********************************************************************************
*                                                                              *
*       Program: Class2.do                                                     *
*       Purpose: Illustrate a basic batch program                              *
*                                                                              *
********************************************************************************;
********************************************************************************
*                                                                              *
*       Reset "end-of-command" delimiter using the #delimit command            *
*       #delimit is a Stata preprocessor command. #commands do not generate a  *
*       return code, nor do they generate ordinary Stata errors.               *
*                                                                              *
********************************************************************************;
#delimit ;

********************************************************************************
*                                                                              *
*       Clear the memory and change working directory                          *
*                                                                              *
********************************************************************************;
cd "C:\stemp";
clear;

********************************************************************************
*                                                                              *
*       Start log and open data set of interest: Caschool.do                   *
*                                                                              *
********************************************************************************;
log     using class2.log,replace;
set     more off;
use     caschool.dta;

********************************************************************************
*                                                                              *
*       Describe the dataset using the "describe" command                      *
*       Command format: describe [varlist] [, memory_options]                  *
*       Command purpose: produces a summary of the dataset in memory or of the *
*                        data stored in a Stata-format dataset.                *
*                                                                              *
********************************************************************************;
describe;

********************************************************************************
*                                                                              *
*       Construct summary statistics for the dataset using "summarize" command *
*       Command format: summarize [varlist] [if] [in] [weight] [, options]     *
*       Command purpose: summarize calculates and displays a variety of        *
*                        univariate summary statistics.  If no varlist is      *
*                        specified, summary statistics are calculated for all  *
*                        the variables in the dataset.                         *
*                                                                              *
********************************************************************************;
summarize;
summarize testscr str, detail;
summarize testscr if str>20;
summarize testscr if str<=20;

********************************************************************************
*                                                                              *
*       Generate discrete counterparts to testscr and str variables            *
*       Command format:  generate [type] newvar[:lblname] =exp [if] [in]       *
*       Command purpose: generate creates a new variable. The values of the    *
*                        variable are specified by =exp.                       *
*                                                                              *
********************************************************************************;
generate hightscr = testscr>654;
generate highstr  = str>20;

********************************************************************************
*                                                                              *
*       Generate cross tabulation table for discrete variables                 *
*       Command form: tabulate varname1 varname2 [if] [in] [weight] [, options]*
*       Command purpose: tabulate produces two-way tables of frequency counts, *
*                        along with various measures of association            *
*                                                                              *
********************************************************************************;
tabulate hightscr highstr;

********************************************************************************
*                                                                              *
*       Investigate correlation among variables "correlation" command          *
*       Command format:  correlate [varlist] [if] [in] [weight] [, options]    *
*       Command purpose: The correlate command displays the correlation matrix *
*                        or covariance matrix for a group of variables or for  *
*                        the coefficients of the most recent estimation. If    *
*                        varlist and _coef are not specified, the matrix is    *
*                        displayed for all variables in the data.              *
*                                                                              *
********************************************************************************;
cor      testscr str;

********************************************************************************
*                                                                              *
*       Graph relationship between student teach ratio and test scores         *
*       Command format:  [graph] twoway plot [if] [in] [, twoway_options]      *
*       Command purpose: twoway is a family of plots, all of which fit on      *
*                        numeric y and x scales.                               *
*                                                                              *
********************************************************************************;
twoway (scatter testscr str);

********************************************************************************
*                                                                              *
*       Close log file, clear memory and exit Stata                            *
*                                                                              *
********************************************************************************;
log close;
clear;
exit;