Question

A Girl Scout troop is preparing to order extra cookies for a Saturday morning sale in a store parking lot. A random sample of potential buyers was obtained, and each was asked to name his or her favorite Girl Scout cookie. The results and the percentages sold nationally last year are given in the following table. Conduct a goodness-of-fit test to determine whether any of this year’s proportions differs from last year’s proportions. Use ? = 0.05. Also, check the assumptions.

Cookie	Favorite	Last Year
Thin Mints	120	25%
Samoas	95	19%
Tagalongs	70	13%
Do-Si-Do’s	58	11%
Trefoils	60	9%
All other varieties	101	23%

Answer 1

The expected frequencies here are computed from the last year proportions while the expected frequencies here are the this year frequencies given.

Total frequency = 120 + 95 + .... + 101 = 504

We would be conducting the chi square test here for goodnes of fit. The chi square test statistic here is computed as:

For n - 1 = 5 degrees of freedom, the p-value here is computed from the chi square distribution tables as:

As the p-value here is 0.19 > 0.05 which is the level of significance, therefore the test is not significant here and we cannot reject the null hypothesis here. Therefore we dont have sufficient evidence here that this year frequencies share is different from last year's shares.