vcov.bnr

Returns the either the estimated covariance matrix of the outcome, the
information matrix for regression coefficients, or the information matrix for
covariance parameters.

Performs estimation and inference on a partially missing target outcome while borrowing information from a correlated surrogate outcome to increase estimation precision and improve power. The target and surrogate outcomes are jointly modeled within a bivariate outcome regression framework. Unobserved values of either outcome are regarded as missing data. Estimation in the presence of bilateral outcome missingness is performed via an expectation conditional maximization algorithm. A flexible association test is provided for evaluating hypotheses about the target regression parameters. See McCaw ZR, Gaynor SM, Sun R, Lin X; “Cross-tissue eQTL mapping in the presence of missing data via surrogate outcome analysis” <doi:10.1101/2020.11.29.403063>.

Zachary McCaw

SurrogateRegression

Surrogate Outcome Regression Analysis

vcov.bnr function

<dl><dt>object</dt>
<dd><code>bnr</code> object.</dd>
<dt>...</dt>
<dd>Unused.</dd>
<dt>type</dt>
<dd>Select "Covariance","Outcome",or "Regression". Default is
"Regression".</dd>
<dt>inv</dt>
<dd>Invert the covariance matrix? Default is FALSE.</dd></dl>

Arguments

Extract Covariance Matrix from Bivariate Normal Regression Model — vcov.bnr

<dl>

<dt>object</dt>
<dd><code>bnr</code> object.</dd>


<dt>...</dt>
<dd>Unused.</dd>


<dt>type</dt>
<dd>Select "Covariance","Outcome",or "Regression". Default is
"Regression".</dd>


<dt>inv</dt>
<dd>Invert the covariance matrix? Default is FALSE.</dd>

</dl>

vcov.bnr: Extract Covariance Matrix from Bivariate Normal Regression Model

Description

Usage

Arguments