M7 Assignment (40 points)
Instruction:
- Review the Assignment Guides, which contains tutorials on how to show the math/process work and examples of assignment answers
- Use this Word document to fill in the answers to the questions. You must type out a clear answer to each question, even if the answer is also contained in the SPSS output.
- Download the Excel file for this assignment and use that data set to answer all the questions in this assignment. Import the data into SPSS if instructed to do so.
- Use a = .05 for all hypothesis testing unless otherwise specified.
Research Scenario:
This data set was adapted from a longitudinal project examining the relationship between aging and cognitive functions. The data set contains both demographic information and cognitive performance scores.
Importing data into SPSS (1 point)
Import the Excel data set into SPSS and configure each variable based on the information in the Codebook worksheet in the Excel file. Paste a screen shot of the Variable View to show the following:
– All variables are imported
– Each variable is correctly configured in “Measure” under the “Variable View”
– All nominal variables have the “Values” specified.
(1 point: Deduct .5 for each missing/incorrect element up to 1)
General Tips for Q1–Q3:
- After importing the data into SPSS, all the questions in Q1 to Q3 can be answered by running Descriptive Statistics – Explore, although some of them can also be done through different analysis choices in SPSS.
- When examining multiple variables, you may enter all of them in the Dependent List or run the analysis on one variable at a time. But the preferred method is to analyze one variable at a time so that the results are clear and easy to interpret. (There is no need to specify “factor” for this analysis.)
- The options for answering Q1-Q3 include:
- Descriptive statistics like mean and standard deviation
- Missing data: total number and percentage of missing data in each variable
- Box plot
- Histogram with normality line and tests of normality
Q1. Checking for missing data (2 points total)
Run Descriptive Statistics – EXPLORE on each variable in the data file for missing data and then answer the following questions.
Hint: You may run one variable at a time or enter all the variables as “dependent” at the same time. But if you analyze all variables at the same time, be sure to select “Exclude cases pairwise” rather than “Exclude cases listwise” so that you will get the result for each individual variable. Each variable should have a unique amount of missing data. If they all have the same percentage of missing data, then the result is not correct.
- Paste the table(s) here to show the number and percentage of missing data in each variable of the data set. (1 point: Deduct .5 for each error, up to 1 total)
- Examine the table(s) of missing data for the variable and answer the following questions:
– Which variable has the most missing data? What’s the percentage?
– Do you think this will be an issue for data analysis? Will you exclude those with missing data in this variable from all analyses?
Hint: There is no standard answer to the second question. Your answer just needs to be logical and reflects your statistical knowledge.
(1 point: .5 for each question)
Q2. Checking for outliers (7 points total)
In this question set, we examine the three scale variables for outliers.
– Use box plot to identify extreme values in each variable
– Calculate Z score for each extreme value to determine if it is an outlier (criterion: Z = 2.5/-2.5)
- Check Verb IQ for outliers
- Paste Box plot and report how many extreme values are shown (.5 point, both need to be correct)
- Report M and s (.5 point)
- Calculate Z score for each extreme value (.5 point)
- How many outliers are there? (.5 point)
- Check Age for outliers
- Paste Box plot and report how many extreme values are shown (.5 point)
Report M and s (.5 point)
- Calculate Z score for each extreme value (.5 point)
- How many outliers are there? (.5 point)
- Check Executive for outliers
- Paste Box plot and report how many extreme values are shown (.5 point)
- Report M and s (.5 point)
- Calculate Z score for each extreme value (.5 point)
- How many outliers are there? (.5 point)
- D. Consider the outlier(s) identified above, would you exclude the outlier(s) from analysis? Why or why not? (1 point: .5 for decision, .5 for rationale)
Hint: There is no standard “correct” answer. An answer is acceptable if the rationale is logical and it demonstrates your knowledge about outliers.
Q3. Checking the normality assumption (6 points total)
In this question set, we examine the three scale variables to check the normality assumption.
– Use histogram to get a visual evaluation.
– Use Shapiro-Wilk’s test of normality to determine if a variable meets the assumption
- Check VerbIQ for the normality assumption.
- Paste the histogram of this variable (.5 point)
- Paste the table for Tests of Normality (.5 point)
- Determine whether the variable meets the normal assumption based on Shapiro-Wilk’s test result and explain your rationale (1 point: .5 for decision, .5 for rationale)
- Check Age for Normality assumption.
- Paste the histogram for this variable (.5 point)
- Paste the table for Tests of Normality (.5 point)
- Determine whether the variable meets the normal assumption based on Shapiro-Wilk’s test result and explain your rationale (1 point: .5 for decision, .5 for rationale)
- Check Executive for the normality assumption.
- Paste the histogram with a normal curve (.5 point)
- Paste the table for Tests of Normality (.5 point)
- Determine whether the variable meets the normal assumption based on Shapiro-Wilk’s test result and explain your rationale (1 point: .5 for decision, .5 for rationale)
Q4. Analyzing data to answer research question (8 points)
Research Question: Does the participants’ age differ significantly across different marital status (Marital) groups?
For this analysis, assume that the variables meet all the assumptions for the statistical test you wish to perform. Use = .05.
- What is your chosen hypothesis test? What is the rationale?
(1 point: .5 for test, .5 for rationale)
- What are the null hypothesis and alternative hypothesis for the test?
(1 point: .5 for each hypothesis)
- Perform your chosen analysis and paste the main result table from SPSS.
(1 point)
- Report the omnibus test result using symbols in the APA format. Be sure to include the test statistic (including degrees of freedom), the p value, and the effect size.
– Report the statistics in one line separated by commas
– Italicize the statistic symbols
(3 points total: deduct .5 for each error in value or format up to 3 total)
- Draw a conclusion on the hypothesis test result (whether the null hypothesis is rejected or not) and answer the research question accordingly.
(2 points: 1 for hypothesis test result, 1 for answering the research question)
Q5. Analyzing data to answer research question (8 points)
Research Question: Can a person’s executive function (Executive) predict his/her verbal IQ (verbIQ)?
For this analysis, assume that the variables meet all the assumptions for the statistical test you wish to perform. Use = .05.
- What is your chosen hypothesis test? What is your rationale?
(1 point: .5 for test, .5 for rationale)
- What are the null hypothesis and alternative hypothesis for the test?
(1 point: .5 for each hypothesis)
- Perform your chosen hypothesis test and paste the main result table(s) from SPSS that contain the test statistic, p value, and effect size.
1 point: If the pasted tables show some statistics but not all three, deduct .5
- Report the omnibus test result using symbols in the APA format. Be sure to include the test statistic (including degrees of freedom), the p value, and the effect size.
– Report the statistics in one line separated by commas
– Italicize the statistic symbols
(3 points total: Deduct .5 for each error in value or format up to 3 total)
- Draw a conclusion on the hypothesis test result (whether the null hypothesis is rejected or not) and answer the research question accordingly.
(2 points: 1 for hypothesis test result, 1 for answering the research question)
Q6. Analyzing data to answer research question (8 points)
Research Question: Do males and females differ in verbal IQ (VerbIQ)?
For this analysis, assume that the variables meet all the assumptions for the statistical test you wish to perform. Use = .05.
- What is your chosen hypothesis test? What is your rationale?
(2 points: 1 for test, 1 for rationale)
- What are the null hypothesis and alternative hypothesis for the test?
(1 point: .5 for each hypothesis)
- Perform your chosen hypothesis test and paste the main result table(s) from SPSS that contain the test statistic, p value, and effect size (if available from SPSS).
(1 point: If the pasted tables show some statistics but not all three, deduct .5)
- Report the omnibus test result using symbols in the APA format. Be sure to include the test statistic (including degrees of freedom) and the p value. (No need to include effect size for this analysis.)
– Report the statistics in one line separated by commas
– Italicize the statistic symbols
(2 points total: deduct .5 for each error in value or format up to 2 total)
- Draw a conclusion on the hypothesis test result (whether the null hypothesis is rejected or not) and answer the research question accordingly.
(2 points: 1 for hypothesis test result, 1 for answering the research question)
