ACTG388 Longitudinal Data: CD4+ T Cell Counts in Two Treatment Arms for Nonparametric Mixed-Effects Models

Data File for Arm 1

Data File for All Three Arms

1. The data were produced from AIDS Clinical Trials Group, ACTG 388 study, which is sponsored by NIAID/NIH. If you have any questions regarding the data, you may contact Dr. Hulin Wu by email:

2. The detailed biomedical findings from this study and more detailed description of the study design can be found from the primary publication of this study, Fischl et al. (2003, Journal of Infectious Diseases). See below for detailed reference list.

3. This data set was used in the paper by Park and Wu (2005) in which more details about the data can be found. A nonparametric mixed-effects model was proposed to model the CD4 response.

4. The data set is part of the data from the AIDS Clinical Trials Group (ACTG) 388 study. The study enrolled 517 HIV-1 infected patients in three antiretroviral treatments. This data set is only CD4 count data from one of the three treatment arms in which 166 patients were treated with an highly active antiretroviral therapy (HAART) for 120 weeks. CD4 cell counts were monitored at weeks 4, 8, and every 8 weeks thereafter.

5. Please cite the following references if appropriate when you use the data in your paper:

1) Fischl MA, Ribaudo HJ, Collier AC, et al. (2003), "A Randomized Trial of 2 Different 4-Drug Antiretroviral Regimens versus a 3-Drug Regimen, in Advanced Human Immunodeficiency Virus Disease," Journal of Infectious Diseases, 188:625-634.

2) Park, J.G. and Wu, H. (2005), "Backfitting and Local Likelihood Methods for Nonparametric Mixed-Effects Models with Longitudinal Data," Journal of Statistical Planning and Inference, in press.