
di _n in wh ". drop if age > 99";
drop if age > 99;
di _n in yel " Step " in wh " 6 " in gre ", calculate variables for the population pyramids " _n
" With the function " in wh "real(c)" in gre " we can convert from string to numeric" _n(2);
di _n in wh ". generate count = real(c)";
gen count = real(c);
di in wh ". generate males = -real(c) if sex == 1";
gen males = -real(c) if sex == 1;
di in wh ". generate females = real(c) if sex == 2";
gen females = real(c) if sex == 2;
set more 0 ; more ; set more 1 ;
di _n in wh ". list sex c count males females in 1/3";
noi list sex c count males females in 1/3,nodisplay;
di _n in wh ". list sex c count males females in 190/193";
noi list sex c count males females in 190/193,nodisplay;
set more 0 ; more ; set more 1 ;
di _n in wh ". describe ";
noi d ;
set more 0 ; more ; set more 1 ;
di _n in yel " Step " in wh " 6a " in gre ", Let us save the file (replace if existing)" _n
_n in wh ". save long, replace" _n(3);
save long, replace;
di in yel " Step " in wh " 7 " in gre ", We want to see the counts ! " _n
" First as a scatterplot with age, then by sex and finally pyramids" _n ;
set more 0 ; more ; set more 1 ;
di in wh ". graph count age";
gra count age;
set more 0 ; more ; set more 1 ;
sort sex;
di in wh ". sort sex";
di in wh ". graph count age, by(sex) total ylabel";
graph count age, by(sex) total;
set more 0 ; more ; set more 1 ;
di _n(2) in wh ". hbar males females";
hbar males females;
di _n in yel " We are not satisfied. " _n
" Labels are awfull and we should have males and females side by side " _n
" Not under each other" in gre " We must do more to the data" ;
set more 0 ; more ; set more 1 ;
di _n in yel " The trick here is to copy the female data to the observations with the " _n
" male data. Look below how to do that" _n
in wh ". list sex age males females in 1/3";
noi list sex age males females in 1/3;
di in wh ". list sex age males females in 101/103";
noi list sex age males females in 101/103;
set more 0 ; more ; set more 1 ;
di _n in wh " _n+100 " in yel "means: value from current observation + 100" _n(2) ;
di in wh ". replace females = real(c[_n+100]) if sex == 1";
replace females = real(c[_n+100]) if sex == 1;
di _n(2) in gre " Let us check the calculation with" in wh " list" _n(2) in wh ". list id age c males females if age < 10";
noi list id age c males females if age < 3;
di " Let us try the pyramid again ";
di _n(2) in wh ". hbar males females";
hbar males females;
di _n in yel " Much better but still: We are not satisfied. " _n
" Labels are awfull and we do not need observations above number 100 " _n(2)
;
set more 0 ; more ; set more 1 ;
di in wh ". drop in 101/200";
drop in 101/200;
di in wh ". drop c count";
drop c count;
di in wh ". generate lbl = age";
gen lbl = age;
* next line thanks to N.Cox:;
di in wh ". replace lbl = . if mod(age,10) > 0" ;
replace lbl = . if mod(age,10) > 0 ;
di in wh ". list in 1/11, nodisplay";
noi list age males females lbl in 1/11, nodispl;
di _n in wh ". hbar males females, l(lbl)" ;
hbar males females, l(lbl);
di " Age labels could be improved and we need titles plus x axis labels";
set more 0 ; more ; set more 1 ;
di in wh ". gen str2 slbl = string(lbl)" ;
gen str2 slbl = string(lbl);
replace slbl = " " if lbl == . ;
di in wh ". replace slbl = " " if lbl == . ";
di in wh ". hbar males females, l(slbl) lap /*" _n
"*/ xla(-4250,-4000,-3000,-2000,-1000,0,1000,2000,3000,4000,4250) /*" _n
"*/ ttick t(Demographic composition, 1998) /*" _n
"*/ barfrac(0.85) xline(-1000,-2000,-3000,0,1000,2000,3000)";
hbar males females, l(slbl) lap /*
*/ xla(-4250,-4000,-3000,-2000,-1000,0,1000,2000,3000,4000,4250) /*
*/ ttick t(Demographic composition, 1998) /*
*/ barfrac(0.85) xline(-1000,-2000,-3000,0,1000,2000,3000);
di _n " Let us save the graph for reuse, note the added lines" _n;
set more 0 ; more ; set more 1 ;
di _n in wh ". hbar males females, l(slbl) lap /*" _n
"*/ xla(-4250,-4000,-3000,-2000,-1000,0,1000,2000,3000,4000,4250) /*" _n
"*/ ttick t1(Demographic composition, 1998) t2(Funen County, Denmark) /*" _n
"*/ barfrac(0.85) xline(-1000,-2000,-3000,0,1000,2000,3000) /* " _n
"*/ saving(pyramid,replace)";
hbar males females, l(slbl) lap /*
*/ xla(-4250,-4000,-3000,-2000,-1000,0,1000,2000,3000,4000,4250) /*
*/ ttick t1(Demographic composition, 1998) t2(Funen County, Denmark)/*
*/ barfrac(0.85) xline(-1000,-2000,-3000,0,1000,2000,3000) saving(pyramid,replace);
di _n " Let us make a new graph which " _n "check the difference in number of males and females ";
set more 0 ; more ; set more 1 ;
di in wh ". gen dif = males - (-females)";
gen dif = males - (-females);
di in wh ". label var dif Male Female ";
label var dif "Male Female ";
di _n in wh ". hbar dif, l(slbl) lap /*" _n
"*/ xla(-500,-250,0,250,500) t2(Diffence N males - N of females) /*" _n
"*/ ttick t1(Female preponderance with age) /*" _n
"*/ barfrac(0.85) xline(-250,0,250,500)" ;
hbar dif, l(slbl) lap /*
*/ xla(-500,-250,0,250,500) t2(Diffence N males - N of females) /*
*/ ttick t1(Female preponderance with age) /*
*/ barfrac(0.85) xline(-250,0,250,500);
#d cr;
di in wh _dup(79) "-" _n(2)
di in yel " You have seen these commands, try " in wh " help" in yel " if you want to repeat" _n(2)
di in wh " list " in gre " listing cases "
di in wh " list in 1/3, nodisplay" in gre " listing subsamples and changing output"
di in wh " generate " in gre " define new variabes"
di in wh " replace .. if x < 1 " in gre " replace value with new value "
di in wh " codebook " in gre " simple table with definitions"
di in wh " label " in gre " adding descriptions to variables"
di in wh " reshape " in gre " change data from wide to long"
di in wh " graph x y, saving() " in gre " graphing with optional save"
di in wh " graph x y, by(z) total" in gre " conditional graphing"
di in wh " hbar " in gre " horizontal bar graphs"
di in wh " save " in gre " saving changed data" _n(2)
di in wh _dup(79) "-" _n
di "Repeat this tutorial: press F7 - list of tutorials press: F6 or F5" _n
exit