DVC ADS data Programming Code Paper
1. Use data in file ADVERTISING.DTA on Canvas. The data are for 200 regional marketsin the U.S.
(a) Regress sales on tv.
(b) Predict population conditional mean sales for TV advertising expenditure of $100,000.
(Note: Check the units of measurement using command describe).
(c) Provide a 95% confidence interval for this population conditional mean with TV adver-
tising expenditure of $100,000.
[Hint: Use the formula for selýcm) given in the coursepack. You will need output se, n, i
and sand can compute = (47–7) assmultiplied by n-1, since s = n1 = 1;-
7)).
(d) Provide a 95% confidence interval for actual sales with TV advertising expenditure of
$100,000. (Hint: Use selŷs) = 8ex V1+*+ 12 (22-1)3-
()
(e) Give the following commands and save the resulting combined graph.
twoway (1fitci sales tv) (scatter sales tv), saving (graph1, replace)
twoway (fitci sales tv, stdf) (scatter sales tv), saving (graph2,replace)
graph combine graph1.gph graph2.gph, iscale(1.2) ysize(2.5) xsize(6) rows (1) ycommon
What do you learn from the combined graph? Hint: give command help twoway lfitci
2. For each of the following estimated models provide the simplest possible explanation of
the effect of IQ (intelligent quotient has mean of 100) on EARNS (annual earnings in $).
Hint: For models with logs use elasticities or semi-elasticities.
(a) EARNS = 1000 + 500xIQ.
(b) EARNS = 20000 + 200xIQ + 2xIQ”.
(c) EARNS = -20000 + 50000 x In(IQ).
(d) EARNS = 45000 + 10000xd, where d=1 if IQ>100 and d=0 if IQ