14.55 Regress TV watching on gender and marital status When we use the 2014 GSS and regress y = number of hours per day watching TV on g = gender

(1 = male, 0 = female) and marital status (m1 = 1 for singles, 0 otherwise, m2 = 1 for married subjects, 0 otherwise), we get the following output

a. Write down the corresponding regression model for the population mean and give the equation for the population mean at each combination of the two factor levels. (Create a table similar to Table 14.11.)

b. Write down the prediction equation and interpret the estimated gender effect.

c. From the expression for the population means in part

a, find the difference in means between single and divorced subjects, separately for each gender. This difference is equal to what regression coefficient?

d. Find and interpret a 95% confidence interval for the difference in means between single and divorced subjects, for given gender. (Note: The df for the t-score equals 1471.)

Transcribed Image Text:

Term Coef SE Coef T-Value P-value Constant 2.78 0.155 17.95 0.000 g 0.16 0.127 1.29 0.197 m 0.41 0.184 2.21 0.027 m2 -0.21 0.170 -1.26 0.209