clear
// Generate data
set seed 1
set obs 50
gen hours = rnormal(3, 1) // Number of hours studied
gen e = rnormal(1,1)
gen questions = 2 + 2*hours + 1*e // Questions answered correctly
// 1) Basic scatterplot
twoway (scatter questions hours), ///
xlabel(0 (1) 5) xtitle("Hours studied for exam") ///
ytitle("Number of questions answered correctly") ///
name(figure1, replace) ylabel(0 (5) 15) xsize(4) ysize(4)
// 2) Scatterplot with regression line
twoway (scatter questions hours) ///
(lfit questions hours), ///
xlabel(0 (1) 5) xtitle("Hours studied for exam") ///
ytitle("Number of questions answered correctly") ///
ylabel(0 (5) 15) legend(off) name(figure2, replace) xsize(4) ysize(4)
// 3) Scatterplot with regression line and equation
regress questions hours
local intercept = round(_b[_cons], .1)
local x = round(_b[hours], .1)
twoway (scatter questions hours) ///
(lfit questions hours), ///
xlabel(0 (1) 5) xtitle("Hours studied for exam") ///
text(14 2 "y = `intercept' + `x' + e", size(large)) ///
ytitle("Number of questions answered correctly") ///
ylabel(0 (5) 15) legend(off) name(figure3, replace) xsize(4) ysize(4)
// 4) Scatterplot with regression line and equation and labels for components
twoway (scatter questions hours) ///
(lfit questions hours, lpattern(solid) range(0 5)) ///
(function y = 1.6 + 2.5, range(1 2)) ///
(function y = 2, range(4.1 6.6) horizontal lpattern(solid) lcolor(red)) ///
(scatteri 1.6 0 (3) "Intercept", msymbol(o) mlabcolor(red)) ///
(scatteri 5 2 "Slope", msymbol(i) mlabcolor(red)), ///
xlabel(0 (1) 5) xtitle("Hours studied for exam") ///
text(14 2 "y = `intercept' + `x' x + e", size(large)) ///
ytitle("Number of questions answered correctly") ///
ylabel(0 1.6 5 10 15) legend(off) name(figure4, replace) xsize(4) ysize(4)
graph combine figure1 figure2 figure3 figure4, col(2) xsize(8) ysize(8) altshrink name(figures14, replace)
