What is the Ex-Post Facto Study?
The Ex-post facto study or post-event investigation is a category of investigation design in which the investigation begins after the event has occurred without the interference of the investigator. Most social research, in contexts where it is not possible or acceptable to manipulate the characteristics of human participants, is based on ex post facto research designs. It is also often applied as a substitute for true experimental research to test hypotheses about cause-effect relationships or in situations where it is not practical or ethically acceptable to apply the full protocol of a true experimental design. Despite studying events that have already occurred, ex post facto research shares part of its basic research logic with the experimental research design.
What is Research Design?
According to Porte (2010: 64), research design is a useful exercise for the critical reader since it will help us to clarify the suitability of the procedures carried out so far and will put us in a better position to judge the suitability of any post data analysis chosen. It means that research design is the processes that include planning and doing the research. Based on Arikunto (2010: 172), the research design is the topic from which the data are collected. It means that research design is a necessary process to collect and achieve scientific truth for an investigation.
When conducting this research, you need to plan some steps that will be taken. The researcher has to follow the research design to achieve the research successfully. The design begins with a general statement of a problem or research topic. At first, the researcher needs to think of a topic in which he is interested and wants to know more about it.
Advantages of Ex-Post Facto Research
Ex post facto research is of great relevance to social and behavioral scientists who are generally restricted from being able to manipulate variables. This research method has an advantage over experimental research because it can be useful to analyze a cause on the basis of an effect that is being studied. Ex post facto research can also be cheaper and less time consuming, and the opinion of the researcher is relevant to the research.
Disadvantages of Ex-Post Facto Research
In ex post facto research designs, the researcher cannot manipulate variables and the researcher cannot randomly assign research subjects to different groups (Harris et al., 2006). The ex post facto research design does not give the researcher the basis to define a clear relationship between the independent and dependent variables being studied (Bevins, 1999). By their very nature, ex post, de facto experiments can provide support for a number of different, and perhaps contradictory, hypotheses; they are so completely flexible that it is largely a matter of hypothesizing according to one's personal preferences.
The point is that the evidence simply illustrates a hypothesis; it does not test the hypothesis, since hypotheses cannot be tested with the same data from which they were derived. The noted relationship may actually exist but it is not necessarily the only relationship, or perhaps even the crucial relationship. "Experiments" are probably best conceived as surveys, useful in deriving hypotheses to be tested through more conventional experimental approaches.
Preliminary Sample of an Ex-Post Facto Research Design
Ex post facto research designs are often systematic. This means that there is a definite order as to how a study will be carried out that is carried out using the ex post facto research design. These steps will be applied to design an ex post facto investigation on Bola Fashion Enterprise, a fashion company, which has dropped its sales of men's fashion items.
Elements of the method
Isaac and Michael (1971) established the sequence of steps involved in ex post facto research, and it should include:
- Define the problem.
- Examine the literature.
- State the hypotheses.
- List the assumptions on which the assumptions are based and the procedures will be based.
- Design the approach:
- Select the appropriate topics and source materials.
- Select or construct techniques to collect the data.
- Establish categories to classify data that are unambiguous, appropriate for the purpose of the study, and capable of revealing significant similarities or relationships.
- Validate data collection techniques.
- Describe, analyze and interpret the findings in clear and precise terms.
Sukhia, Metrotra and Metrotra (1966) listed three important aspects of the causal-comparative method with respect to their data processing:
- Gathering data on factors invariably present in cases where the given result occurs and discarding those elements that are not universally present;
- Collection of data on factors invariably present in cases where the given effect does not occur; and
- Comparing the two sets of data, or indeed, subtracting one from the other to arrive at the causes responsible for the occurrence or not of the effect (p. 45].
Example of an Ex-Post Facto Investigation
Determining the problem.
Bola Fashion Enterprises has experienced a drop in sales of men's fashion items by more than 60% after management assigned sales of these items only to male sales personnel.
Relevant for sales strategy and marketing management in the fashion industry.
When proposing the possible solutions and alternatives, it is necessary to propose a hypothesis. In this case, an alternative will be woven around the possibility that the drop in sales was caused by the loss of female sales personnel from the team that promotes sales of men's fashion items. The case assumptions will be listed and a hypothesis will be formulated.
Once the hypothesis is defined, a sample will be selected that matches the study criteria.
Establishment of validity.
When designing research, it is essential to understand the importance of the research and to know to what extent the findings can be used to make inferences. In this case, it will be necessary to clearly define what other conditions influence sales regardless of gender.
Interpretation and conclusion.
Here, the researcher will analyze and evaluate the collected results in order to gain a good understanding of the event that led to the effect being studied.
Bevins, T. (1999). Research Designs. Retrieved May 29, 2019, from Fgcu.edu website: http://ruby.fgcu.edu/courses/sbevins/50065/qtdesign.html
Harris, A. D., McGregor, J. C., Perencevich, E. N., Furuno, J. P., Zhu, J., Peterson, D. E., & Finkelstein, J. (2006). The Use and Interpretation of Quasi-Experimental Studies in Medical Informatics. Journal of the American Medical Informatics Association, 13(1), 16–23. https://doi.org/10.1197/jamia.m1749
Isaac, S. and Michael, W.B. Handbook in research and evaluation. San Diego, California: Robert R. Knapp, 1971.
Sukhia, M.A., Mehrotra. P.V. and Mehrotra, R.N. Elements of educational research. New York: Allied Publishers, 1966.
You might be also interested in: Inductive Generalization