Essay PreviewMore ↓
2. The recommended design for this type of study is a non-equivalent control group post-test only design.
4. If a study is confounded, the researcher is not absolutely certain that changes in the dependent variable were caused by the manipulation of the independent variable, or some other uncontrolled variable. In a non-equivalent control group post-test only design, any differences observed between the two classes may be due to the non-equivalence of the groups and not to the injection of quizzes. No pre-test measures were given to establish equivalence.
Another confound that may impact the results of this study could be the testing effect. Repeated testing may lead to better or worse performance. Changes in performance on the test may be due to prior experience with the test and not to the independent variable. In addition, repeated testing fatigues the subjects, and their performance declines as a result (Jackson, 2012). Because the professor is interested in determining if the implementation of weekly quizzes would improve test scores, an experimenter and/or an instrumentation effect may also affect results.
In a single group post-test only design, possible confounds include the lack of a comparison group and the absence of an equivalent control group. Once again, a testing and an experimenter effect could also contribute to changes in test performance.
6. A single-case design is used when:
1. Only one person is measured.
2. The researcher does not want or need to generalize the results to a population.
3. The researcher believes it is unethical to withhold treatment to one group.
8. A multiple-baseline design differs from a reversal design by attempting to control for confounds through the introduction of treatment at differing time intervals to a few different people, to the same person in different situations, or to the same person across different behaviors. Reversal designs attempt to control for confounds by reversing the baseline and treatment conditions one or more times to assess the impact on behavior (Jackson, 2012).
2. Describe the advantages and disadvantages of quasi-experiments? What is the fundamental weakness of a quasi-experimental design? Why is it a weakness? Does its weakness always matter?
Quasi-experimental designs are experimental designs that do not provide for the full control of extraneous variables. Primarily, the absence of control in this design is due to the lack of random assignment to groups. Quasi-experimental research designs are used in the study of cause and effect by manipulating the independent variable.
How to Cite this Page
"Quasi-experimental Design." 123HelpMe.com. 04 Apr 2020
Need Writing Help?
Get feedback on grammar, clarity, concision and logic instantly.Check your paper »
- Experimental and Quasi-Experimental Design There are basically two main categories of measuring variables with a sample of participants or subjects: experimental and quasi-experimental. According to (Hopkins, 2008), research studies can be carried out using body tissues, cells, animals or humans. The researcher is looking for a relationship between the variables, and this can be accomplished using statistics, relative frequencies, and/or correlations (Hopkins, 2008). One can accomplish this by simply observing without influencing, manipulating, or controlling the environment or interaction.... [tags: Research Analysis ]
1945 words (5.6 pages)
- A quasi-experimental design was used to examine the research questions posed in this study. Data were collected in the first introductory accounting course at a public university in the southeast region of the United States. Eleven instructors participated in administering final exam questions and collecting results in 46 sections of the Principles of Accounting I over a four- semester period. Per departmental guidelines, all accounting faculty at this institution adopt the same textbook and cover the same course content, although perhaps to different extents and with varying approaches.... [tags: Question, Answer, University, Final examination]
736 words (2.1 pages)
- Critical Appraisal of a Quasi-Experimental Design Nursing research is an essential part of a nurse’s profession, it has remarkable influence on current and future evidence based practice (Tingen, Burnett, & Murchison, 2009), Therefore, it is vital that nurses develop the skill of knowing how to read and understand research reports. One way nurses can develop this skill is through the critique of a research article. Because evidence based practice is embedded in the foundation of nursing, it is vital that nurses develop the ability to recognize research that is trustworthy, current, and relevant to practice.... [tags: Scientific method, Validity, Research]
2118 words (6.1 pages)
- I. Jackson (2012), even-numbered chapter exercises, p 360. 2. The recommended design for this type of study is a non-equivalent control group post-test only design. 4. If a study is confounded, the researcher is not absolutely certain that changes in the dependent variable were caused by the manipulation of the independent variable, or some other uncontrolled variable. In a non-equivalent control group post-test only design, any differences observed between the two classes may be due to the non-equivalence of the groups and not to the injection of quizzes.... [tags: Research methods and statistics]
2375 words (6.8 pages)
- Method For their study they have used quasi-experimental cohort control group design. They said that they have chosen this design since it was impossible for them to create separate treatment and control group for their study. They did not do any random selection neither for teachers nor for students. However, they believed that using participant teachers as a control from pre-treatment to post-treatment added strength to their design. When the teachers finished participating in the program they were called treated.... [tags: Standard deviation, Statistics, Scientific method]
858 words (2.5 pages)
- Experimental designs Experimental designs are viewed as the most accurate, and most demanding of research designs, requiring strict attention to rules and procedures. Researchers use these research designs to manipulate and control testing procedures as a way to understand a cause and effect relationship. Commonly, independent variables are manipulated to judge or decide their effect on a dependent variable (Trochim & Donnelly, 2008). In order for an experiment to be considered a true experimental design, the design must fit specific criteria.... [tags: Research Methodology]
689 words (2 pages)
- Research plays a vital role in more deeply understanding library science. Thoughtful consideration of how evidence-based research is conducted is essential to its effective use. Research helps professionals identify and explore areas of concern or interest in addition to providing possible solutions for known problems. The Delphi and quasi-experimental studies provide examples of research performed in library science. The Delphi Study The Delphi study was developed by The RAND Corporation in the 1950s for the Air Force and was primarily used to forecast future events based on expert opinions (Wildemuth, 2009).... [tags: Research Analysis]
1721 words (4.9 pages)
- Snowden, Masland, Wallace, and Fawley (2009) examined if ethnic minority youth receiving supplemental managed care decrease the propensity for their need to obtain emergency or crisis care and if minority’s decrease were more than that of Whites. According to the article, Associating Supplemental Case Management Activities with Ethnic Minority Children’s Reduced Use of Psychiatric Emergency Services minority children and adolescents inflicted with poverty perform poorly in school and more often immersed in criminal justice and child welfare systems than their White counterparts.... [tags: Criminal Justice, Child Welfare System]
1244 words (3.6 pages)
- Evaluation Plan Background The program evaluation will be assessing the outcomes resulting from offenders that were placed into the HOPE program versus those that were not. As mentioned in previous assignments, the HOPE program is a rigorous probation sentence which entails submitting to random drug testing, mandatory appointments with law enforcement personnel, and the completion of counseling or drug treatment sessions while not repeating previous violations. Violations of the probation program will result in a swift and certain punishment of a short-term jail sentence.... [tags: Violence, Offenders]
770 words (2.2 pages)
- The purpose of this section is to compare and contrast case study and quasi-experiment research designs. I will outline how they differ in their general purpose and goals, which in turn dictates their differences in approaching sampling concerns, the type of data collection methods they employ, and the data analysis techniques they employ. For example purposes, I will be utilizing Dorothy Winsor’s Engineering Writing/Writing Engineering to exemplify case studies and Barry Kroll’s Explaining How to Play a Game to exemplify quasi-experiments.... [tags: Scientific method, Qualitative research]
2056 words (5.9 pages)
Another advantage of the quasi-experimental design is the ability to make inferences about the cause and effect relationship among the variables, by comparing the groups. Quasi-experimental designs allow for control of experimental stimuli when randomization is impractical or unethical. Finally, quasi-experimental designs allows the researcher to choose participants who may benefit the most from the intervention.
The use of quasi-experimental designs increases the probability of producing non-equivalent groups. Non-equivalent groups pose a threat to internal validity. Whenever random sampling methods are not used in constructing experimental and control groups, the potential for low internal validity increases.
The lack of random assignment is the major weakness of the quasi-experimental study design. Due to the lack of randomization, there is difficulty in controlling for other confounding variables. Through randomization, the highest level of credibility in experimental design is attained; however, some researchers may choose not to randomize subjects due to difficulty to randomize, small sample sizes, or ethical considerations. When random sampling is not used, greater diligence must be exercised before concluding the independent variable caused any of the observed changes in the dependent variable. The researcher must utilize other strategies for equating groups and ruling out alternative explanations.
3. If you randomly assign participants to groups, can you assume the groups are equivalent at the beginning of the study? At the end? Why or why not? If you cannot assume equivalence at either end, what can you do? Please explain.
If a researcher randomly assigned participants to groups, the random assignment does not guarantee the groups are equivalent, unless the sample size is large. The randomly assigned groups would be considered as equivalent as possible at the beginning of the study. Groups are never assumed to be equivalent at the end of a study because of uncontrolled extraneous confounding variables. Because equivalence cannot be assumed at the beginning or at the end of the study, the design can be improved upon by matching the groups, or adding statistical controls as determinates of outcome and/or selection criteria.
4. Explain and give examples of how the particular outcomes of a study can suggest if a particular threat is likely to have been present.
Example: In a study with two non-equivalent groups; between the pre-test and the post-test, but before the independent variable was introduced, several study participants moved away from the area. The study participants were replaced. However, the post-test scores were extremely lower than the pre-test scores. The loss of study participants is a major threat to internal validity. Simply replacing the loss subjects does not guarantee the replacement subjects are equivalent to the loss subjects. An attempt to choose participants with similar characteristics, will not conclusively demonstrate equivalency. The best solution in preventing the mortality threat is to minimize the loss of subjects in the study.
The post-test scores were extremely lower than the pre-test scores which leads the researcher to conclude the possible threat of regression to the mean. Regression to the mean is a major threat to internal validity, in which extreme scores, upon retesting, tend to be less extreme (Jackson, 2012). Regression to the mean can likely be controlled in this example by randomly assigning equivalent comparison groups and/or matching the participants to groups at the onset of the study.
The maturation threat is also a concern in the above example, the time interval must be the same for both comparison groups. Once again, the participants should either be randomly assigned or matched to groups for control of the maturation threat. When groups mature at different rates, differences may sometimes be attributed to gender or age differences in participants. Lastly, the outside event of participants leaving the study, could also contribute to a history effect that affects the dependent variable.
5. Describe each of the following types of designs, explain its logic, and why the design does or does not address the selection threats discussed in Chapter 7 of Trochim and Donnelly (2006):
a. Non-equivalent control group pretest only
The non-equivalent control group pretest only does not represent a true experimental design because the participants are not randomly assigned. The pre-test allows the researcher to assess if the groups are equivalent on the dependent measure at the onset and before the treatment is administered. This design addresses selection threats because the pre-test is used as the tool in determining group differences on the variable. The assumption is, the smaller the difference on the pre-test, the less likely a selection bias is occurring during the pre-test. When pretest differences do exist, the selection bias will combine with other threats additively or interactively (Quasi-experimental control: University of North Carolina, n.d.).
b. Non-equivalent control group pretest/posttest
The non-equivalent control group pretest/posttest design is likened to the previous design because the subjects are not randomly assigned to the two conditions. This design allows the researcher to assess any changes that may have occurred in each group after treatment by comparing the pretest measures for each group with their posttest measures (Jackson, 2012). The use of a pretest, control group, and a posttest make it easier to examine selection threats of history, maturation, testing, and possibly instrumentation, mortality and selection-regression.
A cross-sectional design is a type of developmental design in which participants of different ages are studied simultaneously. The researcher wants to be able to conclude that any difference observed in the dependent variable is due to age (Jackson, 2012). This design is based on capturing a point in time and does not specifically address selection-history, selection-maturation, or selection-mortality threats.
Regression-Discontinuity (RD) is a design which uses a pretest-posttest, program-comparison group strategy. Research participants are assigned to groups based on cutoff criterion. RD designs are comparable in internal validity to conclusions drawn from randomized experiments (Trochim & Donnelly, 2008). Therefore, it is not necessary to address selection threats with this design.
6. Why are quasi-experimental designs used more often than experimental designs?
Quasi-experimental designs are used more often than experimental designs because it would be difficult, costly, and time-consuming for researchers to randomly assign subjects to treatment groups. The grand majority of the time, research participants are already in their pre-assigned groups and these groups are often difficult to split and mix. Constructed control groups might be the only feasible way to equate groups because random assignment may not be possible. Quasi-experimental designs can be improved by using matching and statistical controls in equating the groups.
7. One conclusion you might reach (hint) after completing the readings for this assignment is that there are no bad designs, only bad design choices (and implementations). State a research question for which a single-group post-test only design can yield relatively unambiguous findings.
Research Question: Watching TV less than two hours per day increases energy levels in women.
If the researcher attempted to answer this research question using a single-group post-test only design, the conclusions would be flawed. The biggest problem with this design is, there is little evidence of what is observed on the post-test being due to watching less television. There is no pre-test baseline measure, no control group, no equivalent groups, and nothing to compare the previous energy levels of women in the study. By far, the single group post-test only design is the weakest of all experimental designs.
1. What research question(s) does the study address?
R1 TV advertising aimed at children is highly effective.
R2 The influence of TV commercials targeted at children is considerable.
R3 TV advertising aimed at children leads to children wanting more of the advertised item.
2. What is Goldberg�s rationale for the study? Was the study designed to contribute to theory? Do the results of the study contribute to theory? For both questions: If so, how? If not, why not?
Goldberg is attempting to determine if TV advertising aimed at children is a critical determinant of children’s preferences and purchase requests. While the study was initially designed to contribute to theory, the results are not uniform in reaching the conclusion. The unintentional results stress a large number of simultaneous and interacting influences that have minimized TV’s influence on children (Goldberg, 1990). The results of the theory contribute to theory by recognizing a broader network of confounding variables, operating in the environment, having an effect on the outcome. The conclusions also highlight the shortcoming of the correlational method as the basis for establishing causal relationships in this study. The quasi-experiment allows for the determination of causal relationships, much as in the laboratory experiment, but not so in a broader real-world context.
3. What constructs does the study address? How are they operationalized?
The design of this quasi-experiment compares similar groups of English-speaking and French-speaking children and their American Children’s Commercial TV (ACTV) exposure. The study design provided for a comparison of those exposed to higher and lower levels of ACTV and, by extension, the commercials inserted therein (Goldberg, 1990). The level of ACTV exposure was also examined within each of the two groups and related to the dependent measures. Due to considerable evidence linking income to television viewing, any observed differences between English and French-speaking children were noted by income/occupation levels.
4. What are the independent (IV) and dependent variables (DV) in the study?
IV - Children’s cultural affiliation
IV - Number of ACTV programs viewed by each child
DV - Awareness of toys
DV - Children’s cereal purchases currently in the home
DV - Occupation of Father/Mother
5. Name the type of design the researchers used.
The design used in the article most closely resembles a nonequivalent control group pretest/posttest design.
6. What internal and external validity threats did the researchers address in their design? How did they address them? Are there threats they did not address? If so how does the failure to address the threats affect the researchers� interpretations of their findings? Are Goldberg�s conclusions convincing? Why or why not?
The researchers adequately addressed the selection biases by attempting to maintain homogenous groups of English and French speaking children for the study. The children sampled were of similar age and parental income/occupation. The study can likely be generalized to include a larger segment of the population. The researchers failed to address maturation, history, or mortality threats in their analysis. However, social interaction threats were minimized, due to the presence of a language barrier between the two groups. Based on the results of the study, the internal and external threats not specifically addressed in this design, have minimal effect on the conclusions. Goldberg’s results make a truly convincing argument for enacting legislation requiring the reduction of children’s television advertising that promotes sugared cereals and toy awareness.
Cozby, P. C., & Bates, S. C. (2012). Methods in behavioral research (11th ed.). New York, NY: McGraw-Hill.
Creswell, J. W. (2009). Research Design: Qualitiative, quantitative, and mixed methods approaches (3rd ed.). Thousand Oaks, CA: Sage Publications, Inc.
Goldberg, M. E. (1990, November). A quasi-experiment assessing the effectiveness of TV advertising directed to children. Journal of Marketing Research, 27, 445-454. Retrieved from http://search.proquest.com.proxy1.ncu.edu/docview/235231913?accountid=28180
Harris, A. D., McGregor, J. C., Perencevich, E. N., Furuno, J. P., Zhu, J., Peterson, D. E., & Finkelstein, J. (2006, Jan - Feb). The use and interpretation of quasi-experimental studies in medical informatics. Journal of the American Medical Informatics Association, 13(1), 16-23. Doi: 10.1197/jamia.M1749
Jackson, S. L. (2012). Research methods and statistics: A critical thinking approach (4th ed.). Belmont, CA: Wadsworth.
Quasi-experimental control: University of North Carolina. (n.d.). Retrieved from: http://www.psych.uncc.edu/pagoolka/Ch5QuasiControl.pdf
Trochim, W. M., & Donnelly, J. P. (2008). The research methods knowledge base (3rd ed.). Mason, OH: Cengage Learning.
Wiley, R. H. (2009). Trade-offs in the design of experiments. Journal of Comparative Psychology, 123(4), 447-449. Doi: 10.1037/a0016094