Chapter 10: Experimental and Quasiexperimental Designs

A study was conducted to determine whether a videotape would be more effective than a pamphlet in instructing college-age women to perform breast self-examination on a regular basis. Which of the following conditions could be considered an antecedent variable? a. Four participants in the pamphlet-based instruction group had mothers who had been diagnosed with breast cancer, and the other group had no participants with mothers diagnosed with breast cancer. b. The group that received the videotape training comprised members of one sorority, and the group that received the pamphlet-based instruction comprised members of a different sorority. c. During the study, most participants received flu shots through the college's student health service. d. The pamphlet group had 38 members, and the videotape group had 33 members.

ANS: A Feedback A An antecedent variable (e.g., mothers with breast cancer) is something that occurs before the study but may affect the outcome and confuse results. B The sorority effect would occur during data collection in the study, not before the study. C Flu immunization would not have occurred before the study, but during the study. D Sample size would occur during the study, not before it. DIF: Cognitive Level: Analysis REF: Page 220

What aspect should be the primary consideration in critiquing the research report of an experimental study and determining the validity of the conclusions presented? a. How well the researcher controlled for extraneous variables b. The direction of the relationship between dependent and independent variables c. The credentials and previous experience of the researcher d. The number of persons involved in the data collection process

ANS: A Feedback A Control is the ultimate criterion in experimental research because it is related to constancy in the manipulation of variables. B The direction of the treatment relationship is not critical to control. C Researcher credentials and experience, while important, do not ensure experimental control. D The number of data collectors is not a primary criterion for determining the validity of conclusions. DIF: Cognitive Level: Analysis REF: Page 217

Which of the following is a purpose of evaluation research in nursing? a. Documenting the cost-effectiveness of new nursing interventions b. Discovering the health beliefs of a specific ethnic group c. Defining the cause-and-effect relationship in poor surgical outcomes d. Describing various models of health care delivery

ANS: A Feedback A Evaluation research is the use of research methods to evaluate a program, treatment, or policy (e.g., a nursing intervention). B Health beliefs of a specific group would be learned through an ethnographic study. C Cause-and-effect relationships can be analyzed with experimental or quasiexperimental approaches. D Describing models of health care delivery most likely occurs in descriptive research. DIF: Cognitive Level: Comprehension REF: Page 229

Which of the following types of quasiexperimental design is implemented when subjects are not randomly assigned to groups? a. Nonequivalent control group design b. After-only control group design c. Solomon four-group design d. Time series design

ANS: A Feedback A Nonequivalent control group design is a quasiexperimental design in which subjects are not randomly assigned to groups. B After-only control group design does not preclude the use of random assignment. C Random assignment does occur in the Solomon four-group design. D A time series design involves multiple episodes of data collection; it does not mean that random assignment is not used. DIF: Cognitive Level: Knowledge REF: Pages 225-226

What is the term used to describe the experimental treatment initiated by the researcher? a. Independent variable b. Dependent variable c. Extraneous variable d. Outcome variable

ANS: A Feedback A The other term for experimental treatment is independent variable. B The dependent variable is also called the outcome. C The term extraneous variable refers to a variable that can interfere with inferring causality. D Outcome variable is another term for dependent variable. DIF: Cognitive Level: Knowledge REF: Page 217

How differently is the independent variable handled in studies with an experimental design or a quasiexperimental design? a. An independent variable is not identified or needed in a quasiexperimental design. b. Both designs identify an independent variable, and both manipulate the independent variable. c. Experimental designs demonstrate that the independent variable is related to the outcome, but quasiexperimental studies allow for independent variables that stand alone. d. Although both designs identify an independent variable, experimental designs identify it before the research is initiated, and quasiexperimental designs identify it after the data have been analyzed.

ANS: B Feedback A A quasiexperimental design incorporates both dependent and independent variables. B The major difference between experimental and quasiexperimental designs is the randomization of groups; independent variables are manipulated in both designs. C Both experimental and quasiexperimental designs examine the relationship of dependent and independent variables. D In both designs (experimental and quasiexperimental), variables are identified before the study begins. DIF: Cognitive Level: Comprehension REF: Page 223

Which of the following criteria must be met to infer causality? a. The relationship between cause and effect must be measurable and reciprocal. b. The relationship must not be explainable by any other variable. c. The independent variable must change in response to manipulation of the dependent variable. d. The outcome must be logical, expected, and predictable.

ANS: B Feedback A Cause and effect are not necessarily reciprocal. B Control of other variables that may explain the effect of the independent variable on the dependent variable is critical to causality. C In a cause-and-effect relationship, the independent variable changes the dependent variable. D Cause-and-effect-relationships are not necessarily logical or expected. DIF: Cognitive Level: Comprehension REF: Page 217

By what specific criterion should you judge the results or findings of experimental research? a. The size of the experimental group compared with the size of the control group b. The validity that the experimental treatment caused the desired effect on the outcome c. The degree to which the research questions were congruent with the hypotheses and the purpose of the study d. The degree to which the researcher was able to apply the findings to clinical or practice settings

ANS: B Feedback A Findings of an experimental study are not ultimately judged by comparing group sizes. B The validity of the results of an experimental study depends on how well the researcher controlled alternative explanatory variables. C Though important, congruence of research questions, hypotheses, and so on is not the ultimate criterion for evaluating an experimental effect. D Clinical applicability does not guarantee validity of experimental results. DIF: Cognitive Level: Comprehension REF: Page 217 | Page 227

What is the meaning of "control" in a study with an experimental design? a. The care taken to ensure maintenance of participant confidentiality b. The introduction of one or more constants into the experimental situation c. The ability of the researcher to prevent data collection from extending beyond the original time specified for the study d. The faithfulness of the researcher in the application of all the assumptions of the experimental process to the study

ANS: B Feedback A Participant confidentiality is protected by the researcher's coding of subjects. B Control is the introduction of one or more constants into the experimental situation. C Control in an experimental design is not related to specific periods of a study. D Control is associated with holding factors constant, rather than with applying experimental assumptions. DIF: Cognitive Level: Comprehension REF: Page 219

For which of the following studies would an after-only experimental research design be most appropriate? a. The effect of cause of spousal death on widow self-esteem. b. The effect of preoperative teaching on vascular complications after surgery. c. The effect of a mentorship program on improvement of student performance in a BSN program. d. The effectiveness of using the videotape to teach adolescent males about the warning signs of testicular cancer.

ANS: B Feedback A The effect of cause of spousal death cannot be controlled and studied. B After-only design is particularly useful when outcomes cannot be measured beforehand (e.g., postoperative complications). C Student performance can be measured before and after the intervention (mentorship program). D Knowledge about testicular cancer can be measured before and after the intervention (videotape teaching). DIF: Cognitive Level: Analysis REF: Pages 222-223

Using the abstract information provided below, identify which group would be considered the "control group" for this experimental study. "To determine the efficacy of a cognitive-behavioral intervention for treating insomnia in breast cancer survivors, randomized controlled trials were conducted with seventy-two women who through sleep diaries were identified as experiencing insomnia. Participants were randomly assigned to a multi-component intervention including stimulus control instructions, sleep restriction, and sleep or a single-component group (sleep education)." a. The group receiving the multi-component. b. The group receiving the single component. c. The group experiencing adverse effects. d. The group refusing to participate.

ANS: B Feedback A The group receiving the multi-component is the experimental or treatment group. B In true experimental research, the control group is the group that receives the usual treatment. The single component is the usual treatment. C Adverse effects do not occur only in the control group but are more likely to occur in the treatment group. D Refusal to participate does not refer to control group status. DIF: Cognitive Level: Comprehension REF: Pages 217-218

In the study by Siminoff, Burant and Ibrahim entitled "Racial Disparities in Preferences and Perceptions Regarding Organ Donation," sampling was done using a random digit telephone technique. What threats to internal validity does this prevent? a. Selection effects b. Selection bias c. Social desirability bias d. Testing effects

ANS: B Feedback A The researchers used randomly selected individuals in this study, which reduced selection bias. B The researchers used randomly selected individuals in this study, which reduced selection bias—which could threaten internal validity. C Probability sampling helped reduce selection bias, not social desirability bias. D Probability sampling would not reduce the effects of testing, but would help reduce selection bias. DIF: Cognitive Level: Evaluation REF: Page 220

A study compared weight loss in obese subjects between those who participated in a support group and those who chose not to. Which of the following factors or conditions in the study would be considered an intervening variable? a. Data collection for both groups occurred over the Thanksgiving holiday. b. The group that did not participate in a support group had a greater percentage of male subjects. c. Three subjects were diagnosed with hypertension 1 month after the study began. d. Two subjects dropped out of the study 1 month after the study began.

ANS: C Feedback A If a factor affects both groups, then it is likely not an intervening variable. B Group size and gender would be part of the study. C An intervening variable (e.g., hypertension diagnosis) affects the subject during the course of the study; it is therefore not part of the study and could affect the dependent variable. D Subject attrition would not be considered an intervening variable. DIF: Cognitive Level: Analysis REF: Page 220

Which of the following statements about random assignment or randomization is true? a. The randomization process decreases the influence of researcher bias but can increase the effect of systematic bias in a study. b. The randomization process decreases the influence of systematic bias but can increase the effect of researcher bias in a study. c. With randomization, each subject has an equal and known probability of being assigned to any group in a study. d. Randomization eliminates the need for informed consent.

ANS: C Feedback A Randomization does not decrease researcher bias or necessarily increase systematic bias. B Randomization does not necessarily influence systematic bias or researcher bias. C Randomization, or random assignment to a group, implies that each subject has an equal and known probability of being assigned to a group. D Informed consent is always required in any type of research on human subjects. DIF: Cognitive Level: Comprehension REF: Page 218

Which of the following situations meets a criterion for inferring causality between performance of exercise and adaptation behaviour of women receiving chemotherapy for breast cancer? a. Adaptation behaviour began before the exercise program was initiated. b. Adaptive behaviour occurred in the control group over time. c. The level of adaptation behaviours increased proportionately with increase in the intensity of the exercise. d. No differences in adaptation behaviours were observed between subjects in the experimental group and subjects in the control group.

ANS: C Feedback A The change in the dependent variable before treatment begins would interfere with clear causality. B If a change in adaptation behaviour occurred without treatment, that would interfere with causality. C A clear proportional change in the dependent variable that occurs because of clear proportional change in the independent variable supports causality. D The lack of difference between groups suggests that the independent variable (treatment) was not causally related. DIF: Cognitive Level: Analysis REF: Pages 221-222

In a study about help to quit smoking, one group of participants received a single supportive phone call 10 days after attending a program on strategies to resist the urge to smoke. A second group received a weekly supportive phone call for 6 weeks after attending the same program, and a third group received no supportive phone calls after attending the program. What property of experimental research did the researcher employ in this study? a. Quasi-experimental research—no control group b. Random assignment to research groups c. Manipulation of the intervention dose d. Controlling for extraneous variables

ANS: C Feedback A There was a control group—the group that received no phone calls. B The description of the study does not indicate whether random assignment was done. C The description of the study indicates manipulation of the independent variable with various patterns of interventions, that is, phone calls. D Control of extraneous variables is not evident in this description. DIF: Cognitive Level: Analysis REF: Page 219

What type of threat to validity is minimized by the use of the Solomon four-group design? a. Mortality b. Selection bias c. Testing d. Antecedent variable

ANS: C Feedback A Use of four groups does not control subject mortality or attrition. B Selection bias would be controlled by correct sampling processes. C Testing threats to internal validity are ruled out by Solomon four-group design. D Antecedent variables are not controlled by the use of the four-group design. DIF: Cognitive Level: Comprehension REF: Page 222

Why would a nurse researcher opt for a quasiexperimental study design instead of an experimental study design? a. The study is planned to be conducted in a laboratory setting. b. An experimental treatment is not part of the study. c. The researcher has not conducted research before. d. Full experimentational control is not possible.

ANS: D Feedback A A laboratory setting, in itself, would not preclude the use of an experimental design. B If no experimental treatment is used, then the study does not have a quasiexperimental design. C Researcher inexperience should not influence the choice of design. D When full experimental control is not possible, it is appropriate for the researcher to select a quasiexperimental design. DIF: Cognitive Level: Comprehension REF: Page 224

Why is randomization important in a study with an experimental design? a. It reduces the risk of the subject being harmed by participation in the study. b. It ensures that the experimental group and the control group have the same number of participants. c. It allows the study to proceed without the researcher knowing the identity of the treatment group. d. It increases the likelihood that differences in the outcomes of the groups are not related to chance alone.

ANS: D Feedback A Randomization does not protect a research subject from harm. B Sampling techniques such as quota sampling, not randomization, ensure equal group size. C Randomization does not blind the researcher to treatment group versus control group. D Randomization helps attribute any group differences in study outcomes to the treatment or experimental condition and not to chance alone. DIF: Cognitive Level: Comprehension REF: Page 219

Which of the following factors or characteristics is present only in an experimental design (and not in a quasiexperimental design)? a. Research question or hypothesis b. Experimental treatment c. Informed consent d. Randomization

ANS: D Feedback A Research questions or hypotheses are present in all levels of quantitative research. B Experimental treatment is also present in a quasiexperimental design. C Informed consent is required for all types of research. D Randomization or random assignment to a group is not present in a quasiexperimental study. DIF: Cognitive Level: Comprehension REF: Pages 218-219

What advantage do quasiexperimental studies have over experimental studies? a. A smaller sample size is sufficient to obtain significant results in quasiexperimental studies. b. Quasiexperimental studies are stronger in establishing cause-and-effect relationships. c. Descriptive statistics can be used to analyze the data in quasiexperimental studies. d. Quasiexperimental studies are more adaptable to real world settings.

ANS: D Feedback A Sample size is determined by power analysis, rather than design, in quasiexperimental studies. B Quasiexperimental designs are not as strong as experimental designs. C Descriptive statistics can be used for both quasiexperimental and experimental studies. D Quasiexperimental studies are more adaptable to real-world settings, where randomization is difficult or impossible. DIF: Cognitive Level: Comprehension REF: Page 228