DOC PREVIEW
UNL PSYC 971 - Homework 3

This preview shows page 1-2 out of 6 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 6 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 6 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 6 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Homework 3 Here are data from a 2-condition between subjects design (whether or not each participant had previous experience with the class material). Participants were permitted to take as many review exams as they wanted (which were observed and measured) and then, completed the exam. The DV is a performance score. In addition to the linear, group and their interaction effect, this analysis will examine the quadratic relationship between number of review exams and performance, as well as the possibility of a non-inear interaction term (that the shape of the relationship between number of review exams and performance may be different for the two groups). data  numrev.sav 1. Get the univariate statistics for the number of review exams variable mean = ______________ std = _______________2. Preparing variables for the analysis- Construct a dummy code for the previous experience variable with “no previous experience” as the target group - Construct a centered version of the quantitative number of review exams variable- Construct a quadratic term for the number of review exams variable (specifically a quadratic term, not linear+quadratic)- Construct a linear interaction term between number of review exams and previous experience- Construct a quadratic interaction term between number of review exams and the quadratic term for previous experience3. Getting “hierarchical” analyses (it is easier to use regression, but you may use GLM if you prefer – use FTZ to compute R²Δ tests). Be sure to tell me what you learned from each model and/or model test.a. What were the results of the main effects model? R² _______________ F _____________ p____________What did you learn from this?b. What were the results of the model with the quad term? R² _______________ F _____________ p____________What did you learn from this?c. Compare the models w/ and w/o the quad term ? R²-change ____________ F-change __________ p ______What did you learn from this?d. What were the results of adding the linear 2-way? R² _______________ F _____________ p____________What did you learn from this?e. Compare the models w/ and w/o the linear 2--way ? R²-change ____________ F-change __________ p ______What did you learn from this?f. What were the results of adding the non-linear 2-way? R² _______________ F _____________ p____________What did you learn from this?g. Compare the models w/ and w/o the non-linear 2--way ? R²-change ____________ F-change __________ p ______What did you learn from this?h. Why might someone prefer this set of analyses to a single full-model analysis?i. Can you reduce this model (i.e., leave out any noncontributing terms)??? Explain your answer carefully.4. Getting an “alternative” analyses: Imagine that you have previously explored the main effects and interactions of experience group and number or review exams taken, as well as their interaction, but have never previously explored the possibility of nonlinear terms or interactions. So, you decide on the following modeling and model comparison sequence. (Note: It is easier to use regression, but you may use GLM if you prefer – use FTZ to compute R²Δ tests). Be sure to tell me what you learned from each model and/or model test.a. What were the results of the main effects model? R² _______________ F _____________ p____________What did you learn from this?b. What were the results of the model with the interactioin? R² _______________ F _____________ p____________What did you learn from this?j. Compare the models w/ and w/o the interaction ? R²-change ____________ F-change __________ p ______What did you learn from this?k. What were the results of adding quadratic term? R² _______________ F _____________ p____________What did you learn from this?l. Compare the models w/ and w/o the quadratic term ? R²-change ____________ F-change __________ p ______What did you learn from this?m. What were the results of adding the quad interaction? R² _______________ F _____________ p____________What did you learn from this?n. Compare the models w/ and w/o the quad interaction? R²-change ____________ F-change __________ p ______What did you learn from this?o. Why might someone prefer this set of analyses to the previous analysis?p. Can you reduce this model (i.e., leave out any noncontributing terms)??? Explain your answer carefully.5. Complete the following for the full model. Predictor b t(p) βPrevious ExperienceNumber of Practice ExamsQuadratic term for Number of Practice ExamsLinear Interaction termQuadratic Interaction termconstant5. Report the regression model for each Previous Experience groupNo Previous Exp perf’ = Previous Exp perf’ = 6. Plot the regression equation on other paper be sure to plot to +/- 2 std on the x axis7. Answer the following based on the plot and the regression modela. To what specific effect does the Task Experience regression weight refer? Describe that specific effect.b. Describe the main effect for Task Experience.c. Is the main effect for Task Experience descriptive or potentially misleading? Carefully explain your answer.d. To what specific effect does the Number of Practice Exams regression weight refer? Describe that specific effect.e. Describe the main effect for Number of Practice Exams.f. Is the main effect for Number of Practice Exams descriptive or potentially misleading? Carefully explain your answer.g. To what specific effect does the Quadratic Number of Practice Exams regression weight refer? Describe that specific effect.h. Describe the Quadratic component of the main effect for Number of Practice Exams.i. Is the quadratic component of the main effect for Number of Practice Exams descriptive or potentially misleading? Carefully explain your answer.j. What specific information is given by the Task Familiarity * Number of Practice Exams interaction regression weight?k. Describe the interaction of Task Familiarity * Number of Practice Exams interactionl. What specific information is given by the quadratic term of the Task Familiarity * Number of Practice Exams interaction regression weight?m. Describe the interaction of quadratic term of the Task Familiarity * Number of Practice Exams interactionn. What specific information is given by the constant?The data were collected to examine the relationships practice, age, initial performance, and their


View Full Document

UNL PSYC 971 - Homework 3

Download Homework 3
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Homework 3 and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Homework 3 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?