Raboud, J. M., Montaner, J. S. G., Thorne, A., Singer, J., Schechter, M. T., Rachlis, A., Gill, J., Beaulieu, R., Tsoukas, C., Fanning, M., Cameron, W., Lalonde, R., Bergeron, M., Schlech, W., Salit, I., Phillips, P., Salomon, H., Spira, B., Conway, B., ... Wainberg, M. A. (1996). 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), 46-55. https://doi.org/10.1097/00042560-199605010-00007
Impact of missing data due to dropouts on estimates of the treatment effect in a randomized trial of antiretroviral therapy for HIV-infected individuals. / Raboud, J. M.; Montaner, J. S.G.; Thorne, A. et al.
In:
Journal of Acquired Immune Deficiency Syndromes and Human Retrovirology, Vol. 12, No. 1, 1996, p. 46-55.
Research output: Contribution to journal › Article › peer-review
Raboud, JM, Montaner, JSG, Thorne, A, Singer, J, Schechter, MT, Rachlis, A, Gill, J, Beaulieu, R, Tsoukas, C, Fanning, M, Cameron, W, Lalonde, R, Bergeron, M, Schlech, W, Salit, I, Phillips, P, Salomon, H, Spira, B, Conway, B, Auclair, C, Cassol, S, O'Shaughnessy, MV & Wainberg, MA 1996, '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, vol. 12, no. 1, pp. 46-55. https://doi.org/10.1097/00042560-199605010-00007
Raboud JM, Montaner JSG, Thorne A, Singer J, Schechter MT, Rachlis A 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. 1996;12(1):46-55. doi: 10.1097/00042560-199605010-00007
Raboud, J. M. ; Montaner, J. S.G. ; Thorne, A. 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. In: Journal of Acquired Immune Deficiency Syndromes and Human Retrovirology. 1996 ; Vol. 12, No. 1. pp. 46-55.
@article{477bd2f6dd074a61af04b67130382e20,
title = "Impact of missing data due to dropouts on estimates of the treatment effect in a randomized trial of antiretroviral therapy for HIV-infected individuals",
abstract = "Purpose: To evaluate the impact of missing data due to nonrandom dropout on estimates of the effect of treatment on the CD4 count in a clinical trial of antiretroviral therapy for HIV infected individuals. Methods: The effect of treatment on CD4 counts in a recent study of continued ZDV versus ddI in HIV-infected individuals was estimated from the observed data and after imputing missing CD4 counts for patients who dropped 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 weeks 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 were lower than those obtained from the observed data at all follow-up times for both treatment groups. Imputing CD4 counts with regression models yielded higher estimates of the effect of treatment than were obtained using the observed data. Conclusion: Missing outcome data due to dropouts can result in an underestimation of the treatment effect and overly optimistic statements about the outcome of participants on both treatment arms due to the selective dropout of participants with lower or decreasing CD4 counts. When there are significant dropout rates in randomized trials, imputation is a useful technique to assess the range of plausible values of the treatment effect.",
author = "Raboud, {J. M.} and Montaner, {J. S.G.} and A. Thorne and J. Singer and Schechter, {M. T.} and A. Rachlis and J. Gill and R. Beaulieu and C. Tsoukas and M. Fanning and W. Cameron and R. Lalonde and M. Bergeron and W. Schlech and I. Salit and P. Phillips and H. Salomon and B. Spira and B. Conway and C. Auclair and S. Cassol and O'Shaughnessy, {M. V.} and Wainberg, {M. A.}",
year = "1996",
doi = "10.1097/00042560-199605010-00007",
language = "English",
volume = "12",
pages = "46--55",
journal = "Journal of Acquired Immune Deficiency Syndromes and Human Retrovirology",
issn = "1077-9450",
publisher = "Lippincott Williams and Wilkins",
number = "1",
}
TY - JOUR
T1 - Impact of missing data due to dropouts on estimates of the treatment effect in a randomized trial of antiretroviral therapy for HIV-infected individuals
AU - Raboud, J. M.
AU - Montaner, J. S.G.
AU - Thorne, A.
AU - Singer, J.
AU - Schechter, M. T.
AU - Rachlis, A.
AU - Gill, J.
AU - Beaulieu, R.
AU - Tsoukas, C.
AU - Fanning, M.
AU - Cameron, W.
AU - Lalonde, R.
AU - Bergeron, M.
AU - Schlech, W.
AU - Salit, I.
AU - Phillips, P.
AU - Salomon, H.
AU - Spira, B.
AU - Conway, B.
AU - Auclair, C.
AU - Cassol, S.
AU - O'Shaughnessy, M. V.
AU - Wainberg, M. A.
PY - 1996
Y1 - 1996
N2 - Purpose: To evaluate the impact of missing data due to nonrandom dropout on estimates of the effect of treatment on the CD4 count in a clinical trial of antiretroviral therapy for HIV infected individuals. Methods: The effect of treatment on CD4 counts in a recent study of continued ZDV versus ddI in HIV-infected individuals was estimated from the observed data and after imputing missing CD4 counts for patients who dropped 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 weeks 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 were lower than those obtained from the observed data at all follow-up times for both treatment groups. Imputing CD4 counts with regression models yielded higher estimates of the effect of treatment than were obtained using the observed data. Conclusion: Missing outcome data due to dropouts can result in an underestimation of the treatment effect and overly optimistic statements about the outcome of participants on both treatment arms due to the selective dropout of participants with lower or decreasing CD4 counts. When there are significant dropout rates in randomized trials, imputation is a useful technique to assess the range of plausible values of the treatment effect.
AB - Purpose: To evaluate the impact of missing data due to nonrandom dropout on estimates of the effect of treatment on the CD4 count in a clinical trial of antiretroviral therapy for HIV infected individuals. Methods: The effect of treatment on CD4 counts in a recent study of continued ZDV versus ddI in HIV-infected individuals was estimated from the observed data and after imputing missing CD4 counts for patients who dropped 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 weeks 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 were lower than those obtained from the observed data at all follow-up times for both treatment groups. Imputing CD4 counts with regression models yielded higher estimates of the effect of treatment than were obtained using the observed data. Conclusion: Missing outcome data due to dropouts can result in an underestimation of the treatment effect and overly optimistic statements about the outcome of participants on both treatment arms due to the selective dropout of participants with lower or decreasing CD4 counts. When there are significant dropout rates in randomized trials, imputation is a useful technique to assess the range of plausible values of the treatment effect.
UR - http://www.scopus.com/inward/record.url?scp=1842614350&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=1842614350&partnerID=8YFLogxK
U2 - 10.1097/00042560-199605010-00007
DO - 10.1097/00042560-199605010-00007
M3 - Article
AN - SCOPUS:1842614350
SN - 1077-9450
VL - 12
SP - 46
EP - 55
JO - Journal of Acquired Immune Deficiency Syndromes and Human Retrovirology
JF - Journal of Acquired Immune Deficiency Syndromes and Human Retrovirology
IS - 1
ER -