/* This do-file loads a Stata-format dataset, generates a new variable, 
makes a graph, and saves the new dataset. The file also includes
commands to make your interactions with Stata easier (hopefully). */

*comments are denoted with an asterisk or with the slash and asterisk

#delimit; 	*tells Stata that a semicolon denotes the end of a line ; 		
		*allows for multi-line commands;
*note: don’t use semicolons directly in the command window;

clear;	*clears any existing data from memory;

capture log close;  *verifies that any log file is closed;

cd C:\mathcamp; *changes the directory to your own (you need to modify);

set memory 100m;		*allocates more computer memory to Stata; 

set more off;		*allows the program to keep running if output exceeds a page;

log using school.log, replace;	*creates a log file and saves in in the directory;

use school.dta;		*opens the file from the current directory;

describe; 			*lists the variables and their types;		

codebook;			*provides summary statistics for each variable;

sort read;			*sorts data in ascending order according to the variable;

count if prgtype=="vocati";   *counts number of vocational program students;

display 5+3;		*calculates 5+3;

mean read;			*gives the average reading score;

summarize science;	*shows summary statistics;

generate newscience = science+10; 	*creates a new variable which is the score + 10;

summarize newscience;	*shows summary statistics for the new variable;

graph twoway scatter read math; 	*creates a scatterplot; 

sort prgtype;		*sorts the observations, a prerequise for the by command;

by prgtype: summarize newscience; *for each program type, give mean reading score;

correlate read math;	*show the correlation coefficient between reading and math;

save newschool.dta, replace;	*saves a new version of the dataset, overwriting the old;

log close;			*closes the log file;