/**************************************************** 
ECO375 Example 
Topic 3: Simple Regression Model
************************************************/
clear all 
set more off 

use http://bigblue.depaul.edu/jlee141/econdata/eco375/state_cig_data
* dscribe data
desc

* generate real taxes
gen real_tax=(state_tax+federal_tax)/cpi

* get means of real tax and per capita consumption
sum packs_pc real_tax

* get correlation coefficient
corr packs_pc real_tax

* get regression estimate
reg packs_pc real_tax

* plot the data with regression line
tw (scatter packs_pc real_tax) (lfit packs_pc real_tax)

* Generate Yhat and ei
predict yhat
predict ei, resid
list real_tax packs_pc yhat e in 1/10
tw (scatter packs_pc real_tax) (scatter yhat real_tax)

* Check the residuals for normality

sum ei
hist ei 
pnorm ei

scatter ei real_tax, yline(0)