Testing the Effectiveness of Supermarket Sales Strategies

Only available on StudyMode
  • Download(s) : 226
  • Published : October 1, 2011
Open Document
Text Preview
Testing the effectiveness of supermarket sales strategies

Table of Contents

I. Introduction……………………………………………………………………p. 3

II. Scenario………………………………………………………………………..p.4

III. Methodology………………………………………………………………….p.6

IV. Hypothesis……………………………………………………………………p.9

V. Data Analysis……………………………………………………………….p.13

VI. Conclusion………………………………………………………………….p.16

Appendix………………………………………………………………………..p.17

I. Introduction

Most supermarket strategies such as advertising, special promotions, price reductions, in-store promotions, variables in display space or quality of display location are used to increase the unit sales of certain products. Although supermarkets maintain their sales by using these specific merchandising activities, findings of empirical studies doubt that all strategies will produce equally significant increases in unit sales of targeted products. For example, the studies found that price reductions doesn’t always have a significant correlation and more likely to have an unpredictable effect on unit sales. From another hand, supermarkets get a sizable percentage of their total sales through display. It works very simple - displays create in-store excitement and increase the average amount purchased because consumers tend to view them as special bargains and often buy products which they had no previous intention of buying. Thus, it becomes obvious that systematic measurement of the influence of various combinations of merchandising and different activities helps significantly improve a strategy of maximizing profit of the particular supermarket, but also is very essential part of developing management decision-information systems in the world.

II. Scenario
Testing the effectiveness of supermarket sales strategies, I will examine the relative importance of temporary price reductions and display alternatives to unit sales of supermarket products for the week. My experiment involves two factors: Display level (factor A) and Price level (factor B). Each factor has three levels; thus, we have a 3x3 complete factorial experiment. The treatments of an experiment are the factor-level combinations utilized. There are nine treatments in the study: Normal Display-Regular Price, Normal Display-Reduced Price, Normal Display – Cost to Supermarket, Normal Plus Display-Regular Price, Normal Plus Display-Reduced Price, Normal Plus Display-Cost to Supermarket, Twice Normal Display-Regular Price, Twice Normal Display-Reduced Price, and Twice Normal Display-Cost to Supermarket Price. To proceed with the analysis, we test a null hypothesis H0: the treatment means are equal and calculate the F-ratio. Then we compare calculated F value to a table F value with v1 degrees of freedom in the numerator and v2 degrees of freedom in the denominator and corresponding to a Type I error probability of a (alpha). If calculated F value is smaller than table F value, we do not reject the null hypothesis that the treatment means are equal. However, if calculated F value is greater than table F value, we reject the null hypothesis, and we conclude that some differences exist among the treatment means. If at least two of the nine treatment means differ in the supermarket sales strategies experiment, we need to determine if both factors affecting the response, or only one? Does the Display level or the Price level affect mean sales, or do both affect it, and how much? To determine it, we need to partition the treatments Sum of Squares into the Main Effect and Interaction Sum of Squares. Here we test the null hypothesis H0: factors A and B do not interact to affect the response mean by computing F-ratio of the Mean Square for Interaction to the Mean Square for Error: 1) if the test results in nonrejection of the null hypothesis H0: factors A and B do not interact to affect the response mean, we conduct test of other two null hypotheses: H0 (1): no difference among the a mean levels of factor A...
tracking img