Internal Validity Tutorial


myAU\|	Login

g. Experimental Mortality

In the course of an experiment, some subjects may drop out before it is completed. Suppose that subjects in two comparison groups differ with respect to the independent variable. Suppose also that subjects in one group are more likely to discontinue their participation part way through an experiment than subjects in another group and that dependent variable is measured at the end of the experiment. If scores on the dependent measure differ between those subjects remaining in the two groups, the discrepancy may be due to the independent variable or to a unique characteristic of subjects able to endure a particular condition, a subject-related variable that would be disproportionately present in each group.

Background Information

Example

The name of each child in the classes was written on a separate slip of paper. All the slips were put in a bowl and mixed up thoroughly. Students were assigned to the Experimental Group and to the Control Group alternately as their names were pulled out of the bowl one at a time. One day at school, the children in the Control Group were told to go to one room and children in the Experimental Group to another room, where they were exposed to their respective conditions. Some of the children in the Experimental Group appeared bored by the interactive video, became disruptive, and were removed from the room. Two days later, the Generalization Probe was conducted. The mean score for children in the Control Group was 1.2 and the mean score for the remaining children in the Experimental Group was 3.4. We conclude that the 20-minute interactive video improved the children's self-protection skills in a potential abduction situation.

Nonexample

One day at school, the children viewed the 20-minute cartoon (Control condition). Two days later, the Generalization Probe was conducted. Then, in a class the following week, the children viewed the 20-minute interactive video (Experimental condition). Some of the children appeared bored by the interactive video, became disruptive, and were removed from the room. Two days after that, a second Generalization Probe was conducted. The data for the children who left the room during the interactive video were discarded. For the remaining children, their mean score on the first Generalization Probe was 1.2 and their mean score on the second Generalization Probe was 3.4. We conclude that the 20-minute interactive video improved the children's self-protection skills in a potential abduction situation.

Analysis

The first item is an example in which experimental mortality is a threat to internal validity. Children in the Experimental Group who were unable to watch the entire interactive video may possess a unique characteristic, such as a poor attention span. Children having this trait were excluded from the Experimental Group but not from the Control Group. The higher Generalization Probe score by the Experimental Group may be due to exposure to the interactive video or to a subject-related variable such as attention span ability, which would be unequally distributed between the two comparison groups.

In the second item, any subject-related variable pertinent to the inability to watch the entire interactive video was excluded from both comparison groups, and thus would be equally distributed between the two of them. We can be confident that the better Generalization Probe score for the Experimental Group was not the result of experimental mortality. While this experiment appears to be internally valid, discarding the data of those children who did not watch the entire video lowers the external validity of the study, a concept that is beyond the scope of this tutorial.

g. Experimental Mortality

Copyright © 1998 Athabasca University