Scribd
Upload
154 views3 pages

Advanced Data Analytics Examples

A nationwide retailer tested new product shelf facings for Coke Time at 15 stores by comparing total sales the week before and after installation. The data showed average sales decreased from -3.2 units but a t-test found this change was not statistically significant based on a p-value of 0.05, so the null hypothesis that the shelf facings did not increase sales cannot be rejected.

Uploaded by

rvwassup
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
154 views3 pages

Advanced Data Analytics Examples

A nationwide retailer tested new product shelf facings for Coke Time at 15 stores by comparing total sales the week before and after installation. The data showed average sales decreased from -3.2 units but a t-test found this change was not statistically significant based on a p-value of 0.05, so the null hypothesis that the shelf facings did not increase sales cannot be rejected.

Uploaded by

rvwassup
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 3

A nationwide retailer wants to test whether new product shelf facings are effective in

increasing sales volume. New shelf facings for the soft drink Coke Time are tested at a
random sample of 15 stores throughout the country. Data on total sales of Coke Time for
each store, for the week before and the week after the new facings are installed, are given
below
Store 1

10

11

12

13

14

15

Before

57

61

12

38

12

69

39

88

92

26

14

70

22

After

60

54

20

35

21

70

65

79

10

90

32

19

77

29

Level of significance : 0.05


Do you believe that the new shelf facings increase sales of Coke Time?

Null hypothesis, H0: There is no significant difference between the average sales of Coke time
before and after new facings are installed.
1 = 2 i.e. 1 - 2 =0, d = 0
Alternate hypothesis, H1: There is a significant difference
1 2 i.e. d 0
Level of significance : P(reject H0| not reject H0)
=P( 1 2 | 1 = 2)
= 0.05
Constructing test statistic, under H0,
t0 = - d/ (Sd/n^)
= -3.2 0/(8.43/15^)
= -1.4691 (computed value)

Critical Value = 1.761


Since our computed value is less than the critical value, it falls under the acceptance region.
Hence we cannot reject the null hypothesis.
Hence the average sales are not significantly different.
Confidence interval: t /2 * Sd/n^
= -3.2 1.761*(8.43)/15^
= -3.2 0.99

You might also like