Page 178 - [Uma_Sekaran]_Research_methods_for_business__a_sk(BookZZ.org)

162 EXPERIMENTAL DESIGNS

scores O 3 and O 4 (pre- and posttest scores of Group 2) remain the same, then it
is established that neither history, nor maturation, nor testing, nor instrumenta-
tion, nor statistical regression, nor morality has had an impact. In other words,
these have had no impact at all.
Group 3, the experimental group that was not given a pretest, helps to estab-
lish whether or not testing effects have affected internal validity in a given exper-
iment. The difference, if any, between O 2 (the posttest score of Group 1, which
was exposed to a treatment and also took a pretest) and O 5 (the posttest score
of Group 3, which was exposed to a treatment but did not take the pretest), can
be attributed to the testing effects. If, however, O 2 and O 5 are equal, then inter-
nal validity has not been thwarted by testing effects.
Group 4 (which has had only the posttest score but not the pretest or expo-
sure to any treatment) helps us to see whether or not changes in the posttest
scores for our experimental group are a function of the combined effects of his-
tory and maturation by comparing O 6 (the posttest score of the control group
without the pretest) with O 1 (the pretest score of the experimental group that
was exposed to a pretest) and O 3 (the pretest score of the control group that was
exposed to a pretest as well). If all three scores are similar, maturation and his-
tory effects have not been a problem.
Thus, the Solomon four-group experimental design guarantees the maximum
internal validity, ruling out many other rival hypotheses. Where establishing
cause-and-effect relationship is critical for the survival of businesses, as for exam-
ple pharmaceutical companies, which often face lawsuits for questionable prod-
ucts, the Solomon four-group design is eminently useful. However, because of
the number of subjects that need to be recruited, the care with which the study
has to be designed, the time that needs to be devoted to the experiment, and
other reasons, the cost of conducting such an experiment is high. The experi-
mental setup shown in Figure 7.4 with one experimental and one control group,
exposing both to the posttest only, is a viable alternative since it has many of the
advantages of the Solomon four-group design and can do with just half the num-
ber of subjects.
Table 7.2 summarizes the threats to internal validity covered by the different
experimental designs. If the subjects have all been randomly assigned to the
groups, then selection biases and statistical regression are eliminated in all cases.

Double-Blind Studies
When extreme care and rigor are needed in experimental designs as in the case
of discovery of new medicines that could impact on human lives, blind studies
are conducted to avoid any bias that might creep in. For example, pharmaceuti-
cal companies experimenting with the efficacy of newly developed drugs in the
prototype stage ensure that the subjects in the experimental and control groups
are kept unaware of who is given the drug, and who the placebo. Such studies
are called blind studies.
When Aviron tested and announced the Flu-mist vaccine, neither the subjects
nor the researchers who administered the vaccine to them were aware of the