Assignment # 3

MEAN DIFFERENCES ASSIGNMENT #3

Florida County Government

ASSIGNMENT #3

Title: Florida County Government

The Quantitative Analysis Report: Mean Differences Assignment has three parts and uses the Florida County Government. sav dataset. Load the data set into SPSS.

1. Address the following research question using an independent samples t-test:

RQ 3: Is there a significant difference in the percent of total spending that is environmental spending between coastal counties and non-coastal counties?

· H03: There is no statistically significant difference in the percent of total spending that is environmental spending between coastal counties and non-coastal counties.

· Ha3: There is a statistically significant difference in the percent of total spending that is environmental spending between coastal counties and non-coastal counties.

1. Open the data file Florida County Government. sav.

2. Perform an error bar plot first.

3. Click on Graphs/Legacy Dialogs/Error Bar.

4. Click on Simple button and then radio button “summaries for groups of cases” then click on Define.

5. Move to Variable box on the right the dependent variable Average % Envir. Spending in Total spending (AverageEnvirTotal).

6. Move Coastal Area or Not to Category Axis box. This is the independent groups variable. There are two groups: coastal county=1 and not coastal county=0.

7. Click OK.

8. Edit the error bar plot by adding data labels and title.

9. Follow directions in Cronk and in the resources provided. What do you think from that plot you would expect to find in an independent samples t-test?

10. Now, perform an independent t samples t-test with:

· coastal (1)/non-coastal county (0) as your independent variable groups and;

· Average % Envir. Spending in Total spending (AverageEnvirTotal) as your dependent variable.

11. Use Cronk and resources provided to interpret the results of the Levene’s test of assumed equal variances and then interpret the t-test results and report based on the testing of your hypotheses.

[DataSet6] /Users/pamelafarrar/Downloads/Florida County Government (1).sav

Error Bar Plot

Independent Samples t-test

Error Bar Plot

Levene’s Test

2. Address the following research question using a One-Way ANOVA test:

RQ 4: Is there a significant difference in the intergovernmental revenue growth rate (IGR) based on county type (metro/suburban/rural)?

· H04: There is no statistically significant difference in the intergovernmental revenue growth rate (IGR) based on county type (metro/suburban/rural).

· Ha4: There is a statistically significant difference in the intergovernmental revenue growth rate (IGR) based on county type (metro/suburban/rural).

1. Open the data file Florida County Government. sav.

2. Perform an error bar plot first.

3. Move to Variable box on the right the dependent variable intergovernmental revenue growth rate (IGR).

4. Move county type (metro/suburban/rural) to Category Axis box. This is the independent groups variable. There are three groups.

5. Click OK.

6. Edit the error bar plot by adding data labels and title. Follow directions in Cronk and in the resources provided. What do you think from that plot you would expect to find in a One-Way ANOVA test?

7. Now, perform a One-Way ANOVA test with:

· County type as your independent variable groups and;

· Intergovernmental revenue growth rate (IGR Growth rate) as your dependent variable.

8. Run post-hoc tests as well.

9. Use Cronk and resources provided to interpret the results of the Levene’s test of assumed equal variances, interpret the One-Way ANOVA results, interpret the results of post-hoc tests, and produce a report based on the testing of your hypotheses.

Error Bar Plot

One-Way ANOVA test

Post Hoc Tests

Homogeneous Subsets

3. Add a covariate to your One-Way ANOVA and rerun as an ANCOVA. The new research question is:

RQ 5: Controlling for political orientation (political), is there a significant difference in the intergovernmental revenue growth rate (IGR) based on county type (metro/suburban/rural)?

· H05: Controlling for political orientation (political), there is no statistically significant difference in the intergovernmental revenue growth rate (IGR) based on county type (metro/ suburban/rural).

· Ha5: Controlling for political orientation (political), there is a statistically significant difference in the intergovernmental revenue growth rate (IGR) based on county type (metro/suburban/rural).

1. Perform an error bar plot first. What do you think from that plot you would expect to find in an ANCOVA test?

2. Then, perform an ANCOVA test with:

a. County type as your independent variable groups, political as your covariate, and;

b. Intergovernmental revenue growth rate (IGR Growth rate) as your dependent variable.

Error Bar Plot

ANCOVA test

Univariate Analysis of Variance