//indicating the path and working folder

cd "C:\Users\Aki\Documents\stata"

log using feb7


******Exploring data part 2. Data manipulation********************

***DISTRIBUTIONAL ANALYSIS*****
sysuse auto, clear
su price
su price, detail
inspect price

**formal test for normality
sktest price
//Shapiro-Wilk test for normality
//H0: the distribution is normal
//With p-value close to 0, we are rejecting the H0: the distribution is NOT normal

sktest length
//at 5% significance level, we fail to reject H0 (the distribution is normal)
//at 1% level, we reject H0 (the distribution is NOT normal)

su length, detail


********DATA MANIPULATION************
** 1. RECODING*******
tab rep78

//want to merge categories 1 and 2 together, to have 4 categories instead of 5 categories for the variable rep78

help recode
recode rep78 1 2 = 1
tab rep78

sysuse auto, clear

recode rep78 (3=2) (4=3) (5=4)
tab rep78

tab mpg
recode mpg (12/19 = 1) (20/29 = 2) (30/41 = 3), gen(mpgcat)
tab mpgcat
//can be helpful to create a categorical variable out of descrete variable

** 2. GENERATING A NEW VARIABLE******
help gen

**generate a constant
gen constant = 1

**generating a new variable using some old variable
//new price variable which is price divided by the weight of a car
gen newprice = price / weight

gen pricesquared = price*price
gen pricesquared1 = price^2

gen price1000 = price + 1000

help functions

gen ln_price = log(price)

***replace command****
sysuse auto, clear
tab rep78
//want to merge categories 1 and 2, and have 4 categories instead of 5
gen rep78recoded = 1
//if rep78= 1, you don't want to change anything, rep78recoded = 1
//if rep78=2, you don't want to change anything, rep78recoded = 1
replace rep78recoded = 2 if rep78==3
replace rep78recoded = 3 if rep78==4
replace rep78recoded = 4 if rep78==5
tab rep78recoded
//!!! be careful with missing values
replace rep78recoded = . if rep78 ==.

**!! use replace together with generate command***
//unlike recode command, in replace you can use logical and mathematical functions
translate feb7.smcl feb7.log 
log close