Question

3. (4 marks) sleep = 3,840.83 - .163totwrk - 11.71educ - 8.79age +.128age2 + 87.75 male (235.11) (0.018) (5.86) (11.21) (0.134) (34.33) n=706, R2 = .123, R2 = .117 The variable sleep is total minutes per week spent sleeping at night, totwrk is total weekly minutes spent working, educ and age are measured in years, and male is a gender dummy. a. How do we interpret the intercept in this example? b. All other factors being equal, is there evidence that men sleep more than women? How strong is the evidence? (test at a = 5%) c. What is the relationship between one additional hour of work and sleep?

Answer 1

(a intercept Term Sleep - 3840.83 interelt Term Snows The estimated Average Skeel minutes per week ofa Jemale coitu oge ze oo cock, in increase in age 2000, no education and no Total work minutes spent on I working 83840.83+87-75 male of male =] Sleep = 3840.83 of Jemale =0 For men sleep more than coomen. it measured loy Coefficient of male. Now strong dess of evidence is measured by the Testing of significance of mare coefficient Hypothesis Ho: Coefficient of male = 0 / Hi (@eficient of male to t-statistic & male - o - 87.75 = 2.556 Se (male) 34.83

ACRIT ;0/2, 0-2 = 1.962 with d=5% Since I t-statistic> TCRIT we have evidence of dejecting Ho : so. we have very strong That men sleep more than mo women Keering other things constant. Keeling other things constant increase one additional hour of work Leads To decrease in (0.16 3 x 60) 9.78 minutes anfor spent on Sleep per week.