Non-equivalent Control Group Pretest-posttest Design

Learning Objectives

Explain what quasi-experimental research is and distinguish information technology conspicuously from both experimental and correlational research.
Describe three unlike types of ane-group quasi-experimental designs.
Identify the threats to internal validity associated with each of these designs.

One-Group Posttest Just Blueprint

In aone-group posttest just design,a treatment is implemented (or an contained variable is manipulated) and then a dependent variable is measured one time afterwards the treatment is implemented. Imagine, for case, a researcher who is interested in the effectiveness of an anti-drug education plan on elementary school students' attitudes toward illegal drugs. The researcher could implement the anti-drug programme, and and then immediately after the program ends, the researcher could measure out students' attitudes toward illegal drugs.

This is the weakest type of quasi-experimental design. A major limitation to this pattern is the lack of a control or comparison grouping. There is no way to determine what the attitudes of these students would have been if they hadn't completed the anti-drug program. Despite this major limitation, results from this blueprint are frequently reported in the media and are often misinterpreted by the general population. For instance, advertisers might claim that fourscore% of women noticed their skin looked vivid afterward using Brand Ten cleanser for a month. If there is no comparison group, then this statistic means little to nothing.

One-Group Pretest-Posttest Design

In a 1-grouppretest-posttest design, the dependent variable is measured once before the treatment is implemented and one time after information technology is implemented. Let's return to the case of a researcher who is interested in the effectiveness of an anti-drug education programme on simple school students' attitudes toward illegal drugs. The researcher could measure the attitudes of students at a particular elementary school during one week, implement the anti-drug program during the adjacent calendar week, and finally, measure their attitudes once more the following week. The pretest-posttest blueprint is much like a within-subjects experiment in which each participant is tested showtime under the control condition and so under the treatment condition. It is different a within-subjects experiment, even so, in that the club of conditions is non counterbalanced because it typically is not possible for a participant to be tested in the handling condition first and and then in an "untreated" control condition.

You might discover that the pretest-posttest design is much like a within-subjects experiment in which each participant is tested beginning under the control condition and then under the treatment condition. It is unlike a within-subjects experiment, however, in that the lodge of conditions is not counterbalanced because it typically is non possible for a participant to be tested in the treatment condition kickoff and so in an "untreated" control condition.

If the average posttest score is better than the average pretest score (e.thou., attitudes toward illegal drugs are more than negative after the anti-drug educational program), and so it makes sense to conclude that the treatment might be responsible for the improvement. Unfortunately, i often cannot conclude this with a high degree of certainty because in that location may exist other explanations for why the posttest scores may take changed. One category of culling explanations goes nether the name ofhistory. Other things might have happened between the pretest and the posttest that caused a change from pretest to posttest. Possibly an anti-drug programme aired on goggle box and many of the students watched it, or perhaps a celebrity died of a drug overdose and many of the students heard nigh it.

Some other category of alternative explanations goes under the proper noun ofmaturation. Participants might have changed between the pretest and the posttest in means that they were going to anyway because they are growing and learning. If information technology were a year long anti-drug program, participants might go less impulsive or ameliorate reasoners and this might exist responsible for the change in their attitudes toward illegal drugs.

Another threat to the internal validity of one-group pretest-posttest designs istestingwhich refers to when the act of measuring the dependent variable during the pretest affects participants' responses at posttest. For instance, completing the mensurate of attitudes towards illegal drugs may accept had an effect on those attitudes. Simply completing this measure out may accept inspired further thinking and conversations well-nigh illegal drugs that so produced a change in posttest scores.

Similarly, instrumentationcan be a threat to the internal validity of studies using this pattern. Instrumentation refers to when the bones characteristics of the measuring musical instrument change over time. When homo observers are used to mensurate behavior, they may over time proceeds skill, become fatigued, or change the standards on which observations are based. So participants may have taken the measure of attitudes toward illegal drugs very seriously during the pretest when it was novel but then they may accept become bored with the measure at posttest and been less careful in considering their responses.

Another culling explanation for a modify in the dependent variable in a pretest-posttest blueprint isregression to the mean. This refers to the statistical fact that an individual who scores extremely on a variable on one occasion will tend to score less extremely on the next occasion. For example, a bowler with a long-term average of 150 who of a sudden bowls a 220 volition almost certainly score lower in the side by side game. Her score will "backslide" toward her hateful score of 150. Regression to the mean tin exist a trouble when participants are selected for further written reportbecause of their extreme scores. Imagine, for case, that only students who scored peculiarly high on the test of attitudes toward illegal drugs (those with extremely favorable attitudes toward drugs) were given the anti-drug program and then were retested. Regression to the mean all but guarantees that their scores will be lower at the posttest even if the training programme has no effect.

A closely related concept—and an extremely important 1 in psychological inquiry—isspontaneous remission. This is the tendency for many medical and psychological problems to better over fourth dimension without whatever form of handling. The common cold is a skilful example. If one were to measure out symptom severity in 100 common cold sufferers today, give them a basin of chicken soup every day, and then mensurate their symptom severity again in a calendar week, they would probably be much improved. This does not mean that the craven soup was responsible for the improvement, however, considering they would take been much improved without any treatment at all. The same is true of many psychological problems. A group of severely depressed people today is likely to exist less depressed on average in 6 months. In reviewing the results of several studies of treatments for depression, researchers Michael Posternak and Ivan Miller institute that participants in waitlist command conditions improved an boilerplate of 10 to 15% before they received any treatment at all (Posternak & Miller, 2001)^[1]. Thus one must more often than not be very cautious about inferring causality from pretest-posttest designs.

Does Psychotherapy Work?

Early studies on the effectiveness of psychotherapy tended to use pretest-posttest designs. In a classic 1952 article, researcher Hans Eysenck summarized the results of 24 such studies showing that virtually 2 thirds of patients improved betwixt the pretest and the posttest (Eysenck, 1952) ^[2]. But Eysenck too compared these results with archival data from state hospital and insurance visitor records showing that similar patients recovered at virtually the same rate without receiving psychotherapy. This parallel suggested to Eysenck that the comeback that patients showed in the pretest-posttest studies might be no more than spontaneous remission. Note that Eysenck did not conclude that psychotherapy was ineffective. He merely concluded that at that place was no show that it was, and he wrote of "the necessity of properly planned and executed experimental studies into this important field" (p. 323). You can read the unabridged article hither:

http://psychclassics.yorku.ca/Eysenck/psychotherapy.htm

Fortunately, many other researchers took up Eysenck's challenge, and past 1980 hundreds of experiments had been conducted in which participants were randomly assigned to treatment and control conditions, and the results were summarized in a archetype book by Mary Lee Smith, Gene Glass, and Thomas Miller (Smith, Glass, & Miller, 1980) ^[iii]. They found that overall psychotherapy was quite effective, with nearly 80% of treatment participants improving more than the average control participant. Subsequent research has focused more on the weather condition under which different types of psychotherapy are more or less effective.

Interrupted Fourth dimension Series Blueprint

A variant of the pretest-posttest design is the interrupted time-serial design . A fourth dimension series is a set of measurements taken at intervals over a period of time. For case, a manufacturing company might measure its workers' productivity each week for a twelvemonth. In an interrupted time serial-design, a time series like this one is "interrupted" past a treatment. In one classic instance, the handling was the reduction of the work shifts in a mill from x hours to eight hours (Melt & Campbell, 1979) ^[4]. Because productivity increased rather quickly after the shortening of the work shifts, and considering it remained elevated for many months afterward, the researcher concluded that the shortening of the shifts acquired the increment in productivity. Detect that the interrupted fourth dimension-series design is similar a pretest-posttest design in that it includes measurements of the dependent variable both before and later the treatment. Information technology is unlike the pretest-posttest pattern, still, in that it includes multiple pretest and posttest measurements.

Figure viii.1 shows data from a hypothetical interrupted time-series report. The dependent variable is the number of pupil absences per week in a research methods course. The treatment is that the instructor begins publicly taking attendance each twenty-four hour period and so that students know that the teacher is aware of who is present and who is absent. The elevation console of Figure 8.one shows how the data might look if this treatment worked. At that place is a consistently loftier number of absences before the treatment, and in that location is an immediate and sustained drop in absences after the treatment. The bottom panel of Figure 8.1 shows how the data might expect if this treatment did not piece of work. On average, the number of absences after the handling is about the same as the number before. This figure also illustrates an advantage of the interrupted time-series design over a simpler pretest-posttest blueprint. If there had been only one measurement of absences before the handling at Week 7 and 1 afterward at Week 8, so information technology would have looked as though the handling were responsible for the reduction. The multiple measurements both before and after the handling suggest that the reduction betwixt Weeks 7 and 8 is nothing more than normal week-to-week variation.

Figure 7.3 A Hypothetical Interrupted Time-Series Design. The top panel shows data that suggest that the treatment caused a reduction in absences. The bottom panel shows data that suggest that it did not.

Figure 8.ane A Hypothetical Interrupted Time-Serial Design. The height console shows data that advise that the handling caused a reduction in absences. The bottom console shows data that suggest that it did not.