* ===================================================================
* Sample Stata do-file: Data cleaning, summary statistics & regression
* Updated with clear, professional variable names
* Lines: 72
* ===================================================================
 
clear all
set more off
capture log close
 
log using "analysis_log.smcl", replace
 
* 1. Load built-in auto dataset
sysuse auto, clear
 
* 2. Rename variables to meaningful, lowercase names
rename price      car_price
rename mpg        miles_per_gallon
rename weight     car_weight_lbs
rename length     car_length_in
rename rep78      repair_record_78
rename foreign    origin            // 0=Domestic, 1=Foreign
 
* 3. Data cleaning
drop if missing(car_price) | missing(repair_record_78)
 
* Label origin properly
label define origin_lbl 0 "Domestic" 1 "Foreign"
label values origin origin_lbl
 
* 4. Generate transformed and categorical variables
gen ln_price   = ln(car_price)
gen ln_mpg     = ln(miles_per_gallon)
 
recode repair_record_78 (1/2 = 1 "Poor") (3 = 2 "Average") (4/5 = 3 "Good"), ///
    gen(repair_cat)
label var repair_cat "Repair record 1978 (categorical)"
 
gen weight_kg = car_weight_lbs * 0.453592
label var weight_kg "Weight (kilograms)"
 
* 5. Summary statistics with nice table
eststo clear
estpost summarize car_price miles_per_gallon car_weight_lbs ///
                  car_length_in origin ln_price weight_kg, detail
 
esttab using "summary_statistics.rtf", replace ///
    cells("count mean(fmt(2)) sd(fmt(2)) min max") ///
    label title("Descriptive Statistics") nonumber
 
* 6. Regression models
eststo: regress car_price miles_per_gallon car_weight_lbs i.origin i.repair_cat
 
eststo: regress ln_price ln_mpg car_weight_lbs i.origin i.repair_cat, robust
 
* 7. Export publication-ready regression table
esttab using "regression_results.rtf", replace ///
    b(4) se(4) ///
    star(* 0.10 ** 0.05 *** 0.01) ///
    scalar(N r2_a F) sfmt(3) ///
    label ///
    mtitles("Level price" "Log-log model (robust SE)") ///
    title("OLS Regression Results") ///
    note("Model 2 uses robust standard errors")
 
* 8. Basic diagnostic
estat vif       // Check multicollinearity
estat hettest  // Breusch-Pagan test
 
* 9. Save cleaned dataset
save "auto_cleaned_renamed.dta", replace
 
* 10. Optional: export summary stats to Excel
export excel using "descriptive_stats.xlsx", sheet("Summary") firstrow(varlabels) replace
 
log close
display as text "Analysis completed – check the created files in your working directory!"
* End of do-file

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