This paper discusses estimation and limited-information goodness-of-fit test statistics in factor models for binary data using pairwise likelihood estimation and sampling weights. The paper extends the applicability of pairwise likelihood estimation for factor models with binary data to accommodate complex sampling designs. Additionally, it introduces two key limited-information test statistics: the Pearson chi-squared test and the Wald test. To enhance computational efficiency, the paper introduces modifications to both test statistics. The performance of the estimation and the proposed test statistics under simple random sampling and unequal probability sampling is evaluated using simulated data.

Download full-text PDF

Source
http://dx.doi.org/10.1111/bmsp.12358DOI Listing

Publication Analysis

Top Keywords

test statistics
20
pairwise likelihood
12
likelihood estimation
12
estimation limited-information
8
limited-information goodness-of-fit
8
goodness-of-fit test
8
factor models
8
models binary
8
binary data
8
test
7

Similar Publications

Background: Clinical trials handle a huge amount of data which can be used during the trial to improve the ongoing study conduct. It is suggested by regulators to implement the remote approach to evaluate clinical trials by analysing collected data. Central statistical monitoring helps to achieve that by employing quantitative methods, the results of which are a basis for decision-making on quality issues.

View Article and Find Full Text PDF

Importance: Wound complications after obstetric anal sphincter injury (OASI) can amplify morbidity and affect quality of life.

Objective: The objective of this study was to evaluate for characteristics associated with wound complications after OASI.

Study Design: This was a retrospective cohort study of patients with an OASI who were evaluated in a postpartum pelvic floor healing clinic between November 1, 2020, and May 16, 2023.

View Article and Find Full Text PDF

Understanding Noninferiority Trials: What Stroke Specialists Should Know.

Stroke

January 2025

Department of Neurology, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam Neuroscience, the Netherlands. (Y.B.W.E.M.R.).

Noninferiority trials aim to prove that the efficacy, defined in terms of a key clinical outcome, of a new treatment is not meaningfully worse than that of an established active control. Noninferiority trials are important when other aspects of care can be improved, such as convenience, toxicity, costs, and safety (nonefficacy benefits). While the motivation for a noninferiority trial is straightforward, the design, execution, and interpretation of these trials is not a trivial task.

View Article and Find Full Text PDF

Externalizing traits and behaviors are broadly defined by impairments in self-regulation and impulse control that typically begin in childhood and adolescence. Externalizing behaviors, traits, and symptoms span a range of traditional psychiatric diagnostic categories. In this study, we sought to generate an algorithm that could reliably identify transdiagnostic childhood-onset externalizing cases and controls within a university hospital electronic health record (EHR) database.

View Article and Find Full Text PDF

Objectives: Somatic symptom and related disorders (SSRDs) are complex disorders that are commonly encountered in tertiary paediatric settings. Despite this, little is known about ED use prior to hospital admission. We aimed to describe the pattern of ED use in a cohort of children and adolescents who were subsequently admitted to hospital with SSRD and to identify factors associated with ED presentations.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!