hepatitis

Data from a randomized double-blind trial to assess whether
withholding donor blood positive for the non-A, non-B (<code>"NANB"</code>)
surrogate markers would reduce the frequency of post-transfusion
hepatitis. The dataset contains <code>4588</code> subjects enrolled from 1988
to 1992 into two study groups that received allogenic blood from
which units positive for NANB surrogate markers were withheld (n =
<code>2311</code>) or not withheld (n = <code>2277</code>). Subjects were followed up
for 6 months and assessed for the presence of post-transfusion
hepatitis.

datasets

Estimation and inference from generalized linear models based on various methods for bias reduction and maximum penalized likelihood with powers of the Jeffreys prior as penalty. The 'brglmFit' fitting method can achieve reduction of estimation bias by solving either the mean bias-reducing adjusted score equations in Firth (1993) <doi:10.1093/biomet/80.1.27> and Kosmidis and Firth (2009) <doi:10.1093/biomet/asp055>, or the median bias-reduction adjusted score equations in Kenne et al. (2017) <doi:10.1093/biomet/asx046>, or through the direct subtraction of an estimate of the bias of the maximum likelihood estimator from the maximum likelihood estimates as in Cordeiro and McCullagh (1991) <https://www.jstor.org/stable/2345592>. See Kosmidis et al (2020) <doi:10.1007/s11222-019-09860-6> for more details. Estimation in all cases takes place via a quasi Fisher scoring algorithm, and S3 methods for the construction of of confidence intervals for the reduced-bias estimates are provided. In the special case of generalized linear models for binomial and multinomial responses (both ordinal and nominal), the adjusted score approaches to mean and media bias reduction have been found to return estimates with improved frequentist properties, that are also always finite, even in cases where the maximum likelihood estimates are infinite (e.g. complete and quasi-complete separation; see Kosmidis and Firth, 2020 <doi:10.1093/biomet/asaa052>, for a proof for mean bias reduction in logistic regression).

Ioannis Kosmidis

brglm2

Bias Reduction in Generalized Linear Models

Kjell Konis

Nicola Sartori

hepatitis function

A data frame with 28 rows and the following 6 columns:<ul>
<li><code>city</code>: Subjects were recruited from 3 Canadian Red Cross Society
Blood Centres and 13 university-affiliated hospitals in 3 cities:
Toronto, Hamilton and Winnipeg.</li>
<li><code>group</code>: Eligible subjects were assigned to one of two allogenic
blood recipient groups. One group received products that had only
routine Canadian transfusion-transmissible disease marker screening
(no-withhold). The other group received only products that were
not positive for NANB surrogate markers (withhold).</li>
<li><code>time</code>: Hepatitis C (HCV) screening was introduced in Canada in
May, 1990. Subjects were recruited into the study before (pre) and
after (post) the introduction of anti-HCV testing.</li>
<li><code>HCV</code>: Post-transfusion HCV hepatitis present (1) or absent (0).</li>
<li><code>nonABC</code>: Post-transfusion non-A, non-B, non-C hepatitis present (1) or absent (0)</li>
<li><code>counts</code>: Number of subjects</li>
</ul>

hepatitis: Post-transfusion hepatitis: impact of non-A, non-B hepatitis surrogate tests

Description

Usage

Arguments

Format

References