Responding to a classmate; Autumn G Johnson Kline
: When conducting research and making claims based on findings, looking at potential threats in quantitative (and all) research is crucial. Overlooking these potential threats can lead to making discoveries that are not sound and just happen to work for that specific study. Accounting for all potential biases, issues, etc must be done prior to it being considered amenable to scientific study. It would be unethical to post findings from a study that was not fully researched or considered amenable to scientific study because quantitative research should be well-researched and trustworthy. “A quantitative approach in a study tends to estimate occurrences from a larger number of subjects using different survey methods. What it means for a research topic to be amenable to scientific study using a quantitative approach is that a method using a larger number of subjects and different survey methods can be applied to address the problem at hand (Burkholder et al., 2016, p. 6918). Using large populations and a variety of methods helps solidify the findings and prove that it was not a one-off that happened to work for a particular study making it more ethically sound.
For the purpose of this discussion, I will examine a potential threat to the internal and external validity. To begin, I chose to look at the internal validity issue of maturation. “Maturation. Natural changes that participants experience (e.g., growing older, getting tired) during the course of the intervention could account for the outcomes. Thus, unable to conclude with certainty that the “intervention” caused the effect; could be due to the natural change/maturation of the participants (Shadish, Cook & Campbell, 2002).” This to put simply, is the passage of time in relation to the influence of the dependent variable, which cannot certainly account for the outcome of the study. To combat this internal validity, one possible solution can be addressed by creating separate experimental and control groups, and selection interaction, which can be remedied by a random assignment of subjects to a condition. Moving on to look at an external threat in validity, one possibility is a sampling bias. To put simply, this would be when the participants of a study differ substantially from the population. If you are testing a group of people and one group in the experiment is substantially older/younger than the rest of the population tested, it would not be right to generalize these findings. One potential way to mitigate this is to carefully select your population in the study. To do this defining target populations and using simple random sampling, systematic sampling, cluster sampling, and stratified sampling to choose respondents will help eliminate biases.
References:
Burkholder, G., Cox, K., & Crawford, L. (2016).The scholar-practitioner’s guide to research design
Shadish, W. R., Cook, T. D., & Campbell, D. T. (2002). Experimental and quasi-experimental designs for generalized causal inference. Boston, MA: Houghton-Mifflin.
Answer Preview
APA Format,333 words