Bias in experimental research: threats to internal validity Flashcards
Selection
This occurs if for some reasonthe groups are not equivalent: apart from the planned IV-related difference, they differ in some other variable.
History
This refers to the outside events that happen in the course of the experiment. These outside events become a problem when they can potentially influence the DV or is not constants in both groups.
Maturation
In the course of the experiment participants go through natural development processes such as fatigue or simply growth. The DV might be influenced by a confounding variable (e.g aging)
Testing effect
The first measurement of the DV may affect the second (and subsequent) measurements: the repetition of of experiments could skew the results because of gained experience.
Instrumentation
This effect occurs when the instrument measuring the DV changes slightly. For psychology, this becomes relevant when you consider that an ”instrument of measurement is often a human observer. It could be called the ”researcher maturation”.
Regression to the mean
A bias that becomes a concern when the initial score on DV is extreme (either low or high). Extreme scores have a purely statistical tendency to become more average on subsequent trials.
Experimental mortality
This refers to the fact that some participants drop out during an experiment, which may become a problem if dropouts are not random.
For example, ethical questions cause more of the experimental groups participants to dropout than from the control group
Demand characteristics
This refers to a situation in which participants understand the purpose of the experiment and change their behaviour subconsiously to fit that interpretation: they behave in a way they believe the experimenter expects them to behave in
Experimenter bias
This refers to situations in which the researcher unintentionally exerts an influence on the results of the study.
