Lecture 14 - C Multiple time series design 1 O1 O2 O3 O4 X...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Comm. 88 Lecture 14 November 18, 2008 I. Quasi-Experimental Designs A. Time Series Designs 1. Track many observations over time , before and after a manipulation. B. Single-group interrupted time series design 1. O1 O2 O3 O4 X O5 O6 O7 O8 (group 1) 2. Pretests, then manipulation, then posttests a. Improves the “one-group pretest-posttest” b. Example: Crime prevention program Crimes Reported Jan. X Feb. 3. If you do multiple pretests and posttest you will be able to see that the crime prevention program is already going down as the months pass, and the program has no effect on the amount of crime. 4. Advantage to time series: solves some threats to internal validity (testing, maturation). a. You will be able to see a problem and fix it for the next time. b. Variation: take treatment away and then measure again i.e. if the program is actually working in preventing crime then you should close them down and see if crime goes back up.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: C. Multiple time series design 1. O1 O2 O3 O4 X O5 O6 O7 O8 (group1) 2. O1 O2 O3 O4 O5 O6 O7 O8 (group 2) 3. Improves “non-equiv control group” design a. Example: Media Literacy Program Media Literacy Scores X A B 1 2 3 4 5 6 7 8 observations b. Variation: give comparison group treatment and keep measuring. Example Study RQ: What are the effects of listening to music (while studying) on learning? IV? DV? Possible experiment: X (music) O1 (test score) group 1 R (no music) O1 (test score) group 2 Type of design? True experiment (you can make a causal claim) What can you conclude? If you find that group one on average score is significantly higher than group 2, you can conclude that music helps. High internal validity but low external validity. Now, what if we want to test for effects of another IV? I. Factorial Design A. Purpose: 1. To examine the effects of two or more IVs simultaneously B. Factors (IVs) 1....
View Full Document

This note was uploaded on 01/20/2010 for the course COMM comm10 taught by Professor Klein during the Spring '10 term at West Valley.

Page1 / 2

Lecture 14 - C Multiple time series design 1 O1 O2 O3 O4 X...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online