Bayesian inference for categorical data analysis

Agresti, Alan; Hitchcock, David B.

doi:10.1007/s10260-005-0121-y

Cited by 133 publications

(98 citation statements)

References 244 publications

(207 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Where significant changes were evident, standardized residuals for each time period were examined, with scores of greater than or equal to ±1.96 indicating cells with significant variation from expected. 54 For such analyses, study type was reduced to measures/descriptive and intervention research. Two variables were created for study population: "severe" only versus all other categories; and >1 category versus 1 category only.…”

Section: Discussionmentioning

confidence: 99%

Smoking and Mental Illness: A Bibliometric Analysis of Research Output Over Time

Metse¹,

Wiggers²,

Wye³

et al. 2016

NICTOB

View full text Add to dashboard Cite

Introduction: The prevalence of smoking among persons with a mental illness has remained unchanged, being 2-3 times higher than the general population in high-income countries. Assessment of the volume and characteristics of research output over time can assist in identifying research priorities to promote progress within a field. The aim of this study was to undertake such an assessment in the field of smoking and mental illness. Methods: A descriptive repeat cross-sectional study was conducted of peer-reviewed publications in Medline and PsycINFO for the periods 1993-1995, 2003-2005, and 2013-2015. Publications were classified as data-or non-data-based; data-based publications were further categorized by study type, population, setting, and for intervention-focused publications by level of evidence and research translation phase. Results: Included were 547 articles published in 1993-1995 (n = 65), 2003-2005 (n = 153), and 2013-2015 (n = 329). The number and proportion of data-based publications significantly increased over time, although their focus remained predominantly descriptive (≥83%); less than 14% of publications in any period had an intervention focus. The proportion of publications reporting on study populations with multiple diagnostic categories and recruiting from nonmental health settings, significantly increased from 1993-1995 to 2003-2005, however then plateaued by 2013-2015. The level of evidence provided by intervention-focused publications was suggested to increase over time, however there was no evident variation in translation phase. Conclusions: Research has increased over time to characterize smoking among those with a mental illness; however more is needed to inform the development and implementation of effective cessation interventions for this group. Implications: This is the first study to examine the volume and characteristics of research publications in the field of smoking and mental illness over time. The number of publications increased fivefold between

show abstract

Section: Discussionmentioning

confidence: 99%

Smoking and Mental Illness: A Bibliometric Analysis of Research Output Over Time

Metse¹,

Wiggers²,

Wye³

et al. 2016

NICTOB

View full text Add to dashboard Cite

show abstract

“…As a first step, for most of the scores computed in the following sections probabilities have to be estimated from the ensemble. We estimate the event probability p(y i ) using a beta-binominal model with a flat beta prior (Agresti and Hitchcock, 2005) which leads to…”

Section: Probabilistic Performancementioning

confidence: 99%

Towards a probabilistic regional reanalysis system for Europe: evaluation of precipitation from experiments

Bach¹,

Schraff²,

Keller³

et al. 2016

Tellus A: Dynamic Meteorology and Oceanography

View full text Add to dashboard Cite

A B S T R A C TA new development in the field of reanalyses is the incorporation of uncertainty estimation capabilities. We have developed a probabilistic regional reanalysis system for the CORDEX-EUR11 domain that is based on the numerical weather prediction model COSMO at a 12-km grid spacing. The lateral boundary conditions of all ensemble members are provided by the global reanalysis ERA-Interim. In the basic implementation of the system, uncertainties due to observation errors are estimated. Atmospheric assimilation of conventional observations perturbed by means of random samples of observation error yields estimates of the reanalysis uncertainty conditioned to observation errors. The data assimilation employed is a new scheme based on observation nudging that we denote ensemble nudging. The lower boundary of the atmosphere is regularly updated by external snow depth, sea surface temperature and soil moisture analyses. One of the most important purposes of reanalyses is the estimation of so-called essential climate variables. For regional reanalyses, precipitation has been identified as one of the essential climate variables that are potentially better represented than in other climate data sets. For that reason, we assess the representation of precipitation in our system in a pilot study. Based on two experiments, each of which extends over one month, we conduct a preliminary comparison to the global reanalysis ERAInterim, a dynamical downscaling of the latter and the high-resolution regional reanalysis COSMO-REA6. In a next step, we assess our reanalysis system's probabilistic capabilities versus the ECMWF-EPS in terms of sixhourly precipitation sums. The added value of our probabilistic regional reanalysis system motivates the current production of a 5-year-long test reanalysis COSMO-EN-REA12 in the framework of the FP7-funded project Uncertainties in Ensembles of Regional Re-Analyses (UERRA).

show abstract

“…Details and further information on the Bradley-Terry model can be found in Agresti (2002). A simple iterative algorithm for finding the maximum likelihood estimate, π i j , has been known for a long time, see Zermelo (1929 Agresti and Hitchcock (2005). In fact, there are known conditions that ensure whether or not the algorithms to find π i j converge, see Ford (1957) and Hunter (2004).…”

Section: Bradley-terry Modelmentioning

confidence: 99%

An Oracle method to predict NFL games

Balreira

Miceli

Tegtmeyer

2014

Journal of Quantitative Analysis in Sports

View full text Add to dashboard Cite

Multiple models are discussed for ranking teams in a league and introduce a new model called the Oracle method. This is a Markovian method that can be customized to incorporate multiple team traits into its ranking. Using a foresight prediction of NFL game outcomes for the 2002-2013 seasons, it is shown that the Oracle method correctly picked 64.1% of the games under consideration, which is higher than any of the methods compared, including ESPN Power Rankings, Massey, Colley, and PageRank.

show abstract

Bayesian inference for categorical data analysis

Cited by 133 publications

References 244 publications

Smoking and Mental Illness: A Bibliometric Analysis of Research Output Over Time

Smoking and Mental Illness: A Bibliometric Analysis of Research Output Over Time

Towards a probabilistic regional reanalysis system for Europe: evaluation of precipitation from experiments

An Oracle method to predict NFL games

Contact Info

Product

Resources

About