Benefits and Limitations of Self-Reported Data
Data like that collected by the Student Health Center has its, first and foremost being that it saves time for the researcher since the data has already been gathered. Thus, time and money are not spent on a long data collection process. It also means it is possible for analysis of larger samples that likely would not be possible for individual researchers (Pederson et al., 2020).
However, secondary data also has its limitations. For one thing, it might fit well with the ones research questions. For another, researchers have no control over its quality, accuracy, or completeness. The lack of clarity on how the original data was collected can introduce bias, and limit its reliability (Baldwin et al., 2022).
In the given scenario, the main limitation of the secondary data is its design. The original was meant to look at binge drinking rates, not the association between race/ethnicity and binge drinking. Therefore, the survey might not have collected detailed or nuanced information about race, ethnicity, or other confounding variables necessary for a robust analysis. The convenience sampling method (students visiting the health center) could also introduce selection bias, as those seeking care may differ from the general student population in significant ways. Another thing is that the data was collected from a relatively small sample of 300 students, which will reduce its generalizability.
To address these threats to validity, one could apply weighting techniques to account for underrepresented groups in the sample or conduct sensitivity analyses to assess the impact of potential biases. If possible, one should try to supplement the secondary data with additional primary data collection focused on race and ethnicity (Baldwin et al., 2022). A researcher should also be careful to consider the limitations in their conclusions, acknowledging that the findings may not fully represent the college undergraduate population.
References
Baldwin, J. R., Pingault, J. B., Schoeler, T., Sallis, H. M., & Munaf, M. R. (2022). Protecting
against researcher bias in secondary data analysis: challenges and potential solutions.European Journal of Epidemiology,37(1), 1-10.
Pederson, L. L., Vingilis, E., Wickens, C. M., Koval, J., & Mann, R. E. (2020). Use of secondary
data analyses in research: Pros and Cons.Journal of Addiction Medicine and Therapeutic Science,6(1), 058-060.
