This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Case Study 1.(a) 100000 80000 60000 40000 20000 14 12 10 8 6 4 2 pa ge cost Frequency H istogr a m of pa gecost 16000 12000 8000 4000 20 15 10 5 circ Frequency Histogr a m of cir c 80 60 40 20 9 8 7 6 5 4 3 2 1 pe rcma le Frequency Histogr a m of pe r cmale 3 5 0 0 0 3 0 0 0 0 2 5 0 0 0 2 0 0 0 0 1 5 0 0 0 1 4 1 2 1 0 8 6 4 2 m e d ia n in c o m e Frequency H i st o g r a m o f m e d i a n i n co m e The histogram of page cost and circulation is skewed to the right. The histogram of percent male is skewed to neither right nor left, and the histogram of median income is very slightly skewed to the right but almost symmetrical. (b) 4 0 0 0 0 3 5 0 0 0 3 0 0 0 0 2 5 0 0 0 2 0 0 0 0 1 5 0 0 0 1 0 0 0 0 0 8 0 0 0 0 6 0 0 0 0 4 0 0 0 0 2 0 0 0 0 m e d ia n in c o m e pagecost S ca t t e r p l o t o f p a g e co st v s m e d i a n i n co m e 9 0 8 0 7 0 6 0 5 0 4 0 3 0 2 0 1 0 1 0 0 0 0 0 8 0 0 0 0 6 0 0 0 0 4 0 0 0 0 2 0 0 0 0 p e r c m a le pagecost S ca t t e r p l o t o f p a g e co s t v s p e r cm a l e 20000 15000 10000 5000 100000 80000 60000 40000 20000 circ pagecost Scatte r plot of pa gecost v s cir c There is a slight linear relationship between the circulation and the page cost. There is not much of a linear relationship between the median income and the page cost, nor between the percent male and the page cost. 2. (a) Ho: β1= β2= β3=0 Ha : At least one of the β is not equal to 0 Analysis of Variance Source DF SS MS F P Regression 3 15657778292 5219259431 28.18 0.000 Residual Error 40 7408830150 185220754 Total 43 23066608442 S = 13609.6 RSq = 67.9% RSq(adj) = 65.5% From above, pvalue≈0.000< 0.05, Reject Ho, and we can say that this multiple regression model is useful. Also, from RSq(adj)= 65.5%, we can conclude that it is significant overall. (b) The regression equation is pagecost =  5673 + 5.17 circ + 5.0 percmale + 1.09 medianincome (c) Predictor Coef SE Coef T P Constant 5673 13273 0.43 0.671 circ 5.1731 0.5632 9.19 0.000 percmale 4.99 84.56 0.06 0.953 medianincome 1.0889 0.5757 1.89 0.066 *β1=circulation Test Ho: β1=0, Ha : β1≠0. Pvalue≈0.000< 5% We reject Ho, and we can conclude that there is strong evidence that circulation has a significant relationship with pagecost. * β2=permale Test Ho: β2=0, Ha: B2≠0. PValue= 0.953>5% We fail to reject Ho, and we can conclude that the percent male is not significantly related with the pagecost. * β3=medianincome Test Ho: β3=0, Ha : β 3≠0. Pvalue = 0.066>5% We fail to reject Ho, and we can conclude that the median income is not significantly related with the pagecost. Therefore, we keep the circulation as a predictor and drop out permale and medianincome....
View
Full Document
 Fall '07
 Lv
 Linear Regression, Regression Analysis, Errors and residuals in statistics, median income

Click to edit the document details