[Statistical models and multivariable analysis].

P Ravani; F Malberti

PubMed · 16267795

[Statistical models and multivariable analysis].

Abstract

Most clinical research can be simplified as an investigation of an input/output relationship. The inputs are called explanatory (independent) variables or predictors and are thought to be related to the outcome, or response (independent) variable. This relationship is usually complicated by other factors related to both the input and the output (presence of confounding) and can vary according to the levels of the other variables (presence of interaction). This input/output relationship is usually described by statistical models that include a fit part and a residual component or difference between the data and the fit. The most popular models are the general linear models, which can be considered the paradigm of all models used in multi-variable analyzes.

Explore related subjects

Biomedical Research Humans Models, Statistical Multivariate Analysis English Abstract Journal Article Review

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

P Ravani, F Malberti. [Statistical models and multivariable analysis].. https://pubmed.ncbi.nlm.nih.gov/16267795/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

Covariates missing by design: comparison of the efficient score to other weighted methods.

This paper addresses the modelling of missing covariate data with the logistic regression model. The aim of this paper is to evaluate the properties of an efficient score for logistic regression in a two-phase design. Simulation studies show that the efficient score is more efficient than two other pseudo-likelihood methods when the correlation between the missing covariate and its surrogate is high or the sampling proportion is small. These methods are illustrated with data from the National Wilms Tumor Study Group. Results from the example confirm the simulation study findings with the exception that the pseudo-likelihood approach produces more reliable estimates than the weighted pseudo-likelihood approach.

Biomedical Research↗

PubMed2007

Tree-based model checking for logistic regression.

A tree procedure is proposed to check the adequacy of a fitted logistic regression model. The proposed method not only makes natural assessment for the logistic model, but also provides clues to amend its lack-of-fit. The resulting tree-augmented logistic model facilitates a refined model with meaningful interpretation. We demonstrate its use via simulation studies and an application to the Pima Indians diabetes data.

Biomedical Research↗

PubMed2007

Evidence-based analysis of physical therapy in Parkinson's disease with recommendations for practice and research.

Physical therapy is often prescribed in Parkinson's disease. To facilitate the uniformity and efficacy of this intervention, we analyzed current evidence and developed practice recommendations. We carried out an evidence-based literature review. The results were supplemented with clinical expertise and patient values and translated into practice recommendations, developed according to international standards for guideline development. A systematic literature search yielded 6 systematic reviews and 23 randomized controlled trials of moderate methodological quality with sufficient data. Six specific core areas for physical therapy were identified: transfers, posture, reaching and grasping, balance, gait, and physical capacity. We extracted four specific treatment recommendations that were based on evidence from more than two controlled trials: cueing strategies to improve gait; cognitive movement strategies to improve transfers; exercises to improve balance; and training of joint mobility and muscle power to improve physical capacity. These practice recommendations provide a basis for current physical therapy in Parkinson's disease in everyday clinical practice, as well as for future research in this field.

Biomedical Research↗