testcox

Test size of asymptotic Cox tests.

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.

John E Kolassa

PHInfiniteEstimates

Tools for Inference in the Presence of a Monotone Likelihood

testcox function

<dl><dt>nsamp</dt>
<dd>Number of MC samples</dd>
<dt>nobs</dt>
<dd>Number of observations</dd>
<dt>ncov</dt>
<dd>Number of covariates</dd>
<dt>randomcov</dt>
<dd>Indicator of whether to draw random covariates.</dd></dl>

Arguments

Test size of asymptotic Cox tests. — testcox

<dl>

<dt>nsamp</dt>
<dd>Number of MC samples</dd>


<dt>nobs</dt>
<dd>Number of observations</dd>


<dt>ncov</dt>
<dd>Number of covariates</dd>


<dt>randomcov</dt>
<dd>Indicator of whether to draw random covariates.</dd>

</dl>

testcox: Test size of asymptotic Cox tests.

Description

Usage

Value

Arguments