ANOVA Project -
A marketing research analyst has conducted a study to determine the effects of two factors on the point-of-sale marketability of a particular product. The two factors are packaging design and display position (location of the product on the display shelf). There are three packaging designs under consideration referred to simply as A, B, and C. There are also three levels of the display position variable; top, middle, and bottom, referred to as 1, 2, and 3, respectively. The objective is to produce a two-factor analysis of variance with interaction to determine if either of these factors significantly affects unit sales.
For each of the nine treatments (3x3), four retail outlets were randomly selected, each using a one-month trial period, for the study. The data obtained from the study are provided in the data set with the dependent (response) variable being daily unit sales averaged over the trial period.
Produce a report that included the following:
1. Comment on the design of the above experiment. Specifically:
a. Is this a completely randomized design with respect to retail outlets? Why or why not?
b. Are the factors in the model used as control or experimental factors?
c. Is the above model a fixed effects model (Model I) or a random effects model (Model II)?
2. Create and present a table that reports the estimated treatment (cell) means as well as the factor level means and the grand mean.
3. Produce a graph or plot the cell means using sales on the vertical axis and packaging design on the horizontal axis.
4. Create and present a table that reports the estimated main factor effects and the interaction effects.
Present the ANOVA table for the two-factor analysis of variance with interaction and then answer the following questions:
5. Test an appropriate hypothesis to determine if the main packaging design effects are significant, that is, is there a significant effect on sales attributable to packaging design?
6. Test an appropriate hypothesis to determine if there a significant effect on sales due to display position
7. Test an appropriate hypothesis to determine if significant interaction is present.
8. Use Tukey's T method to determine which package design factor means are significantly different from the others. (There are three comparisons possible.)
9. Do the same as #8 above for display position.
Attachment:- Assignment Files.rar