Week7-1

Week7/week7_analysis.do

@@ -0,0 +1,165 @@
+version 15.0
+clear all
+set more off
+set type double
+set linesize 160
+capture log close _all
+cd "C:/Users/cattom/Documents/econometrics/Week7"
+log using "week7_stata.log", text replace
+
+display "Week 7: household consumption and disposable income"
+display "Input: numeric cells C3:L17; row 17 contains reported totals."
+import excel using "Eg2_1_1/Eg2_1_1.xlsx", sheet("Sheet1") cellrange(C3:L17) clear
+
+tempname audit
+postfile `audit' double income int n double detail_total reported_total difference using "source_totals_audit.dta", replace
+local income = 800
+foreach col in C D E F G H I J K L {
+    assert `col'[1] == `income'
+    quietly summarize `col' in 2/14
+    local count = r(N)
+    local total = r(sum)
+    local reported = `col'[15]
+    post `audit' (`income') (`count') (`total') (`reported') (`total' - `reported')
+    rename `col' consume`income'
+    local income = `income' + 300
+}
+postclose `audit'
+preserve
+    use "source_totals_audit.dta", clear
+    list, noobs separator(0)
+    quietly ds, has(type numeric)
+    format `r(varlist)' %21.15g
+    export delimited using "source_totals_audit.csv", datafmt replace
+restore
+
+keep in 2/14
+generate int excel_row = _n + 3
+reshape long consume, i(excel_row) j(income)
+drop if missing(consume)
+sort income excel_row
+generate int household_id = _n
+order household_id excel_row income consume
+assert _N == 98
+assert !missing(income, consume)
+label variable income "每月可支配收入（元）"
+label variable consume "每月消费支出（元）"
+label variable excel_row "Source worksheet row"
+label variable household_id "Record identifier"
+save "households_clean.dta", replace
+quietly ds, has(type numeric)
+    format `r(varlist)' %21.15g
+export delimited using "households_clean.csv", datafmt replace
+summarize income consume
+
+regress consume income
+estimates store OLS
+estimates save "consumption_ols.ster", replace
+predict double fitted, xb
+predict double residual, residuals
+generate double residual_sq = residual^2
+scalar slope_ols = _b[income]
+scalar intercept_ols = _b[_cons]
+scalar rsquared_ols = e(r2)
+scalar rmse_ols = e(rmse)
+scalar rss_ols = e(rss)
+scalar N_ols = e(N)
+scalar F_ols = e(F)
+scalar df_ols = e(df_r)
+scalar pF_ols = Ftail(e(df_m), e(df_r), e(F))
+
+tempname coef
+postfile `coef' str12 term double estimate double se double t double p double ci_low double ci_high using "regression_coefficients.dta", replace
+foreach term in income _cons {
+    scalar tval = _b[`term'] / _se[`term']
+    scalar crit = invttail(e(df_r), .025)
+    post `coef' ("`term'") (_b[`term']) (_se[`term']) (tval) (2*ttail(e(df_r), abs(tval))) (_b[`term']-crit*_se[`term']) (_b[`term']+crit*_se[`term'])
+}
+postclose `coef'
+preserve
+    use "regression_coefficients.dta", clear
+    quietly ds, has(type numeric)
+    format `r(varlist)' %21.15g
+    export delimited using "regression_coefficients.csv", datafmt replace
+restore
+
+quietly summarize residual, meanonly
+scalar residual_sum = r(sum)
+generate double income_residual = income * residual
+quietly summarize income_residual, meanonly
+scalar income_residual_sum = r(sum)
+display "Sum of residuals = " %21.12g scalar(residual_sum)
+display "Sum of income * residual = " %21.12g scalar(income_residual_sum)
+drop income_residual
+save "households_fitted.dta", replace
+quietly ds, has(type numeric)
+    format `r(varlist)' %21.15g
+export delimited using "households_fitted.csv", datafmt replace
+
+preserve
+    collapse (count) n=consume (mean) mean_consume=consume (sd) sd_consume=consume (min) min_consume=consume (max) max_consume=consume, by(income)
+    recast double mean_consume sd_consume
+    generate double fitted_mean = scalar(intercept_ols) + scalar(slope_ols)*income
+    generate double mean_residual = mean_consume - fitted_mean
+    save "income_group_summary.dta", replace
+    quietly ds, has(type numeric)
+    format `r(varlist)' %21.15g
+    export delimited using "income_group_summary.csv", datafmt replace
+    list, noobs separator(0)
+restore
+
+set scheme s2color
+graph set window fontface "SimSun"
+twoway (scatter consume income, mcolor("26 71 111") msymbol(O) msize(small)) (lfit consume income, lcolor("174 44 51") lwidth(medthin)), title("不同可支配收入水平组家庭消费支出的条件分布图", size(medium) color(navy)) xtitle("每月可支配收入（元）", size(medsmall)) ytitle("每月消费支出（元）", size(medsmall)) xlabel(1000(500)3500) ylabel(500(500)3000, angle(90) grid glcolor("225 236 238")) xscale(range(500 4000)) yscale(range(0 3600)) legend(order(1 "consume" 2 "Fitted values") rows(1) region(lcolor(black) fcolor(white))) graphregion(color("234 242 243")) plotregion(color(white)) xsize(9) ysize(6.55) name(consumption_fit, replace)
+graph save "consumption_fit.gph", replace
+graph export "consumption_fit.png", width(1800) replace
+graph export "consumption_fit.svg", replace
+graph export "consumption_fit.pdf", replace
+
+* Heteroskedasticity-robust standard errors as a sensitivity check.
+regress consume income, vce(robust)
+estimates store Robust
+estimates save "consumption_robust.ster", replace
+tempname robustcoef
+postfile `robustcoef' str12 term double estimate double se double t double p double ci_low double ci_high using "robust_coefficients.dta", replace
+foreach term in income _cons {
+    scalar tval = _b[`term'] / _se[`term']
+    scalar crit = invttail(e(df_r), .025)
+    post `robustcoef' ("`term'") (_b[`term']) (_se[`term']) (tval) (2*ttail(e(df_r), abs(tval))) (_b[`term']-crit*_se[`term']) (_b[`term']+crit*_se[`term'])
+}
+postclose `robustcoef'
+preserve
+    use "robust_coefficients.dta", clear
+    quietly ds, has(type numeric)
+    format `r(varlist)' %21.15g
+    export delimited using "robust_coefficients.csv", datafmt replace
+restore
+estimates restore OLS
+estat hettest
+scalar bp_chi2 = r(chi2)
+scalar bp_p = r(p)
+
+preserve
+    clear
+    set obs 1
+    generate N = scalar(N_ols)
+    generate intercept = scalar(intercept_ols)
+    generate slope = scalar(slope_ols)
+    generate r_squared = scalar(rsquared_ols)
+    generate root_mse = scalar(rmse_ols)
+    generate rss = scalar(rss_ols)
+    generate F = scalar(F_ols)
+    generate df_resid = scalar(df_ols)
+    generate p_F = scalar(pF_ols)
+    generate residual_sum = scalar(residual_sum)
+    generate income_residual_sum = scalar(income_residual_sum)
+    generate bp_chi2 = scalar(bp_chi2)
+    generate bp_p = scalar(bp_p)
+    quietly ds, has(type numeric)
+    format `r(varlist)' %21.15g
+    export delimited using "model_statistics.csv", datafmt replace
+restore
+
+display "WEEK7_ANALYSIS_COMPLETED"
+log close
+exit, clear