JS Oct 1 10:13pm

Shen et al. (2023) used a quantitative, longitudinal survey design to look at differences in COVID-19-related trauma (CRT) and mental health symptoms across groups defined by sexual orientation and race/ethnicity. They collected data in two waves during the early months of the pandemic (March–April 2020 and May–June 2020). This type of design allowed them to check both differences at one point in time and changes over time. As Frankfort-Nachmias, Leon-Guerrero, and Davis (2020) note, quantitative designs like this are helpful when researchers want to compare groups and look at trends using numerical scores (such as mental health ratings).

Use of t-tests

The authors used independent-samples t-tests to compare averages between groups—for example, comparing sexual minorities to heterosexuals, or comparing racial/ethnic minority students to White students. In some cases, they used Welch’s t-test, which adjusts for unequal variances between groups. According to Wagner (2020), t-tests are the right choice when comparing two independent groups on a continuous outcome, which matches the study’s purpose of looking at whether mental health outcomes differed across identity categories.

Appropriateness of the Method

Using a t-test made sense for the cross-sectional part of the study, because it directly answers the question of whether two groups are different on average. But t-tests can only compare two groups at a time. For example, when looking at race/ethnicity, the test can compare White vs. minority students, but it can’t capture differences among several racial/ethnic groups at once. In those cases, an ANOVA might have been more useful. The authors also went beyond t-tests by using residualized change score regressions to track changes over time, which gave them a more detailed look at predictors of mental health outcomes. This combination of methods made the study stronger.

Data Display and Interpretation

The results were shown in tables that listed means, standard deviations, and p-values. This clear layout makes it easier for readers to interpret the findings on their own, which increases the transparency of the study. However, one drawback is that the authors did not report effect sizes (like Cohen’s d). As Frankfort-Nachmias et al. (2020) point out, effect sizes are important for understanding the practical meaning of the differences, not just whether they are statistically significant. Without effect sizes, it’s harder to know how big or meaningful the group differences actually were.

Conclusion

Overall, Shen et al. (2023) designed a solid quantitative study that made good use of t-tests to examine group differences in mental health during the COVID-19 pandemic. Their additional use of regression analysis added depth by showing changes over time. The main limitation was not reporting effect sizes, which leaves some questions about how large or meaningful the differences were. Even with that gap, the article makes a valuable contribution to research on disparities in trauma and mental health. Future studies could strengthen this work by including both significance levels and effect sizes to paint a clearer picture of the findings.

Respond to one of your colleagues’ posts and:

Make recommendations for the design choice.

Explain whether you think that this is the appropriate t test to use for the research question. Why or why not?

As a lay reader, were you able to understand the results and their implications? Why or why not?