10_18%20Threats%20to%20Validity%20in%20Experiments%20-%20Ch8

10_18 Threats to - 1 Sociology SYA4300 Professor Rob White Tuesday(10/18 Threats to Validity in Experiments 1 2 A Better Design One-group

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon

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

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

Unformatted text preview: 1 Sociology SYA4300 Professor Rob White Tuesday (10/18) Threats to Validity in Experiments 1 ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ 2 A Better Design One-group pretest-posttest design VS Two-group pretest-posttest design Time 1 Time 2 Y1a Y2a Y1 b Taking Econ Class Y2 b Time 1 Time 2 Y1 _ Taking Soc Class Y2 _ Control group. Experimental group. The “treatment” But are these two groups the same? ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ 3 Threats to Internal Validity 3. Selection bias: differential selection of respondents into the experimental group and the control group Ex: groups are different in some characteristics, (e.g., students who are more concerned about racial issues take sociology classes) and the difference in outcome may be due to these differences rather than the treatment Types of selection: a) Observed selection (e.g. gender, age, etc. Solution: statistical control, make the groups comparable) b) Unobservable selection (e.g., unmeasured attitudes, ability, motivation, etc. No quick and easy solution) ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ 2 4 Threats to Internal Validity 3a. Endogeneity bias: a type of unobserved selection bias, occurs when two conditions occur: 1. Treatment effects differ across subjects, 2. and subject selection into the experimental group is a function of the treatment 3b. Experimental mortality: differential attrition rates of the comparison groups. ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ ___________________________________ 5 Threats to Internal Validity 4. Treatment misspecification: 4a. Contamination: Either the experimental group or the control group is aware of each other and influenced in the posttest as a result....
View Full Document

This note was uploaded on 11/09/2011 for the course SYA 4300 taught by Professor Staff during the Fall '08 term at University of Florida.

Page1 / 7

10_18 Threats to - 1 Sociology SYA4300 Professor Rob White Tuesday(10/18 Threats to Validity in Experiments 1 2 A Better Design One-group

This preview shows document pages 1 - 3. Sign up to view the full document.

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