Chapter 9 Lecture - Chapter 9 Quasi-Experimental Design...

Info iconThis preview shows pages 1–7. Sign up to view the full content.

View Full Document Right Arrow Icon
Copyright Atomic Dog Publishing, 2005 Chapter 9 Quasi-Experimental Design
Background image of page 1

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

View Full DocumentRight Arrow Icon
Copyright Atomic Dog Publishing, 2005 Quasi-Experimental Design Has several key features of experimental design: Pre-post measurement Treatment-control group comparisons But: Lacks random assignment to treatment group Non-equivalent groups design Regression discontinuity Others
Background image of page 2
Copyright Atomic Dog Publishing, 2005 Nonequivalent-Groups Design (NEGD) One of the most used designs in social research Pre-post two-group quasi-experimental design structured like randomized experiment without random assignment to groups The central challenge is determining the equivalency of groups ( selection threat to internal validity) Notation: N O X O N O O
Background image of page 3

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

View Full DocumentRight Arrow Icon
Copyright Atomic Dog Publishing, 2005 Possible outcomes with the NEGD The bivariate distribution Bivariate plots of pre- and post-test mean scores for the treatment and comparison groups make visible possible threats to internal validity Note: Differences between pre-test scores? Differences between post-test scores? Differences between rates of increase? Group scores moving in the expected direction ? Any crossover effect?
Background image of page 4
Copyright Atomic Dog Publishing, 2005 Possible Outcome #1 Selection-maturation threat—comparison group is not growing. Selection-history threat—a possibility. Regression to the mean—program group is moving away from the comparison group.
Background image of page 5

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

View Full DocumentRight Arrow Icon
Possible Outcome #2 Selection maturation threat—this is what it looks like. Selection history threat—a possibility.
Background image of page 6
Image of page 7
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/11/2011 for the course CHFD 5110 taught by Professor Johnson during the Spring '11 term at University of Georgia Athens.

Page1 / 27

Chapter 9 Lecture - Chapter 9 Quasi-Experimental Design...

This preview shows document pages 1 - 7. Sign up to view the full document.

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