Question

Starbucks enjoyed considerable success with its debit cards, which they sell for $5 to $500. Suppose a study of 25 randomly selected prepaid card purchasers is taken. Respondents are asked the amount of the prepaid card, the customer's age, the number of days per month the customer makes a purchase at Starbucks, the number of cups of coffee the customer drinks per day, and the customer's income. The data is below.

1. How strong is the model? Explain in detail.
2. Which particular independent variables seem to have more promise in predicting how many days per month a customer visits Starbucks?  Explain in detail.

AMOUNT OF PREPAID CARD ($)	DAYS PER MONTH AT STARBUCKS	AGE	INCOME ($1,000)	CUPS OF COFFEE PER DAY
5	4	25	20	1
25	12	30	35	5
10	10	27	30	4
5	8	42	30	5
15	11	29	25	8
50	12	25	60	5
10	8	50	30	3
15	6	45	35	5
5	16	32	25	7
5	10	23	20	1
20	18	40	40	5
35	12	35	40	3
40	10	28	50	3
15	12	33	30	2
200	15	40	80	5
15	3	37	30	1
40	10	51	35	8
5	8	20	25	4
30	15	26	35	5
100	19	38	45	10
30	12	27	35	3
25	14	29	35	6
25	10	34	45	4
50	6	30	55	3
15	8	22	30	5

Answer 1

using excel>data>data analsysis>Regression

we have

SUMMARY OUTPUT
Regression Statistics
Multiple R	0.659013
R Square	0.434298
Adjusted R Square	0.321158
Standard Error	3.306643
Observations	25
ANOVA
	df	SS	MS	F	Significance F
Regression	4	167.8823	41.97058	3.838578	0.017933
Residual	20	218.6777	10.93388
Total	24	386.56
	Coefficients	Standard Error	t Stat	P-value	Lower 95%	Upper 95%
Intercept	8.002839	3.988364	2.006547	0.058509	-0.31674	16.32242
AMOUNT OF PREPAID CARD ($)	0.026516	0.032853	0.80713	0.429086	-0.04201	0.095046
AGE	-0.08234	0.084357	-0.97608	0.340686	-0.25831	0.093627
INCOME ($1,000)	0.00554	0.096628	0.05733	0.954851	-0.19602	0.207102
CUPS OF COFFEE PER DAY	0.993135	0.327462	3.032827	0.006571	0.310061	1.676208

Ans 1 ) About 43.42% variation in DAYS PER MONTH AT STARBUCKS is explained by idependent variables

also p value of F stat is 0.018 which is less than 0.05 so model is significant to use at 95% confidence level but not at 99% confidence level.

Ans 2 ) CUPS OF COFFEE PER DAY variables seem to have more promise in predicting how many days per month a customer visits Starbucks because p value of this variable is less than so this is significant variable .