**************************************************************
* cfkids.do                                                  *
**************************************************************
*                                                            *  
* PURPOSE:  analysis of FEV1 among CF kids                   *
*                                                            *
* AUTHOR:  P. Heagerty                                       *
*                                                            *
* DATE:  31 March 2005                                       *
*        04 April 2006                                       *  
**************************************************************

infile id fev1 age gender pseudoA f508 pancreat using NewCFkids.data

*
*  ID       = patient id
*  FEV1     = percent-predicted forced expiratory volume in 1 second
*  AGE      = age (years)
*  GENDER   = sex (1=male, 2=female)
*  PSEUDOA  = infection with Pseudo Aeruginosa (0=no, 3=yes)
*  F508     = genotype (1=homozygous, 2=heterozygous, 3=none)
*  PANCREAT = pancreatic enzyme supplmentation (0,1=no, 2=yes)
*


label variable age "Age (years)"

recode gender 1=0 2=1
label variable gender "female"

recode pseudoA 3=1

recode pancreat 1=0 2=1

recode f508 1=2 2=1 3=0

save NewCFkids, replace

***
*** some exploratory data analysis -- observation level
***
  
summarize  fev1

gen y8 = fev1
recode y8 (min/max=.) if age > 8.75
recode y8 (min/max=.) if age < 7.25

gen y10 = fev1
recode y10 (min/max=.) if age > 10.75
recode y10 (min/max=.) if age < 9.25

gen y12 = fev1
recode y12 (min/max=.) if age > 12.75
recode y12 (min/max=.) if age < 11.25

gen y14 = fev1
recode y14 (min/max=.) if age > 14.75
recode y14 (min/max=.) if age < 13.25

gen y16 = fev1
recode y16 (min/max=.) if age > 16.75
recode y16 (min/max=.) if age < 15.25

gen y18 = fev1
recode y18 (min/max=.) if age > 18.75
recode y18 (min/max=.) if age < 17.25

gen y20 = fev1
recode y20 (min/max=.) if age > 20.75
recode y20 (min/max=.) if age < 19.25

***** the following creates a single record per kid:
  
collapse (mean) f508 gender y8 y10 y12 y14 y16 y18 y20, by(id)


***** look at means over these ages:

summarize

sort f508
by f508: summarize

sort gender
by gender: summarize


***** information on correlation

corr y8 y10 y12
corr y12 y14 y16
corr y16 y18 y20 

graph twoway (scatter y14 y8)
graph export c:/COURSES/CORRELATED/Intro/cfkids-y14y8.ps, as(eps) replace
graph twoway (scatter y12 y8)
graph export c:/COURSES/CORRELATED/Intro/cfkids-y12y8.ps, as(eps) replace
graph twoway (scatter y10 y8)
graph export c:/COURSES/CORRELATED/Intro/cfkids-y10y8.ps, as(eps) replace

graph twoway (scatter y16 y10)
graph export c:/COURSES/CORRELATED/Intro/cfkids-y16y10.ps, as(eps) replace
graph twoway (scatter y14 y10)
graph export c:/COURSES/CORRELATED/Intro/cfkids-y14y10.ps, as(eps) replace
graph twoway (scatter y12 y10)
graph export c:/COURSES/CORRELATED/Intro/cfkids-y12y10.ps, as(eps) replace

***
*** some exploratory data analysis -- person level
***

clear

use NewCFkids

collapse (min) age f508 gender, by(id)

tab f508

tab gender

tab f508 gender


***
*** add the age-at-entry to the data
***

gen age0 = age

drop age f508 gender

***** save data with just ID and age0
save NewCFage0, replace

***** return to original data, and merge
clear

use NewCFkids

sort id

merge id using NewCFage0

list in 1/4


***** create ageL and save
gen ageL = age - age0

save NewCFkids, replace

***
*** plot some individual series
***

graph twoway (lowess fev1 age) (scatter fev1 age) ///
      if (id<=101799), by(id)
graph export c:/COURSES/CORRELATED/Intro/cfkids-series1.ps, as(eps) replace

graph twoway (lowess fev1 age) (scatter fev1 age) ///
      if (id>101799 & id<=103399), by(id)
graph export c:/COURSES/CORRELATED/Intro/cfkids-series2.ps, as(eps) replace

***
*** plot some fitted lines
***

graph twoway (lfit fev1 age) (scatter fev1 age) ///
      if (id<=101799), by(id)
graph export c:/COURSES/CORRELATED/Intro/cfkids-lines1.ps, as(eps) replace

graph twoway (lfit fev1 age) (scatter fev1 age) ///
      if (id>101799 & id<=103399), by(id)
graph export c:/COURSES/CORRELATED/Intro/cfkids-lines2.ps, as(eps) replace