Learn R Programming

PHInfiniteEstimates (version 2.9.5)

Tools for Inference in the Presence of a Monotone Likelihood

Description

Proportional hazards estimation in the presence of a partially monotone likelihood has difficulties, in that finite estimators do not exist. These difficulties are related to those arising from logistic and multinomial regression. References for methods are given in the separate function documents. Supported by grant NSF DMS 1712839.

Copy Link

Version

Install

install.packages('PHInfiniteEstimates')

Monthly Downloads

277

Version

2.9.5

License

GPL-3

Maintainer

John E Kolassa

Last Published

November 24th, 2023

Functions in PHInfiniteEstimates (2.9.5)

Convert a proportional hazards regression to a multinomial regression.

Test size of asymptotic Cox tests.

Reduce a logistic regression with monotone likelihood to a conditional regression with double descending likelihood.

Summarize the results of simulations investigating operating conditions for the data reduction method to avoid monotone likelihood. Files are of form "hsxxx", for xxx numerals.

Summarize proportional hazards fits

lrapproximations

Assess the accuracy of the log rank statistic approximation to the true value, in the case without censoring. Provides plots of statistics, and empirical test level.

Perform inference on conditional sample space.

Subset of British elections data used in kolassa16PHInfiniteEstimates. Data are from besPHInfiniteEstimates.

Simulate Weibull survival data from a model, perform reduction to remove infinite estimates, and calculate p values.

simultaneouscoverage

Calculate simultaneous coverage of pointwise confidence intervals.

PHInfiniteEstimates

PHInfiniteEstimates: Tools for Proportional Hazards Estimation, and Inference on the Associate Parameters, when Other Parameters are Estimated at Infinity.

Plot resuts of simcode

Examine the potential role of treatment in treatment in a model already including sex. Straight lines that are not 45 degrees indicate the appropriateness of new variable as a linear effect.

Newton Raphson Fitter for partial likelihood

Plot hazards for two strata for each time. At times with an event in one but not the other group, the fitted hazard remains constant, and so the plot is a step function. If hazards are proportional between strata, then the plot should be close to a straight line.

compete.simulation

Simulate from a competing risk model with correlated log normal errors, and plot various estimates.

Calculate the Aalen-Johansen (1978) estimate in the Competing risk context. See Aalen, Odd O., and Søren Johansen. "An Empirical Transition Matrix for Non-Homogeneous Markov Chains Based on Censored Observations." Scandinavian Journal of Statistics 5, no. 3 (1978): 141-50. Accessed January 15, 2021. http://www.jstor.org/stable/4615704.

Produce a graphical assessment of Monte Carlo experiment on fidelity of proportional hazards regression to the uniform ideal.

convertbaselineltolr

Convert a baseline logit model data set, formatted in the long form as described in the documentation for mlogit.data from mlogit package, to a conditional logistic regression.

Check how censoring impacts sampling properties of KM fit and log rank test.

Convert a polytomous regression to a conditional logistic regression.

This function enumerates conditional sample spaces associated with logistic regression,

Remove observations from a proportional hazards regression, and return the fit of the reduced model.

Proportional hazards partial likelihood, using Breslow method for ties, excluding some observations.

Simulate operating characteristics of repaired Cox regression and competitors.

Draw diagram for toy PH example.

gehan.wilcoxon.test

Perform Gehan's application to the Wilcoxon test for multiple samples, testing for equivalance of survival curve. See Klein and Moeschberger (1997) Survival Analysis (7.3.3) and pp. 193-194.

Fit survival probabilties from a survreg object.

Partial likelihood for proportional hazards