Question

You are given the following table of output pertaining to voters in a sample of urban voting districts across the country. Voters is the number of voters who cast a ballot in 100s, and TV ads is the number of political advertisements purchased for TV in the market.

Table 1: OLS regression TV advertisements and voters

	Dependent variable Voters
TV Ads	1.25∗∗∗ (0.10)
Constant	20.6∗∗∗ (0.06)
Observations	300
R(square)	0.02
Adjusted Rsquare	0.02
Residual Std. Error	2.4 (df = 298)
F Statistic	10.15∗∗∗ (df = 1; 298)

NOTE: ∗p<0.1; ∗∗p<0.05; ∗∗∗p<0.01

(a) Use the information in the table to write the regression equation.

(b) According to the results, how many voters are generated from each TV advertisement?

(c) How much of the variation in voters is explained by this model? Interpret this finding.

(d) Suppose one of the voting districts is Erie. There are 30 TV ads in Erie, and 6000 voters. Use the output in the table to calculate the predicted number of voters. (2 points)

(e) What is the residual for Erie?

(f) Did Erie have more or fewer voters than would be expected for the number of TV Ads?

(g) What other factors would enter into the residual of this regression?

Answer 1

a) The regression equation is

b) For each T.V advertisement the number of voters generated is 1.25or round to whole number is 1.

c) R squarred is 0.02 . So 2% variation in voters is explained by this model.

d) x= 30

or 58 are the predicted number of voters.

e) Residual of Erie is voters

f) Erie have more voters than would be expected for the number of TV Ads

g) Gender of the voters or Age of the voters are the other factors would enter into the residual.