TITLE

Poisson regression analysis of ungrouped data

AUTHOR(S)
Loomis, D.; Richardson, D. B.; Elliott, L.
PUB. DATE
May 2005
SOURCE
Occupational & Environmental Medicine;May2005, Vol. 62 Issue 5, p325
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
Background: Poisson regression is routinely used for analysis of epidemiological data from studies of large occupational cohorts. It is typically implemented as a grouped method of data analysis in which all exposure and covariate information is categorised and person-time and events are tabulated. Aims: To describe an alternative approach to Poisson regression analysis using single units of person-time without grouping. Methods: Data for simulated and empirical cohorts were analysed by Poisson regression. In analyses of simulated data, effect estimates derived via Poisson regression without grouping were compared to those obtained under proportional hazards regression. Analyses of empirical data for a cohort of 138 900 electrical workers were used to illustrate how the ungrouped approach may be applied in analyses of actual occupational cohorts. Results: Using simulated data, Poisson regression analyses of ungrouped person-time data yield results equivalent to those obtained via proportional hazards regression: the results of both methods gave unbiased estimates of the "true" association specified for the simulation. Analyses of empirical data confirm that grouped and ungrouped analyses provide identical results when the same models are specified. However, bias may arise when exposure-response trends are estimated via Poisson regression analyses in which exposure scores, such as category means or midpoints, are assigned to grouped data. Conclusions: Poisson regression analysis of ungrouped person-time data is a useful tool that can avoid bias associated with categorising exposure data and assigning exposure scores, and facilitate direct assessment of the consequences of exposure categorisation and score assignment on regression results.
ACCESSION #
17095981

 

Related Articles

  • Point process models for mixed sessile forest stands. Ngo Bieng, Marie; Ginisty, Christian; Goreaud, François // Annals of Forest Science (EDP Sciences);Mar2011, Vol. 68 Issue 2, p267 

    • Background: Growth modelling of complex stands calls for the use of spatially explicit single-tree models. Such models require spatially explicit tree locations as the initial state to run simulations. Given the cost of such data, virtual forest stands, where tree locations are...

  • A New Method for Estimating the Distribution of Scan Statistics for a Two-Dimensional Poisson Process. Haiman, G.; Preda, C. // Methodology & Computing in Applied Probability;Dec2002, Vol. 4 Issue 4, p393 

    A method for estimating the distribution of scan statistics with high precision was introduced in Haiman (2000). Using that method sharp bounds for the errors were also established. This paper is concerned with the application of the method in Haiman (2000) to a two-.dimensional Poisson process....

  • SIMULATION OF CLUSTER POINT PROCESSES WITHOUT EDGE EFFECTS. Brix, Anders; Kendall, Wilfrid S. // Advances in Applied Probability;Jun2002, Vol. 34 Issue 2, p267 

    Presents a simulation method for cluster point processes which requires simulation only of those parent points actually giving rise to observed daughter points. Random pattern of parent points; Method to avoid edge effect approximation when simulating a cluster point process; Simulation of...

  • SHOT NOISE COX PROCESSES. M�ller, Jesper // Advances in Applied Probability;Sep2003, Vol. 35 Issue 3, p614 

    Shot noise Cox processes constitute a large class of Cox and Poisson cluster processes in R[sup d], including Neyman-Scott, Poisson-gamma and shot noise G Cox processes. It is demonstrated that, due to the structure of such models, a number of useful and general results can easily be...

  • Point patterns of forest fire locations. Turner, Rolf // Environmental & Ecological Statistics;Jun2009, Vol. 16 Issue 2, p197 

    In this paper I demonstrate some of the techniques for the analysis of spatial point patterns that have become available due to recent developments in point process modelling software. These developments permit convenient exploratory data analysis, model fitting, and model assessment. Efficient...

  • A new approach to analyse longitudinal epidemiological data with an excess of zeros. Spriensma, Alette S.; Hajos, Tibor R. S.; de Boer, Michiel R.; Heymans, Martijn W.; Twisk, Jos W. R. // BMC Medical Research Methodology;2013, Vol. 13 Issue 1, p1 

    Background: Within longitudinal epidemiological research, 'count' outcome variables with an excess of zeros frequently occur. Although these outcomes are frequently analysed with a linear mixed model, or a Poisson mixed model, a two-part mixed model would be better in analysing outcome variables...

  • SDRF2GRAPH -- a visualization tool of a spreadsheet-based description of experimental processes. Kawaji, Hideya; Hayashizaki, Yoshihide; Daub, Carsten O. // BMC Bioinformatics;2009, Vol. 10, Special section p1 

    Background: As larger datasets are produced with the development of genome-scale experimental techniques, it has become essential to explicitly describe the meta-data (information describing the data) generated by an experiment. The experimental process is a part of the metadata required to...

  • From Data to the Physics Using Ultrametrics: New Results in High Dimensional Data Analysis. Murtagh, Fionn // AIP Conference Proceedings;2006, Vol. 826 Issue 1, p151 

    We begin with pervasive ultrametricity due to high dimensionality and/or spatial sparsity. How extent or degree of ultrametricity can be quantified leads us to the discussion of varied practical cases when ultrametricity can be partially or locally present in data. We show how the ultrametricity...

  • The Limiting Behavior for Observations That Change with Time*. Xiuyun Wang; Zhengyan Lin // Chinese Annals of Mathematics;Feb2007, Vol. 28 Issue 1, p123 

    Consider a system where units have random magnitude entering according to a homogeneous or nonhomogeneous Poisson process, while in the system, a unit's magnitude may change with time. In this paper, the authors obtain some results for the limiting behavior of the sum process of all unit...

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

Sign out of this library

Other Topics