/***************************************************************************************
ECO304 DePaul University
Jin Man Lee

An Example of Population, Sample and Sample Mean Distribuion using House Price in Chicago
The house prices are the listing prices at MLS in 2017. 
Consider the whole listing price is the population.  
****************************************************************************************/

clear all
use https://bigblue.depaul.edu/jlee141/econdata/eco375/mls2017chi.dta
summarize hprice 
keep hprice 
hist hprice, xline(279358) title(Distribution of All House Price N=48523) name(g1,replace)  
save mls2007, replace 
sample 1000, count 
summarize hprice 
hist hprice, xline(279358) title(Sample Distribution of House Price n=1000) name(g2,replace)  
graph combine g1 g2, col(1)

/* Sample Size of 25 */
program housep, rclass
drop _all
use mls2017 
sample 25, count
summarize hprice
return scalar meanx = r(mean)
end

simulate xbar = r(meanx), reps(500) : housep
sum xbar
hist xbar, xline(279358) bin(15) name(sg1,replace)  title(A. Sample Mean Distribution from Sample Size of 25)
program drop housep 

/* Sample Size of 100 */
program housep, rclass
drop _all
use mls2017 
sample 100, count
summarize hprice
return scalar meanx = r(mean)
end

simulate xbar = r(meanx), reps(500) : housep
sum xbar
hist xbar, xline(279358) bin(15) name(sg2,replace) title(B. Sample Mean Distribution from Sample Size of 100)
program drop housep 


/* Sample Size of 2500 */
program housep, rclass
drop _all
use mls2017 
sample 2500, count
summarize hprice
return scalar meanx = r(mean)
end

simulate xbar = r(meanx), reps(500) : housep
sum xbar
hist xbar, xline(279358) bin(15) name(sg3,replace) title(C. Sample Mean Distribution from Sample Size of 2500)
program drop housep 

graph combine g1 g2 sg1 sg2 sg3, col(1) xcommon xsize(7) ysize(10)