MCQs

Overall score:
0 out of 0 attempts

Chapter 35, Question 1.
Sensitivity analysis and missing data

---

Researchers in Taiwan¹ investigated the association between physical activity levels at two time-points and the incidence in depressive symptoms in 3778 participants aged 50 or older. The primary analyses categorised patients into four groups based on their activity levels when assessed in 1996 and 1999 (high/high, high/low, low/high or low/low) and excluded patients with any missing data on either the exposure variable or any of the other covariates in the model. To investigate the possible impact of missing data, a sensitivity analysis was performed in which missing data were imputed using a multiple imputation approach. The findings from the sensitivity analysis generally supported the findings from the main analyses.

1. Ku, P-W., Fox, K.R., and Chen, L-J. (2009) Physical activity and depressive symptoms in Taiwanese older adults: A seven-year follow-up study. Prevent. Med. 48; 250-255.

Select all of the statements which you believe are true.

The authors performed the sensitivity analyses so that they could identify the sub-group of participants in whom the association between physical activity and depressive symptoms was strongest.
The authors performed a sensitivity analysis to see whether those with missing data on any of the covariates were more likely to experience depressive symptoms.
The finding that the sensitivity analyses for missing data gave similar results to the main analysis reassured the authors that their findings were unlikely to be due to bias.
The finding that the sensitivity analyses for missing data gave similar results to the main analysis reassured the authors that the exclusion of participants with missing data had not biased their findings.
The finding that the sensitivity analyses for missing data gave similar results to the main analysis suggests that the authors’ findings are relatively robust to any effects of missing data.