1) Management of ABC Movie Theaters, Inc. is interested in analyzing the relationship between weekly revenue and advertising expenditures using television, newspapers, and radio. A sample of 35 was obtained and a regression performed with Revenue (in $000) as the dependent variable and the predictors TV ad expenditure (in $000, variable name TV), newspaper ad expenditure (in $000, variable name NP), and radio ad expenditure (in $000, variable name radio). Output appears below. Pearson Correlation Coefficients Source Variable Model Error Corrected Total DF Intercept Revenue TV Radio NP 1 1 1 1 Parameter Estimate Revenue 1.00000 0.78755 0.53140 0.68412 46.81238 7.43603 6.24525 5.15351 DF Root MSE Dependent Mean 3 31 34 Dependent Variable: Revenue Analysis of Variance Sum of Squares TV 0.78755 1.00000 0.19254 0.57077 8104.34992 1445.48906 9549.83898 6.82852 98.39504 Standard Parameter Estimates Error t Value Radio 0.53140 0.19254 1.00000 0.12103 11.39 6.01 5.48 4.01 Mean Square 2701.44997 46.62868 R-Square Adj R-Sq Pr > |t| Exhibit A Regression run including only TV advertising expenditure as predictor Source Model Error Corrected Total Variable Intercept TV Source Model Error Corrected Total Variable Intercept Radio Source Model Error Corrected Total NP Variable Intercept DF 1 1 Regression run including only Radio expenditure as predictor DF 1 1 Dependent Variable: Revenue Analysis of Variance Sum of Squares 5923.20573 3626.63326 9549.83898 DF 1 1 DF 1 33 34 Parameter Estimate 58.62160 11.31765 DF 1 Parameter Estimates. 33 34 Regression run including only NP as predictor Dependent Variable: Revenue Analysis of Variance Sum of Squares 2696.70005 6853.13893 9549.83898 Parameter Estimate 81.31299 8.50008 DF 1 33 34 Mean Square 5923.20573 109.89798 Parameter Estimates Standard Error 5.70006 1.54160 4469.57432 5080.26466 9549.83898 Dependent Variable: Revenue Analysis of Variance Sum of Squares Parameter Estimate 72.55522 10.32320 Mean Square 2696.70005 207.67088 Standard Error 5.32958 2.35882 Parameter Estimates. Standard Error t Value 10.28 7.34 Mean Square 4469.57432 153.94741 5.23414 1.91588 t Value 15.26 3.60 t Value 13.86 5.39 F Value 53.90 F Value 12.99 Pr > It| Exhibit A (Continued) Regression run including only v1 and NP as predictors Source Model Error Corrected Total i Variable Intercept v1 NP Source Model Error Corrected Total Variable Intercept v2 Radio Source Model Error Corrected Total DF 1 Variable Intercept v3 Radio Regression run including only v2 and Radio as predictors 1 1 DF 1 1 1 DF Dependent Variable: Revenue Analysis of Variance Sum of Squares 7947.09165 1602.74734 9549.83898 1 1 1 DF 2 32 34 Parameter Estimate 47.41221 Parameter Estimates. Standard Error DF 2 32 34 4.37113 4.58462 Regression run including only v3 and Radio as predictors Parameter Estimate 50.65091 DF 2 32 34 Dependent Variable: Revenue Analysis of Variance Sum of Squares 7716.12516 1833.71382 9549.83898 8.09656 6.59371 3973.54582 50.08585 4.24479 Parameter Estimates 0.52459 1.29170 Parameter Estimate 46.61209 8.24990 6.20279 Dependent Variable: Revenue Standard Error 4.30941 0.86510 1.25570 3858.06258 57.30356 Analysis of Variance Sum of Squares 8071.49997 1478.33902 9549.83898 Mean Square Parameter Estimates Standard Error t Value 11.17 4.08275 0.76486 1.13275 Mean Square 4035.74998 46.19809 t Value 11.75 9.36 5.25 Mean Square 8.33 3.55 t Value 11.42 10.79 5.48 F Value 79.33 Pr > |t| 1b) Note the 99% confidence limits for the three advertising expenditure regression coefficients. Use the above results and the Bonferroni simultaneous estimation methodology to determine the family confidence coefficient for all three confidence intervals. Interpret your family confidence coefficient. 1c) Suppose the analysis was conducted using only radio advertising expenditure as a predictor (see Exhibit A). Interpret the estimated coefficient for radio, and comment on using this result to provide information about the effect of radio advertising expenditure on revenue. 1d) Suppose the researcher was interested in testing whether the coefficient for NP is half as large as the coefficient for TV. Conduct the test of this restriction using alpha-0.05. Note the information in Exhibit A has a run of a model that includes variable v1=2(TV) + Radio, a run of a model that includes v2=0.5(TV) + NP, and a run of a model that includes v3=TV + 0.5(NP). State the hypotheses, decision rule, test statistic, and decision.