(10) Moe’s Computer Store hired an advertising agency to prepare two advertisements of comparable quality
(10) Moe’s Computer Store hired an advertising agency to prepare two advertisements of comparable quality for their new television-computer wristwatch. To see whether both ads led to the same distribution of sales, Moe hired a statistician to find out. Two random samples were taken on 12 months of the first year of sales for these innovative watches. Data is shown in the table below. Process the data as show in the paper on the Mann-Whitney U test.
| Ad 1 | 26 | 39 | 28 | 33 | 43 | 32 | 45 | 25 | 39 | 42 | 45 | 49 |
| Ad 2 | 36 | 31 | 46 | 45 | 37 | 49 | 40 | 41 | 35 | 44 | 39 | 43 |
- (1) H0: The ads lead to the same distribution of sales
- (1) H1: The ads don’t lead to the same distribution of sales
- (1) Critical Value: z c = 1.96
- (5) Test Statistic (Show procedure.) z = 0.924
2. (10) Charmers’ Candy Store sells wrapped hard candies in the following flavors: strawberry, blueberry, lemon, lime, and orange. They advertise that there are equal proportions of each flavor in every size of their candy boxes. To test their claim, a parent opens her son’s candy box and counts each flavor. On the next page are mom’s observations for a large box that contains 100 candies.
Fill in the table, and perform a one-dimensional Chi Square goodness of fit test.
| Category | O (Observed Frequency) | E (Expected Frequency) | D (difference) | (O - E) squared | (O-E)sqd/E |
| Strawberry | 15 | ||||
| Blueberry | 20 | ||||
| Lemon | 21 | ||||
| Lime | 19 | ||||
| Orange | 25 | ||||
| Total |
-
Complete the table. (See page 293 in your book.)
Category O (Observed Frequency) E (Expected Frequency) D (difference) (O - E) squared (O-E)sqd/E Strawberry 15 Blueberry 20 Lemon 21 Lime 19 Orange 25 Total 100 - (5) Set up a hypothesis test. (See page 293 in your book.) Is Charmers’ truthful? Explain by working through a hypothesis test.
H0:
H1:
CV: (Use Table B.5)
TS (Show procedure.):
Decision and Conclusion:
3. (5) A state collects data on whether cell phone use while driving contributes to accidents. The 2 x 2 contingency table below is filled in. Complete the Chi Square test of independence by calculating the Chi Square test statistic.
| Accident Last Year | No Accident Last Year | Total | |
| Cell Phone in Use | 30 (38.43) | 350 (341.57) | 380 |
| Cell Phone not in Use | 60 (51.57) | 450 (458.43) | 510 |
| Total | 90 | 800 | 890 |
Numbers in parentheses are the expected frequencies. Numbers not in parentheses are the observed frequencies. The expected frequencies are found by multiplying the row total by the column total and dividing by the grand total.
The degrees of freedom (df) = (row – 1) x (column -1).
To complete the Chi Square test, use the formula below.
where is the observed frequency and is the expected frequency. Then make the decision whether cell phone use while driving is related to vehicular accidents. Note that the table value of Chi Square at 1 df for 5% risk is 3.84. What is the obtained Chi Square statistic?
4. (10) Calculate the parallel forms reliability for scores of a small sample of students on a professor-composed test for tax preparation. Scores can range from 0 to 100. Twenty students took both the A form and then the next day the B form.
| 89 | 60 | 80 | 72 | 85 | 79 | 83 | 65 | 88 | 92 | 71 | 68 | 96 | 93 | 87 | 82 | 90 | 98 | 100 | 76 |
| 85 | 65 | 78 | 75 | 80 | 82 | 85 | 60 | 86 | 95 | 76 | 70 | 92 | 95 | 85 | 89 | 90 | 100 |
9
8 |
80 |
- (5) Use Excel’s CORREL program to compute the reliability coefficient. Paste your printout here, or attach it to this assignment.
-
(5) Using the information in Chapter 16 and in Chapter 5, do you think the professor’s test is reliable? Explain.
5. (10) Measurement specialists know that the longer the test, in general, the higher the reliability coefficient. On pages 310-311, you are introduced to Cronbach’s alpha. The calculated measure .24 results from a small number of items on a particular instrument be it a test or questionnaire. Calculate Cronbach’s alpha for a long three-hour exam for entrance to a certain college’s MBA program. Below are important data.
= 10.70, = 2.83, and the number of test items, k, = 50.- (5) \[\alpha \] =
5.(cont’d)
(b) (5) Would you say that this test has good reliability? Compare \[\alpha \] to \[{{r}_{xy}}\] in Table 5.2 on page 127. Explain.
6. (5) Let’s connect reliability to validity. Suppose the graduate school exam in #5 above has been checked for content validity. In other words, items included in the test represent knowledge and skills that students who have completed a bachelor’s degree should know for entrance into an MBA program. See page 320 and the note that links reliability with validity.
- (2) Why it is a necessary condition that a test be reliable before it is judged for content validity?
- (3) What is the validity coefficient for the MBA exam? Show your procedure.
Deliverable: Word Document
