/* ---------------------------------------
Administrative commands 
------------------------------------------*/

capture log close				/* Opens log file */
log using crdata, replace		/* Creates log file crdata */
set more off				

/* ---------------------------------------
Create data set 
------------------------------------------*/

/* Reads data set in states.out */

insheet using "states.out", tab clear  

/*Check if data loaded right by looking at the first 10 lines in the data set */

list state csat expense percent high college in 1/10

/* Create variables */


generate NCdummy = state=="North Carolina"		/* Dummy for NC state = 1*/

generate South_East = region=="South" | region=="Midwest" /* Dummy for states in South and Midwest 
										 The | symbols tells stata to put a 1 if
										 region equals Sout or Midwest */
generate West = region=="West"

generate College_Dummy = college>10		/* Dummy for states with % adults w/college degree above 10% */


/* Label variables */

label variable state "State"
label variable csat "Mean composite SAT score"
label variable expense "Per pupil expenditures prim&sec"
label variable percent "% HS graduates taking SAT"
label variable high "% adults w/HS diploma"
label variable college "% adults w/college degree"
label variable region "Geographical region"
label variable NCdummy "Dummy 1 if NC state"
label variable South_East "Dummy 1 if Sout or East state"
label variable West "Dummy  1 if West state"
label variable College_Dummy "Dummy equal to 1 if state college>10%"

keep state csat expense percent high college region NCdummy South_East West College_Dummy 

/* Summarize data */

summarize 


/* Save data set in stata format */

save states, replace 

/* ---------------------------------------
 Close log file
------------------------------------------*/
log close
exit