IMPACT OF MISSING DATA DUE TO DROPOUTS ON ESTIMATES OF THE TREATMENT EFFECT IN A RANDOMIZED TRIAL OF ANTIRETROVIRAL THERAPY FOR HIV-INFECTED INDIVIDUALS
Jm. Raboud et al., IMPACT OF MISSING DATA DUE TO DROPOUTS ON ESTIMATES OF THE TREATMENT EFFECT IN A RANDOMIZED TRIAL OF ANTIRETROVIRAL THERAPY FOR HIV-INFECTED INDIVIDUALS, Journal of acquired immune deficiency syndromes and human retrovirology, 12(1), 1996, pp. 46-55
Purpose: To evaluate the impact of missing data due to nonrandom dropo
ut on estimates of the effect of treatment on the CD4 count in a clini
cal trial of antiretroviral therapy for HIV infected individuals, Meth
ods: The effect of treatment on CD4 counts in a recent study of contin
ued ZDV versus ddI in HIV-infected individuals was estimated from the
observed data and after imputing missing CD4 counts for patients who d
ropped out of the study. Imputation methods studied were (a) carrying
forward the last observed CD4 count, (b) predicting missing CD4 counts
from regression models, and (c) assuming that CD4 counts of patients
who dropped out declined at a rate of 100 cells per year. Results: Of
the 245 patients enrolled in the study, 52% completed the planned 48 w
eeks of follow-up, Patients with lower CD4 counts were more likely to
drop out of the study (RR = 1.77; p = 0.0001), Patients receiving ZDV
had a greater tendency to drop out than patients receiving ddI (p = 0.
07), Mean CD4 counts calculated after imputing missing data in ere low
er than those obtained from the observed data at all follow-up times f
or both treatment groups. Imputing CD4 counts with regression models y
ielded higher estimates of the effect of treatment than were obtained
using the observed data, Conclusion: Missing outcome data due to dropo
uts can result in an underestimation of the treatment effect and overl
y optimistic statements about the outcome of participants on both trea
tment arms due to the selective dropout of participants with lower or
decreasing CD4 counts. When there are significant dropout rates in ran
domized trials, imputation is a useful technique to assess the range o
f plausible values of the treatment effect.