Answer Happy

Sketch a graph of the results. (Reminder: Put thedependent variable on the y-axis.)
Decide whether the study is subject to any of theinternal validity threats listed in Table 11.1
Indicate whether you could redesign the study to corrector prevent any of the internal validity threats.
Dr. Dove was interested in the effects of eatingchocolate on well-being. She randomly assigned 20participants to two groups. Both groups ate as they normallywould, but one group was instructed to eat a 1-ounce square of darkchocolate after lunch. After 4 weeks on this diet, theycompleted a questionnaire measuring their level of well-being(happiness, contentment). Dr. Dove was surprised to find thechocolate had no effect: Both groups, on average, scored thesame on the well-being measure, and their 95% CIs overlapped. Help Dr. Dove troubleshoot her study. What should she do nexttime to improve her chances of precisely estimating the effect forthe chocolate-enhanced diet, if eating chocolate really doesimprove well-being?
TABLE 11.1 Asking About Internal Validity Threats in Experiments NAME Design confound Selection effect Order effect Maturation History Regression to the mean Attrition 338 DEFINITION A second variable that unintentionally varies systematically with the independent variable. In an independent-groups design, when the two independent variable groups have systematically different kinds of participants in them. In a repeated-measures design, when the effect of the independent variable is confounded with carryover from one level to the other, or with practice, fatigue, or boredom. An experimental group improves over time only because of natural development or spontaneous improvement. An experimental group changes over time because of an external factor that affects all or most members of the group. An experimental group whose average is extremely low (or high) at pretest will get better (or worse) over time because the random events that caused the extreme pretest scores do not recur the same way at posttest. An experimental group changes over time, but only because the most extreme cases have systematically dropped out and their scores are not included in the posttest. EXAMPLE From Chapter 10: If people who take notes on laptops answer harder questions than those who take notes longhand. From Chapter 10: In the autism study, some parents insisted they wanted their children to be in the intensive-treatment group rather than the control group. From Chapter 10: People rated the shared chocolate higher only because the first taste of chocolate is always more delicious than the second one. Disruptive boys settle down as they get used to the camp setting. Dorm residents use less air conditioning in November than September because the weather is cooler. A group's average is extremely depressed at pretest, in part because some members volunteered for therapy when they were feeling much more depressed than usual. Because the most rambunctious boy in the cabin leaves camp early, his unruly behavior affects the pretest mean but not the posttest mean. CHAPTER 11 More on Experiments: Confounding and Obscuring Variables QUESTIONS TO ASK Did the researchers turi potential third variable: to control variables-for example, keeping question diffic constant? Did the researchers usedom assignment or matchecoups to equalize groups? Did the researchers counterbalance the orders of presentation of the levels of the independent variable? Did the researchers use a comparison group of boys who had an equal amount of time to mature but who did not receive the treatment? Did the researchers include a comparison group that had an equal exposure to the external factor but did not receive the treatment? Did the researchers include a comparison group that was equally extreme at pretest but did not receive the therapy? Did the researchers compute the pretest and posttest scores with only the final sample included, removing any dropouts' data from the pretest group average?
NAME Testing Instrumentation. Observer bias Demand characteristic Placebo effect DEFINITION A type of order effect: An experimental group changes over time because repeated testing has affected the participants. Practice effects (fatigue effects) are one subtype. An experimental group changes over time, but only because the measurement instrument has changed. An experimental group's ratings differ from a comparison group's, but only because the researcher expects the groups' ratings to differ. Participants guess what the study's purpose is and change their behavior in the expected direction. Participants in an experimental group improve only because they believe in the efficacy of the therapy or drug they receive. EXAMPLE GRE verbal scores improve only because students take the same version of the test both times and therefore are more practiced at posttest. Coders get more lenient over time, so the same behavior is coded as less disruptive at posttest than at pretest. The researcher expects a low-sugar diet to decrease the campers' unruly behavior, so he notices only calm behavior and ignores wild behavior. Campers guess that the low-sugar diet is supposed to make them calmer, so they change their behavior accordingly. Women receiving cognitive therapy improve simply because they believe the therapy will work for them. CHECK YOUR UNDERSTANDING 1. How does a one-group, pretest/posttest design differ from a pretest/ posttest design, and which threats to internal validity are especially applicable to this design? 2. Using Table 11.1 as a guide, indicate which of the internal validity threats would be relevant even to a (two-group) posttest-only design. QUESTIONS TO ASK *622-822 dd aas 'z szed aast Did the researchers have a comparison group take the same two tests? Did they use a posttest-only design, or did they use alternative forms of the measure for the pretest and posttest? Did the researchers train coders to use the same standards when coding? Are pretest and posttest measures demonstrably equivalent? Were the observers of the dependent variable unaware of which condition participants were in? Were the participants kept unaware of the purpose of the study? Was it an independent- groups design, which makes participants less able to guess the study's purpose? Did a comparison group receive a placebo (inert) drug or a placebo therapy? Threats to Internal Validity: Did the Independent Variable Really Cause the Difference? 339