1.) Internal validity asks the question: do the conclusions that we draw about a demonstrated experimental relationship truly imply cause? External validity asks the question: does an observed causal relationship generalize across persons, settings, and times? Each type of validity has specific threats. Threats of internal validity are history, maturation, testing, instrumentation, selection, statistical regression, and experimental mortality. When it comes to history, during the time an experience is taking place, some events may occur that will confuse the relationship that is being studied. Maturation is changes that may also occur within the subject that are the functions of the passage of time and are not specific to any particular event. A subject can become hungry, bored, or tired in a short amount of time, which can ultimately affect the response results (Cousert, 2013, p. 231). The process of test taking can affect the scores of a second test. The experience from taking the first test can have a learning effect that can influence the results of the second test. When it comes to instrumentation, the threat to validity will result from the changes between observations in either the measuring instrument or the observer. When using different observers, this can threaten validity. There may also be a problem if the same observer is used for all of the measures. The observer experience, boredom, fatigue, and anticipation can all distort the results of separate observations. Selection can also be an important threat to internal validity. Validity considerations require that the groups be equivalent in every respect. If the subjects are randomly assigned to experimental and control groups, then this selection problem can be too much to overcome. Matching the members of the groups on key factors can enhance the equivalence of the groups. Statistical regression is a factor that operates especially when the groups have been selected by their extreme scores. Lastly, experiment mortality occurs when the composition of the study groups changes during the test. Attrition is especially likely in the experimental group, and with each dropout, the group changes. There are 5 additional threats to internal validity which are: diffusion or imitation of the treatment, compensatory equalization, compensatory rivalry, and resentful demoralization of the disadvantaged. The first three of these effects have the effect of equalizing the experimental and control groups (Cousert, 2013, p. 232). External validity is concerned with the interaction of the experimental treatment with other factors and the resulting impact on the ability to generalize to times, settings, or persons. There are some major threats to external validity which are: reactivity of testing on X, interaction of selection and X, and other reactive factors. The reactive effect refers to the sensitizing subjects of a pretest so that the will respond to the experimental stimulus (X) in a different way. Before measurement of a subject’s knowledge about the ecology programs will more often than not sensitize the subject to the various experimental communication efforts that can possibly be made about the company. When dealing with the interaction of selection and X, this is where the
