| convertstoml {PHInfiniteEstimates} | R Documentation |
Convert a proportional hazards regression to a multinomial regression.
Description
Convert a proportional hazards regression to a multinomial regression.
Usage
convertstoml(survobj, covmat)
Arguments
survobj |
A survival object, with potentially right censoring. |
covmat |
a matrix of covariates. |
Details
Implements version of (Kolassa and Zhang 2019).
The proportional hazards regression is converted to a multinomial regression logistic regression, and methods of (Kolassa 2016) may be applied.
This function is intended to produce intermediate results to be passed to convertmtol, and then to reduceLR of (Kolassa 1997). See examples in the convertmtol documentation.
Value
a data set on which to apply conditional multinomial regression, corresponding to the proportional hazards regression analysis. In order to run the line commented out below, you would need this: # @importFrom mlogit mlogit.data
References
Kolassa JE (1997). “Infinite Parameter Estimates in Logistic Regression.” Scandinavian Journal of Statistics, 24, 523–530. doi:10.1111/1467-9469.00078.
Kolassa JE (2016). “Inference in the Presence of Likelihood Monotonicity for Polytomous and Logistic Regression.” Advances in Pure Mathematics, 6, 331-341. doi:10.4236/apm.2016.65024.
Kolassa JE, Zhang J (2019). https://higherlogicdownload.s3.amazonaws.com/AMSTAT/fa4dd52c-8429-41d0-abdf-0011047bfa19/UploadedImages/NCB_Conference/Presentations/2019/kolassa_toxslides.pdf. Accessed: 2019-07-14.