CHAIN: Subset of variables from the CHAIN project, a longitudinal...
In mi: Missing Data Imputation and Model Checking

Description Usage Format Details Source References See Also

The CHAIN cohort was recruited in 1994 from a large number of medical care and social service agencies serving HIV in New York City. Cohort members were interviewed up to 8 times through 2002. A total of 532 CHAIN participants completed at least one interview at either the 6th, 7th or 8th, and 508, 444, 388 interviews were completed respectively at rounds 6,7 and 8th.

1	data(CHAIN)

A data frame with 532 observations on the following 8 variables.

h39b.W1: log of self reported viral load level at round 6th (0 represents undetectable level).
age.W1: age at time of interview at round 6th.
c28.W1: family annual income. Values range from under \$5,000 to \$70,000 or over at round 6th.
pcs.W1: a continuous scale of physical health with a theoretical range between 0 and 100 (better health is associated with higher scale values) at round 6th.
mcs37.W1: a binary measure of poor mental health ( 1=Yes, 0=No ) at round 6th.
b05.W1: ordered interval for the CD4 count (indicator of how much damage HIV has caused to the immune system) at round 6th.
haartadhere.W1: a three-level ordered variable: 0=Not currently taking HAART (highly Active antiretroviral therapy), 1=taking HAART nonadherent, 2=taking HAART adheremt at round 6th.

A missing value in the virus load level (h39b) was assigned to individuals who either could not recall their viral load level, did not have a viral load test in the six month preceding the interview, or reported their viral loads as "good" or "bad".

http://cchps.columbia.edu/research.cfm

Messeri P, Lee G, Abramson DA, Aidala A, Chiasson MA, Jones JD. (2003). “Antiretroviral therapy and declining AIDS mortality in New York City”. Medical Care 41:512–521.

mi

mi documentation built on May 2, 2019, 4:43 p.m.