1. This research scenario will be familiar to you. Do letters a, b, and c, answering the questions beneath your SPSS output.
2. Write a current APA-style Results section based on your analyses. All homework "Results sections" must follow the example given in the SPSS tutorials and the Course Content document "Writing Results of Statistical Tests in Current APA Format" (note: you do not have to refer to a figure). Remember to include a decision about the null hypothesis.
3. Create a boxplot as done in earlier modules/weeks.
2. Spearman Rho Exercise: This exercise is not found in Green and Salkind. Open the data file "Mod8_SpearmanRho_Exercise File" in the Module 8 SPSS Assignments folder in Blackboard, read the following information, and answer the questions below.
Scenario: During the Vietnam War, a "draft" was put in place that selected young men born on certain dates and placed them in the armed services. The process proceeded via lottery: Dates like "Sept. 14" were placed in capsules, one for each of the 365 days of the year, and the capsules were then drawn randomly from a container. In the 1970 draft, Sept. 14 was the first date drawn, meaning that all young men born on Sept. 14 were eligible for the very first round of the draft, and so on. After the results of the 1970 draft were analyzed, many statisticians and politicians asserted that the process had not been random at all, and certain men had a higher chance of being drafted than others. This case is famous, making it to the pages of international newspapers and the U.S. Supreme Court.
In the SPSS data file in Blackboard, you will find the original 1970 draft data with two variables. Column 1 contains the consecutive day of the year (1 = Jan. 1; 2 = Jan. 2; and so on). Column 2 contains the draft rank (1 = first date drawn; 2 = second date drawn; and so on). So, in the first row of the data set, Day 1 (Jan. 1) had a draft rank of 305. The lower the draft rank, the sooner and more likely a man was to be drafted. So a higher rank (like 305, for example) was preferable to those who did not want to be drafted right away.
If the process had been statistically random, there would be no correlation between the day of the year you were born and the rank that was assigned to you (r = 0). Any type of significant correlation would mean that there was something relating the variables beyond mere random error, or chance.
a) Open the data file and perform a Spearman correlation analysis for the day of year and the draft rank. Paste your output in the homework document.
b) Write a current APA-style Results section based on your analyses. All homework "Results sections" must follow the example given in the SPSS tutorials and the Course Content document "Writing Results of Statistical Tests in Current APA Format" (note: you do not have to refer to a figure). Remember to include a decision about the null hypothesis.
c) Answer the next question in "layman's terms" as if for someone who doesn't know much about statistics: Why did people accuse this process of not being random?
Part 2:
1. A university assessment department collects data to determine whether university rankings differ based on their regional location. Some rankings are missing because the universities ranked at that level were in different regions than those of interest to the department. Based on eight universities in each of two different regions, is there a difference between university rankings based on their regional locations? Perform a Mann-Whitney U test, being sure to follow the directions under the table.
|
West Coast
|
East Coast
|
|
2
5
6
12
16
17
18
19
|
1
3
4
7
8
10
13
15
|
Note: Your file must be set up in the same manner as the example data file and the exercise file from Part 1, with a grouping variable and a dependent/test variable. Because these are rankings, they are ordinal data and must be identified as such in "Variable View" under the column "Measure." Click in the cell under "Measure" in the row for your university rank variable and choose "Ordinal." This ensures that SPSS treats the data at the proper level of measurement.
2. Create a boxplot depicting the results.
3. Write a current APA-style Results section based on your analyses. All homework "Results sections" must follow the example given in the SPSS tutorials and the Course Content document "Writing Results of Statistical Tests in Current APA Format" (note: you do not have to refer to a figure). Remember to include a decision about the null hypothesis.
Part 3: Cumulative Homework
1. A political pollster is curious about the effects of a town hall meeting on people's intentions to support a state proposition that would legalize gambling. He interviews people as they leave and asks them whether their opinion about the proposition has changed as a result of the meeting. He records these frequencies in the table below. Choose the appropriate test to analyze this data, and follow the directions below the table.
|
Less likely to support
|
No change
|
More likely to support
|
|
24
|
11
|
12
|
a) Paste appropriate SPSS output.
b) Paste appropriate SPSS graph.
c) Write a current APA-style Results section based on your analyses. All homework "Results sections" must follow the example given in the SPSS tutorials and the Course Content document "Writing Results of Statistical Tests in Current APA Format" (note: you do not have to refer to a figure). Remember to include a decision about the null hypothesis.