* NOTE: The first line of any Stata do file should contain a 'log using' command
* to open/start a text-format Stata log file where all the results of the Stata commands
* in this do file are recorded.
*
log using 452note08_stata11_exercise1_f11.log, replace
version
set more off

* To have Stata execute this do file, enter the following Stata command
* on the Stata command line:
*
*  do 452note08_stata11_exercise1_f11.txt
*
* Do file: 452note08_stata11_exercise1_f11.txt 
* Log file: 452note08_stata11_exercise1_f11.log
*
* Input dataset: wage1_econ452_stata11.dta
* Output dataset: wage1_econ452_stata11.dta (re-saved)
*
* Read input dataset 'wage1_econ452_stata11.dta' into memory
use wage1_econ452_stata11, clear
describe, short
describe
summarize

* Check gender indicators 'f' and 'm'
tab1 f m, missing
tab2 f m, missing

* Check industry dummy variables
*
tab1 industry, missing
tab2 industry ind1, missing col
tab2 industry ind2, missing col
tab2 industry ind3, missing col
tab2 industry ind4, missing col
tab2 industry ind5, missing col
tab2 industry ind6, missing col
tab2 industry ind7, missing col

* Generate Female Interactions with All Other Regressors in Model 5.5
*
generate fed = f*ed
generate fexp = f*exp
generate fedsq = f*edsq
generate fexpsq = f*expsq
generate fedexp = f*edexp

generate find1 = f*ind1
generate find2 = f*ind2
generate find3 = f*ind3
generate find4 = f*ind4
generate find5 = f*ind5
generate find6 = f*ind6
generate find7 = f*ind7

summarize fed fexp fedsq fexpsq fedexp find1 find2 find3 find4 find5 find6 find7

*
* Note 8 -- Model 5.5: Gender base group = males
*                      Industry base group = industry 1 (ind1)
* 
* Below we use '#delimit' to enable us to put a single Stata command on more than one line.
*
#delimit ;
regress lnw ed exp edsq expsq edexp ind2 ind3 ind4 ind5 ind6 ind7 f fed fexp fedsq fexpsq fedexp
 find2 find3 find4 find5 find6 find7 ;
#delimit cr

* Model 5.5: Compute the female coefficient estimates
lincom _b[_cons] + _b[f]
lincom _b[ed] + _b[fed]
lincom _b[exp] + _b[fexp]
lincom _b[edsq] + _b[fedsq]
lincom _b[expsq] + _b[fexpsq]
lincom _b[edexp] + _b[fedexp]

lincom _b[ind2] + _b[find2]
lincom _b[ind3] + _b[find3]
lincom _b[ind4] + _b[find4]
lincom _b[ind5] + _b[find5]
lincom _b[ind6] + _b[find6]
lincom _b[ind7] + _b[find7]

* Model 5.5: Display the male coefficient estimates
lincom _b[_cons]
lincom _b[ed] 
lincom _b[exp] 
lincom _b[edsq]
lincom _b[expsq]
lincom _b[edexp]

lincom _b[ind2]
lincom _b[ind3]
lincom _b[ind4]
lincom _b[ind5]
lincom _b[ind6]
lincom _b[ind7]

* Model 5.5: Display the female-male coefficient differences
lincom _b[f]
lincom _b[fed] 
lincom _b[fexp] 
lincom _b[fedsq]
lincom _b[fexpsq]
lincom _b[fedexp]

lincom _b[find2]
lincom _b[find3]
lincom _b[find4]
lincom _b[find5]
lincom _b[find6]
lincom _b[find7]

*
* Model 5.5: Tests on marginal effect of ed for Males
* Test 1m: ME of ed for males is zero for all values of ed & exp
test ed edsq edexp
return list

* Test 2m: ME of ed for males is constant
test edsq edexp
return list

* Test 3m: ME of ed for males is unrelated to ed
test edsq 
test edsq = 0
return list
lincom _b[edsq]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

* Test 4m: ME of ed for males is unrelated to exp
test edexp 
test edexp = 0
return list
lincom _b[edexp]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Tests on marginal effect of ed for Females
* Test 1f: ME of ed for females is zero for all values of ed & exp
test ed + fed = 0, notest 
test edsq + fedsq	= 0, accumulate notest
test edexp + fedexp = 0, accumulate
return list

* Test 2f: ME of ed for females is constant
test edsq + fedsq	= 0, notest
test edexp + fedexp = 0, accumulate
return list

* Test 3f: ME of ed for females is unrelated to ed
test edsq + fedsq = 0 
return list
lincom _b[edsq] + _b[fedsq]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

* Test 4f: ME of ed for females is unrelated to exp
test edexp + fedexp = 0 
return list
lincom _b[edexp] + _b[fedexp]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Tests on Female-Male differences in marginal effect of ed
* Test 5: Female-Male difference in ME of ed is zero for all values of ed & exp
test fed fedsq fedexp
return list

* Test 6: Female-Male difference in ME of ed is a constant 
*         Female-Male difference in ME of ed is unrelated to ed & exp
test fedsq fedexp
return list

* Test 7: Female-Male difference in ME of ed is unrelated to ed
test fedsq
test fedsq = 0
return list
lincom _b[fedsq]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

* Test 8: Female-Male difference in ME of ed is unrelated to exp
test fedexp
test fedexp = 0
return list
lincom _b[fedexp]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Tests of Industry Effects
*
* Test 1-Industry: Test of industry effects for Males
test ind2 ind3 ind4 ind5 ind6 ind7
return list

* Test 2-Industry: Test of industry effects for Females
test ind2 + find2 = 0, notest
test ind3 + find3 = 0, notest accumulate
test ind4 + find4 = 0, notest accumulate
test ind5 + find5 = 0, notest accumulate
test ind6 + find6 = 0, notest accumulate
test ind7 + find7 = 0, accumulate
return list

* Test 3-Industry: Test of  Female-Male differences in industry effects
test find2 find3 find4 find5 find6 find7 
return list

*
* Model 5.5: Tests for Female-Male Differences in Conditional Mean lnw
*
* Test 1: Female-Male Difference in Conditional Mean lnw Equals Zero
test f fed fexp fedsq fexpsq fedexp find2 find3 find4 find5 find6 find7
return list

* Test 2: Female-Male Difference in Conditional Mean lnw Equals a Constant
test fed fexp fedsq fexpsq fedexp find2 find3 find4 find5 find6 find7
return list

* Test 3: Female-Male Difference in Conditional Mean lnw Unrelated to ed
test fed fedsq fedexp
return list

* Test 4: Female-Male Difference in Conditional Mean lnw Unrelated to exp
test fexp fexpsq fedexp
return list

* Test 5: Female-Male Difference in Conditional Mean lnw Unrelated to Industry
test find2 find3 find4 find5 find6 find7 
return list

*
* Model 5.5: Evaluating the Marginal Effect of ed at Median Values of ed & exp
*
summarize ed, detail
return list
scalar edmed = r(p50)

summarize exp, detail
return list
scalar expmed = r(p50)
scalar list edmed expmed

*
* Model 5.5: Evaluate Marginal Effect of ed for Males 
*            at Median Values of ed & exp
lincom _b[ed] + 2*_b[edsq]*edmed + _b[edexp]*expmed
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Evaluate Marginal Effect of ed for Females 
*            at Median Values of ed & exp
lincom (_b[ed] + _b[fed]) + 2*(_b[edsq] + _b[fedsq])*edmed + (_b[edexp] + _b[fedexp])*expmed
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Evaluate Female-Male Difference in Marginal Effect of ed 
*            at Median Values of ed & exp
lincom _b[fed] + 2*_b[fedsq]*edmed + _b[fedexp]*expmed
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Evaluating Conditional Effect of Industry
*            at Median Values of ed & exp
*

* Model 5.5: Conditional Effect of Industry for Females 
*
* Model 5.5: Conditional Mean lnw for Females in Industry 1
*            at Median Values of ed & exp
#delimit ;
lincom _b[_cons] + _b[f] + (_b[ed] + _b[fed])*edmed + (_b[exp] + _b[fexp])*expmed
 + (_b[edsq] + _b[fedsq])*edmed*edmed + (_b[expsq] + _b[fexpsq])*expmed*expmed
 + (_b[edexp] + _b[fedexp])*edmed*expmed ;
#delimit cr
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Females in Industry 2
*            at Median Values of ed & exp
#delimit ;
lincom _b[_cons] + _b[f] + (_b[ed] + _b[fed])*edmed + (_b[exp] + _b[fexp])*expmed
 + (_b[edsq] + _b[fedsq])*edmed*edmed + (_b[expsq] + _b[fexpsq])*expmed*expmed
 + (_b[edexp] + _b[fedexp])*edmed*expmed + (_b[ind2] + _b[find2]) ;
#delimit cr
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Females in Industry 3
*            at Median Values of ed & exp
#delimit ;
lincom _b[_cons] + _b[f] + (_b[ed] + _b[fed])*edmed + (_b[exp] + _b[fexp])*expmed
 + (_b[edsq] + _b[fedsq])*edmed*edmed + (_b[expsq] + _b[fexpsq])*expmed*expmed
 + (_b[edexp] + _b[fedexp])*edmed*expmed + (_b[ind3] + _b[find3]) ;
#delimit cr
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Females in Industry 4
*            at Median Values of ed & exp
#delimit ;
lincom _b[_cons] + _b[f] + (_b[ed] + _b[fed])*edmed + (_b[exp] + _b[fexp])*expmed
 + (_b[edsq] + _b[fedsq])*edmed*edmed + (_b[expsq] + _b[fexpsq])*expmed*expmed
 + (_b[edexp] + _b[fedexp])*edmed*expmed + (_b[ind4] + _b[find4]) ;
#delimit cr
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Females in Industry 5
*            at Median Values of ed & exp
#delimit ;
lincom _b[_cons] + _b[f] + (_b[ed] + _b[fed])*edmed + (_b[exp] + _b[fexp])*expmed
 + (_b[edsq] + _b[fedsq])*edmed*edmed + (_b[expsq] + _b[fexpsq])*expmed*expmed
 + (_b[edexp] + _b[fedexp])*edmed*expmed + (_b[ind5] + _b[find5]) ;
#delimit cr
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Females in Industry 6
*            at Median Values of ed & exp
#delimit ;
lincom _b[_cons] + _b[f] + (_b[ed] + _b[fed])*edmed + (_b[exp] + _b[fexp])*expmed
 + (_b[edsq] + _b[fedsq])*edmed*edmed + (_b[expsq] + _b[fexpsq])*expmed*expmed
 + (_b[edexp] + _b[fedexp])*edmed*expmed + (_b[ind6] + _b[find6]) ;
#delimit cr
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Females in Industry 7
*            at Median Values of ed & exp
#delimit ;
lincom _b[_cons] + _b[f] + (_b[ed] + _b[fed])*edmed + (_b[exp] + _b[fexp])*expmed
 + (_b[edsq] + _b[fedsq])*edmed*edmed + (_b[expsq] + _b[fexpsq])*expmed*expmed
 + (_b[edexp] + _b[fedexp])*edmed*expmed + (_b[ind7] + _b[find7]) ;
#delimit cr
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

* Model 5.5: Conditional Effect of Industry for Males 
*
* Model 5.5: Conditional Mean lnw for Males in Industry 1
*            at Median Values of ed & exp
lincom _b[_cons] + _b[ed]*edmed + _b[exp]*expmed + _b[edsq]*edmed*edmed + _b[expsq]*expmed*expmed + _b[edexp]*edmed*expmed
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Males in Industry 2
*            at Median Values of ed & exp
lincom _b[_cons] + _b[ed]*edmed + _b[exp]*expmed + _b[edsq]*edmed*edmed + _b[expsq]*expmed*expmed + _b[edexp]*edmed*expmed + _b[ind2]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Males in Industry 3
*            at Median Values of ed & exp
lincom _b[_cons] + _b[ed]*edmed + _b[exp]*expmed + _b[edsq]*edmed*edmed + _b[expsq]*expmed*expmed + _b[edexp]*edmed*expmed + _b[ind3]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Males in Industry 4
*            at Median Values of ed & exp
lincom _b[_cons] + _b[ed]*edmed + _b[exp]*expmed + _b[edsq]*edmed*edmed + _b[expsq]*expmed*expmed + _b[edexp]*edmed*expmed + _b[ind4]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Males in Industry 5
*            at Median Values of ed & exp
lincom _b[_cons] + _b[ed]*edmed + _b[exp]*expmed + _b[edsq]*edmed*edmed + _b[expsq]*expmed*expmed + _b[edexp]*edmed*expmed + _b[ind5]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Males in Industry 6
*            at Median Values of ed & exp
lincom _b[_cons] + _b[ed]*edmed + _b[exp]*expmed + _b[edsq]*edmed*edmed + _b[expsq]*expmed*expmed + _b[edexp]*edmed*expmed + _b[ind6]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Conditional Mean lnw for Males in Industry 7
*            at Median Values of ed & exp
lincom _b[_cons] + _b[ed]*edmed + _b[exp]*expmed + _b[edsq]*edmed*edmed + _b[expsq]*expmed*expmed + _b[edexp]*edmed*expmed + _b[ind7]
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

* Model 5.5: Female-Male Differences in Conditional Effect of Industry
*
* Model 5.5: Female-Male Difference in Conditional Mean lnw for Industry 1
*            at Median Values of ed & exp
lincom _b[f] + _b[fed]*edmed + _b[fexp]*expmed + _b[fedsq]*edmed*edmed + _b[fexpsq]*expmed*expmed + _b[fedexp]*edmed*expmed 
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Female-Male Difference in Conditional Mean lnw for Industry 2
*            at Median Values of ed & exp
lincom _b[f] + _b[fed]*edmed + _b[fexp]*expmed + _b[fedsq]*edmed*edmed + _b[fexpsq]*expmed*expmed + _b[fedexp]*edmed*expmed + _b[find2] 
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Female-Male Difference in Conditional Mean lnw for Industry 3
*            at Median Values of ed & exp
lincom _b[f] + _b[fed]*edmed + _b[fexp]*expmed + _b[fedsq]*edmed*edmed + _b[fexpsq]*expmed*expmed + _b[fedexp]*edmed*expmed + _b[find3] 
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Female-Male Difference in Conditional Mean lnw for Industry 4
*            at Median Values of ed & exp
lincom _b[f] + _b[fed]*edmed + _b[fexp]*expmed + _b[fedsq]*edmed*edmed + _b[fexpsq]*expmed*expmed + _b[fedexp]*edmed*expmed + _b[find4] 
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Female-Male Difference in Conditional Mean lnw for Industry 5
*            at Median Values of ed & exp
lincom _b[f] + _b[fed]*edmed + _b[fexp]*expmed + _b[fedsq]*edmed*edmed + _b[fexpsq]*expmed*expmed + _b[fedexp]*edmed*expmed + _b[find5] 
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Female-Male Difference in Conditional Mean lnw for Industry 6
*            at Median Values of ed & exp
lincom _b[f] + _b[fed]*edmed + _b[fexp]*expmed + _b[fedsq]*edmed*edmed + _b[fexpsq]*expmed*expmed + _b[fedexp]*edmed*expmed + _b[find6] 
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

*
* Model 5.5: Female-Male Difference in Conditional Mean lnw for Industry 7
*            at Median Values of ed & exp
lincom _b[f] + _b[fed]*edmed + _b[fexp]*expmed + _b[fedsq]*edmed*edmed + _b[fexpsq]*expmed*expmed + _b[fedexp]*edmed*expmed + _b[find7] 
return list
display r(estimate)/r(se)
display 2*ttail(r(df), abs(r(estimate)/r(se)))

* Re-save dataset in memory
describe, short
summarize
save, replace
describe, short
describe
summarize

log close