Question

Need this answer done by hand, not using SAS, I need to understand how to solve this question and need answers to part a to c

Q. Suppose data on sales revenue Y , and television advertising X1 and print advertising
X2 are collected for several stores. The edited SAS (Proc Reg) output shows

Table 2: Y regressed on Xi, and X2 source | df | Type I SS Type II SS 20 25 30 25 50 error 20 (a) Provide variables-added-in-order tests for both variables, while X is added first, use α .05. (b) Provide variables-added-in-order tests for both variables, while X2 is added first, use α = .05. (c) Provide a table for variables-added-last tests.

Answer 1

Referring to last table in the picture.

The Y-intercept value is 20.31190

The cofficient value is 0.45238

yes, it makes sense to intrepret , because the p-values (pr>|t|) for both the coefficient and the intercept are less than 0.05 which means both the values are significant at 95% confidence level.

when you perform the linear regression you will get the best fitted line in the form y=mx+c

where 'y' is the dependent variable, 'x' is the independent variable, 'm' is the estimated slope coefficient and 'c' is the y-intercept.

In this problem dependent variable is Hips, independent variable is chest, slope is 0.45238, Y-intercept is 20.31190

Question 2 Answer:

The coefficient of determination is the R-squared value which is 0.2283. Refer Table3 in the picture

Question 3 Answer:

Yes. the  hypothesis test suggest that the two variables are linearly related. we can see from the last table that

p-values (pr>|t|) for both the coefficient and the intercept are less than 0.05 which means both the values are significant at 95% confidence level.

Hence there exists the linear dependency. ie hips= 0.45238* chest + 20.31190