Research - Module 7 Drop Box assignment

QUANTITATIVE RESEARCH

METHODOLOGIES

Experimental, Quasi-Experimental, and Ex Post Facto Designs Chapter Nine

Experimental Design

 This can be used to identify cause-and-effect

relationships

 Independent variable is one that the researcher

studies as a possible cause of something else

 Dependent variable is a variable that is potentially

influenced by the independent variable

Importance of Control

 The extent to which an experimental study’s design and data allow the researcher to draw legitimate conclusions about cause-and-effect and other relationships is internal validity

 Internal validity is essential in experimental designs

 Whenever we compare two or more groups that are or might be different in ways in addition to the particular treatment or intervention we are studying, we have confounding variables

 Confounding variables threaten internal validity

Controlling for Confounding Variables

 Keep some things constant

 Include a control group

 Randomly assign people to groups

 Assess equivalence before the treatment with one or more pretests

 Expose participants to all experimental conditions

 Statistically control for confounding variables

 Partial correlation

 Analysis of covariance (ANCOVA)

 Structural equation modeling

Overview of Experimental, Quasi-

Experimental, and Ex Post Facto

Designs  In true experimental research, the researcher

manipulates the independent variable and

examines its effects on another, dependent variable

 A variety of research designs have emerged that

differ in the extent to which the researcher

manipulates the independent variable and controls

for confounding variables (the designs differ in the

degree to which they have internal validity)

5 Design Categories

 Pre-experimental designs

 True experimental designs

 Quasi-experimental designs

 Ex post facto designs

 Factorial designs

Pre-Experimental Designs

 One-Shot Experimental Case Study

 One-Group Pretest-Posttest Design

 Static Group Comparison

True Experimental Designs

 Pretest-Posttest Control Group Design

 Solomon Four-Group Design

 Posttest-Only Control Group Design

 Within-Subjects Design

Quasi-Experimental Designs

 Nonrandomized Control Group Pretest-Posttest

Design

 Simple Time-Series Design

 Control Group, Time-Series Design

 Reversal Time-Series Design

 Alternating Treatments Design

 Multiple Baseline Design

 Single-Subject Studies

Ex Post Facto Designs

 Simple Ex Post Facto Design

Factorial Designs

 Two-Factor Experimental Design

 Combined Experimental and Ex Post Facto Design

Meta-Analyses

 When researchers have conducted many

replications of a study, another researcher may

conduct a meta-analysis (an analysis of the

analyses

 A meta-analysis is primarily a statistical technique