ninds: NINDS rt-PA stroke trial data
In JMcmprsk: Joint Models for Longitudinal and Competing Risks Data

The ninds data frame has 1906 rows and 16 columns.

1	data(ninds)

This data frame contains the following columns:

ID: patient identifier.
Y: Acute ischemic stroke in an ordinal scale. Coded as 1 = no symptoms or no significant disability despite symptoms; 2 = slight disability; 3 = moderate disability or moderately severe disability; 4 = severe disability or dead.
intcpt_RE: a column of 1's for model setup as a random intercept covariate.
smlves_NP: small vessel occlusive disease as a non-proportional odds covariate.
lvORcs_NP: large vessel atherosclerosis / cardioembolic stroke as a non-proportional odds covariate.
group: treatment group indicator.
time3: dummy variable to indicate 3 months of follow-up.
time6: dummy variable to indicate 6 months of follow-up.
time12: dummy variable to indicate 12 months of follow-up.
mrkprior: modified Rankin scale prior stroke onset.
smlves: small vessel occlusive disease as a proportional odds covariate.
lvORcs: large vessel atherosclerosis / cardioembolic stroke as a proportional odds covariate.
smlves.group: interaction term between smlves and group.
lvORcs.group: interaction term between lvORcs and group.
surv: time to drop out or remaining in severe disability.
comprisk: event indicator. Coded as 0 = censored; 1 = drop out; 2 = remaining in severe disability.

Li, Ning, et al. "Joint modeling of longitudinal ordinal data and competing risks survival times and analysis of the NINDS rt-PA stroke trial." Statistics in medicine 29.5 (2010): 546-557.

JMcmprsk documentation built on March 22, 2021, 9:07 a.m.