Scenario:
You are the new director of institutional research at a small state university, and you have been assigned the task of analyzing information for the dean of the School of Education regarding the performance of their undergraduate students on the often-controversial Graduate Record Exam (GRE). Many educators believe the GRE is a poor evaluator of undergraduate performance as well as a poor predictor of graduate school performance. The dean is considering eliminating the GRE from graduate school admissions requirements.
The dean has already collected data on four variables: 1) gender, 2) grade point average (GPA), 3) GRE score, and 4) graduate degree completion frequency. Your job is to develop a proposed analysis to assist the dean to make an informed decision regarding the future use of the GRE.
Note:
(For this assignment, you don't have to produce any data. This assignment is asking for you to develop the analyses to answer the different questions (see below 1 - 4); relationships questions (What analyses can you use for relationship questions? What types of data (level of measurement)?), for effect questions (What analyses can you use to test for effects of independent variables on dependent variables?) Think on the levels of the independent variables. What types of data (nominal, ordinal, interval, ratio)?), and interaction effects between independent variables.
You should also discuss the assumptions of each test. No data is required to be presented. This is similar to a question that you will encounter in your Doctoral Comprehensive Exams. You should provide information that shows your understanding of the different types of analyses, as well as possible outcomes of the analyses. In addition, you have to include in your discussion the possible conclusions based on the possible results; rejecting the null, and not rejecting the null.
Using this information, develop the following foundational components for a proposed analysis
- A relationship research question involving GPA and GRE scores; corresponding null and alternative hypotheses; the type of statistical analysis to be employed to determine significance; explanations of fictitious outcomes identifying both non-significant and significant relationships as related to both null and alternative hypotheses; and recommendations based on non-significant and significant findings.