Chapter 11: Quasi- Experimental Designs This multimedia product and its contents are protected under copyright law. The following are prohibited by law: Any public performance or display, including transmission of any image over a network; Any public performance or display, including transmission of any image over a network; Preparation of any derivative work, including the extraction, in whole or in part, of any images; Preparation of any derivative work, including the extraction, in whole or in part, of any images; Any rental, lease, or lending of the program Any rental, lease, or lending of the program

Introduction Quasi-experimental design—an experimental type design that does not eliminate all threats to internal validity Quasi-experimental design—an experimental type design that does not eliminate all threats to internal validity Causal inferences are made by ruling out rival hypothesis Causal inferences are made by ruling out rival hypothesis –By identification and study of the threats –By including design elements as pretests or other control groups –By coherent pattern matching—making a complex prediction that few rival hypotheses can explain

Nonequivalent Comparison Group Design pre-test treatment posttest pre-test treatment posttest Exper. Gp Y 1 X Y 2 Exper. Gp Y 1 X Y 2 Control Gp Y 1 Y 2 Control Gp Y 1 Y 2 This is the most common quasi-experimental design This is the most common quasi-experimental design Participants not randomly assigned to groups Participants not randomly assigned to groups Threats frequently reveal themselves in the outcome Threats frequently reveal themselves in the outcome

Possible Outcome Patterns in the Nonequivalent Comparison Group Design Increasing treatment effect— Increasing treatment effect— experimental experimental control control pretestposttest pretestposttest Can be due to selection-maturation or a selection-history effect

Increasing treatment and control groups Increasing treatment and control groupsexperimental control control pretest posttest pretest posttest –Selection-maturation is a threat

Increasing treatment effect Increasing treatment effect –Statistical regression is a threat –Selection-history is a threat controlexperimental pretest posttest

Cross-over effect Cross-over effect –Statistical regression not possible experimentalcontrol pretest posttest

Causal Inference and the Nonequivalent Comparison Group Design Effect size about the same if nonequivalent comparison group design and randomized design equally well designed and executed Effect size about the same if nonequivalent comparison group design and randomized design equally well designed and executed The important quasi-experimental design characteristics are The important quasi-experimental design characteristics are –Do not let participants self-select into groups –Minimize pretest differences in groups

Time Series Design Conducts an experimental study on one group Conducts an experimental study on one group –Interrupted Time-Series design –Pre-response Treatment Post-response –Y 1 Y 1 Y 1 Y 1 X Y 2 Y 2 Y 2 Y 2 Threats to internal validity revealed in pattern of pretests Threats to internal validity revealed in pattern of pretests Treatment effect revealed by a different pattern of pre and posttest responses Treatment effect revealed by a different pattern of pre and posttest responses

Some possible patterns of pre and post treatment responses X