1 / 19

Lecture 16: Power & Project

Lecture 16: Power & Project. 2011, 11, 17. Today ’ s Lecture. When to use related-samples t -test and independent-samples t -test? How to conduct independent-samples t -test by hand?. Related-Samples t -Test.

reuel
Download Presentation

Lecture 16: Power & Project

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Lecture 16: Power & Project 2011, 11, 17

  2. Today’s Lecture • When to use related-samples t-test and independent-samples t-test? • How to conduct independent-samples t-test by hand?

  3. Related-Samples t-Test • Situation 1: When we want to compare two samples that representing two populations (e.g., women vs. men), and the two samples are related, we use related-samples t-test to exam if one population mean is greater/less/equal to the other population mean. • Situation 2: When we want to compare two set of scores collected from one sample, we use related-samples t-test to exam if posttest mean is greater/less/equal to pretest mean. • Key terms: • You must have two set of scores (two columns). • The two set of scores must relate to each other.

  4. Independent-Samples t-Test • When we want to compare two samples that representing two populations (e.g., women vs. men), and the two samples are independent, we use independent-samples t-test to exam if one population mean is greater/less/equal to the other population mean. • Key terms: • You must have two set of scores • The two set of scores must from two independent samples

  5. Question 1 • Hout, Duncan, and Sobel (1987) studied if there was any difference between men and women in the relative sexual satisfaction. They asked each member of 91 married couples to rate the degree to which they agreed with “Sex is fun for me and my partner” on a four-point scale. Here is part of their data: • Husband: 1,1,1,1,2,2,3,3,4,4,4,4 • Wife: 1,1,3,4,3,3,3,3,2,2,3,3

  6. Question 2 • Do women have more close friends than men? A recent survey reported that the 12 females had a mean of 8.9 close friends (SSF = 15.6) and the 10 males had a mean of 8.3 close friends (SSM = 17.3). Conduct a statistical test. Assume  = 0.01.

  7. Question 3: Do women have more close friends than men? • Step 1: State Hypotheses • Step 2: Set Criteria • Step 3: Compute Std. Err.

  8. Question 3: Do women have more close friends than men? • Step 4: Compute tobs • Step 5: Compare tobs to tcrit and make conclusion.

  9. = 0.05 p=.01 p=.025 p=.025 Power • The power of a statistical test: the ability to reject a null hypothesis. • Alpha • Sample size • One-tailed vs. two-tailed test p=.05

  10. Final Project • Read the description of a research project • Understand the dataset • Run some analyses • Write a report

  11. Project Description • This study investigated the effect of teaching technique on measures of learning and interest in the topic. Two sections of a sociology course received different teaching formats. One section experienced a traditional lecture format, while the second section was taught with a combination of lectures, web-based activities, and in-class exercises. Learning of the course material was measured by the grade on the final exam and interest was measured with a topical interest scale developed by the researcher.

  12. Project Dataset

  13. Research Questions • Is there a difference between the two teaching formats in learning of the material? • Which test? • Independent variable? • Dependent variable? • Is there a difference between the two teaching formats in interest in the material? • Which test? • Independent variable? • Dependent variable? • Is learning related to interest in the topic? • Which test?

  14. Final Project Checklist and Grading Policy (120 pts Total) • Format (16 pts) • Attach this sheet on the top of your project paper. (4 pts) • Double spaced (4 pts) • Complete sentences/paragraphs (4 pts) • Grammar & Spelling (4 pts)

  15. Design Description (16 pts) • Independent variable(s) (4 pts) • How is IV manipulated (4 pts) • Dependent variable(s) (4 pts) • How is DV measured (4 pts)

  16. Descriptive Statistics (16 pts) • Run descriptive statistics of each dependent variable for the whole group. Paste the descriptive table onto your project paper. Report the mean and Std. Dev. (8 pts) • Run descriptive statistics of each dependent variable for each experimental group. Paste the descriptive table onto your project paper. Report the means and standard deviations. (8 pts)

  17. Inferential Statistics: Compare Means (30 pts) • State the research hypotheses being tested and the null hypotheses (6 pts) • State the appropriate statistical tests used (e.g., 1-sample z-test, 1-sample t-test, related-sample t-test, or independent-sample t-test), and run the test (6 pts) • Paste the SPSS output onto your project paper (6 pts) • Report the relevant parts of the results of the statistical test (df, tobs, p-value) (6 pts) • Report the conclusions (reject/fail to reject) (6 pts)

  18. Inferential statistics: Test a Relationship (30 pts) • State the appropriate test used (e.g., Pearson correlation analyses or regression analysis) (6 pts) • Paste the SPSS output onto your project paper (6 pts) • Paste the scatter plots for the correlational analyses (6 pts) • Report the relevant parts of the results (6 pts) • Report the conclusions of your relationship test (6 pts)

  19. Overall Quality of the paper (12 pts) • Flow and fluency

More Related