Credibility and Generalizability in the Experiment

Construct validity

characterizes the quality of operationalization. Remember that operationalization is how a researcher applies a measurable quality to a behavior.

Internal validity

characterizes the methodological quality of the experiment. Internal validity is high when the confounding variables have been controlled and high certainty the IV caused the change in DV.

External validity

characterizes how the results of the research can be generalized back to the population as a whole.

Bias

comes from may confounding factors which interfere with the cause and effect relationship between the IV and DV, decreasing the researcher’s certainty.

Selection (bias)

occurs when groups are not equivalent from the start of the experiment.

History (bias)

when outside events happen to participants in the course of the experiment.

Maturation (bias)

during the experiment, participants go through natural development, such as fatigue or simply growth.

Experimenter bias

occurs when the experimenter influences the results unintentionally.

Testing effect (bias)

Instrumentation (bias)

this effect occurs when the instrument measuring the DV changes slightly between measurements. This is like if an observer measuring a behavior.

Regression to the mean

this occurs when the resulting DV’s measurement is extreme (either too low or high).

Experimental mortality

refers to the fact that some participants leave or drop out from the experiment, especially if not random.

Demand characteristics

this situation happens when participants understand the purpose of the experiment and change their behavior to fit the experiment.

Quasi-experiment

Quasi-almost; in this experiment, the groups are not made randomly and are grouped based upon pre-existing differences like age, gender, culture, and/or occupation.

Field experiments

experiments that are conducted in real life settings. The researcher manipulates the IV, but the participants are in their natural setting.

Natural experiments

conducted in participants’ natural environment, but here the researcher has no control over the IV- the IV occurred naturally.