Question

A market researcher is studying on-line subscription services. She is particularly interested in what variables relate to the number of subscriptions for a particular on-line service. She is able to obtain the following sample information on 25 on-line subscription services. The following notation is used:

Service		Sub	Web Page Hits	Adv	Price	Service	Sub	Web Page Hits	Adv	Price
1		37.95	588.9	13.2	35.1	14	38.39	586.5	15.4	35.5
2		37.66	585.3	13.2	34.7	15	37.29	544.0	11.0	34.9
3		37.55	566.3	19.8	34.8	16	39.15	611.1	24.2	35.0
4		38.78	642.9	17.6	35.1	17	38.29	643.3	17.6	35.3
5		37.67	624.2	17.6	34.6	18	38.09	635.6	19.8	34.8
6		38.23	603.9	15.4	34.8	19	37.83	598.9	15.4	35.1
7		36.90	571.9	11.0	34.7	20	39.37	657.0	22.0	35.3
8		38.28	584.3	28.6	35.3	21	37.81	595.2	15.4	35.1
9		38.95	605.0	28.6	35.1	22	37.42	520.0	19.8	35.1
10		39.27	676.3	17.6	35.6	23	38.83	629.6	22.0	35.3
11		38.30	587.4	17.6	34.9	24	38.33	680.0	24.2	34.7
12		38.84	576.4	22.0	35.4	25	40.24	651.2	33.0	35.8
13		38.14	570.8	17.6	35.0

  Determine the regression equation. (Negative value should be indicated with a minus sign. Round your answers to 4 decimal places.)

yˆy^ =  +  x₁ +  x₂ +  x₃

2. Conduct a global test of hypothesis to determine whether any of the regression coefficients are not equal to zero. Use α = 0.05. (Round your answers to 2 decimal places.)

H₀: β₁ = β₂ = β₃ = 0

H₁: Not all β_i's = zero.

3. Conduct a test for the individual coefficients. Would you consider deleting any coefficients
4. In Excel, develop a normal probability plot. Do you see any problems with the normality assumption?

Answer 1