# Grand Canyon PSY 870: Module 5 Problem Set 47765

QuestionPSY 870: Module 5 Problem Set

Anxiety and Country

This study examined differences in anxiety level between an industrial country and a

nonindustrial country. Anxiety is assessed three wayscognitive, affective, and behavioral

with higher scores indicating higher levels of the anxiety dimensions.

Directions:

Using the SPSS data file for Module 5 (located in Topic Materials), answer the following

questions. NOTE: Helpful hints are provided here for you to use while answering these

questions.

1. What is the ONE independent variable in this study? What are the dependent variables?

2. Why is a one-way between-subjects MANOVA appropriate to use for this research

design?

HINT:

Consider the number of IVs and the number of DVs for your answer.

3. Did you find any errors that the researcher made when setting up the SPSS data file

(dont forget to check the variable view)? If so, what did you find? How did you correct

it?

HINT:

YES! The Measures (for scale of measurement) is wrong for each of the 4 variables!

You need to indicate what was wrong and what should be the correct measures.

4. Perform Initial Data Screening. What did you find regarding missing values, univariate

outliers, multivariate outliers, normality? Although you are not asked to make

adjustments, what should you consider when you find these kinds of outcomes?

HINTS:

For missing values, see Case Processing Summary

Univariate outliers: inspect boxplots

Multivariate outliers: Dont forget to create the Case ID variable to do this

analysis. Then, perform a regression analysis with CaseID as the DV and

Country as the IV in order to compute the Mahalanobis distance measures. Be

sure to click Save when you are setting up the regression so the regression scores

will be saved to a new variable (automatically named MAH_1). Then, Explore

MAH_1 scores, remembering to check the Outliers box that is found with Plots.

This will give you information about multivariate outliers.

Normality:

Examine the skewness and kurtosis values for each dependent variable:

Examining the histograms

Examine the Shapiro-Wilks results

5. Perform a one-way between-subjects MANOVA on the data. Before interpreting the

results of the MANOVA, check outcomes that test other assumptions for this statistic:

equality of covariance matrices (see Boxs Test) and sufficient correlation among the DVs

(see Bartletts Test of Sphericity). Also check the results of the Levenes Test of Equality

of Error Variances to evaluate that assumption for the univariate ANOVAs that are run

and show in the Tests of Between-Subjects Effects output. What have you found about

whether the data meet these additional assumptions for the MANOVA and followup

ANOVAs?

HINTS:

Be sure to read the instructions very carefully in the textbook for

what to check to get these results for these tests of assumptions (e.g., you have to

check Residual SSCP matrix within Options to get the results of the Bartletts Test

of Sphericity).

Be sure to review what a statistically significant outcome means

for each test: in some cases, it means a violation, but in others it means an

assumption is met.

6. What is the outcome of the multivariate tests (which looks at the effects of the IV on all

three DVs at the same time)? Given results of your tests for homogeneity of variancecovariance matrices for the dependent variables, is it more appropriate to use Wilks

lambda or Pillais trace to interpret outcomes, or does it make a difference? Report either

the Pillais Trace or Wilkss Lambda for your results, as well as the associated F value

and its statistical significance. Use the following format for notation: Pillais Trace OR

Wilks lambda = ____; F(df, df) = ____, p = ____, 2= _____. What does this

information tell you about the difference between the two countries on the linear

combination (the variate) of the dependent variables?

HINT:

2013. Grand Canyon University. All Rights Reserved.

Here, and ONLY for a one-way MANOVA with only two groups for the IV, eta

squared and partial eta squared are the same value; you can use the value given

for partial eta squared in the SPSS results of the Multivariate Tests to be eta

squared, 2, and save the step of hand calculating 2 .)

7. Given the results of the multivariate tests, is it OK now to move on to interpret the results

of the Tests of Between-Subjects Tests? Why? Explain. If yes, what are the results and

what do they mean? (Report each of the results using the format of F(df, df) = _____, p =

_____ , 2 = _____ for each DV. )

8. Citing the results of your statistical analyses, what is the conclusion you can draw (and

support) regarding research question that was posed in this research (see problem

statement)?

HINT: Use the sample results write-up in the textbook to see what you should

report and how to say it. Just substitute the correct language and values for the

analyses you have done for this problem.