clear all

* --- Setting things up ---

* defining folder stucture
global data "/Users/hannastenhammar/Dropbox (Aalto)/PhD/teaching/Principles_of_Economic_Analysis/aapo/session four/data"
global output "/Users/hannastenhammar/Dropbox (Aalto)/PhD/teaching/Principles_of_Economic_Analysis/aapo/session four/output"

*This is the same fleed data set we used in excersise 2
import delimited "$data/fleed_puf_julk.csv", clear

gen year=1995+vuosi
rename svatva income
rename sukup sex
rename a18lkm nr_children 
table nr_children
replace nr_children = 3 if nr_children>=3 & nr_children!=. 
gen age=year-syntyv
rename shtun id

* Level of education
* see "Detailed description" here: https://www.stat.fi/en/luokitukset/koulutus/
tostring ktutk, replace
gen edul=substr(ktutk,1,1)
destring edul, replace
replace edul=1 if edul==. | edul<4
replace edul=2 if edul>=4 & edul<6
replace edul=3 if edul>=6 & edul!=.
label define edul 1 "Less/unknown", add
label define edul 2 "Secodary", add
label define edul 3 "More", add
label values edul edul

cd $output
reg income age, robust
eststo kakkonen1
reg income age sex , robust
eststo kakkonen2
reg income age sex i.edul, robust
eststo kakkonen3
reg income age sex i.edul i.year , robust
eststo kakkonen4
esttab kakkonen* using "regression_table.rtf", label star(* 0.1 ** 0.05 *** 0.01)  replace
esttab kakkonen* using "regression_table_2.rtf", label star(* 0.1 ** 0.05 *** 0.01)  replace drop(*.year)

xtset id year 

xtreg income age, fe vce(cluster id)