clear;
# delimit ;
cap log close;
*************************************************************;
* Caschool.do
* Prepare Final Data for Text book
* California School District Data
*************************************************************;
log using ch4.log,replace;
set more 1;
***********************************;
*** Modify the next line so that the path is correct for your data;
use caschool.dta;
*;
*;
* Decription of Data;
* dist_code -- district Code;
* Read_scr  -- avg Reading Score;
* Math_scr  -- avg Math Score;
* County   --  county;
* District -- District;
* gr_span -- grade span of district;
* enrl_tot -- total enrollment;
* teachers -- number of teachers;
* computer -- number of computers;
* testscr -- avg test score (= (read_scr+math_scr)/2 );
* comp_stu -- computers per student ( = computer/enrl_tot);
* expn_stu -- expentitures per student;
* str -- student teacher ration (teachers/enrl_tot);
* el_pct -- percent of English Learners;
* Meal_pct -- Percent qualifying for reduced-price lunch;
* clw_pct -- Percent qualifying for CalWorks;
* aving -- district average income (in $1000's);

**************************************************************;
***** Table 4.1 ******
**************************************************************;
summarize str str;
pctile pct_tsc = testscr, nq(20) genp(pctx);
pctile pct_str = str, nq(20);
list pctx pct_str pct_tsc in 1/20;
**************************************************************;
***** Correlation ******
**************************************************************;
cor str testscr;
**************************************************************;
***** Equation 4.11 ******
**************************************************************;
reg testscr str, r;
**************************************************************;
***** Equation 4.33 ******
**************************************************************;
gen d = (str<20);
reg testscr d, r;
log close;
clear;
exit;