Poisson Regression Analysis of Ungrouped Data

Overview

Journal Occup Environ Med

Specialties Environmental Health
Occupational Medicine

Date 2005 Apr 20

PMID 15837854

Citations 26

Authors

D LOOMIS

D B Richardson

L Elliott

Affiliations

Soon will be listed here.

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.

Citing Articles

Long-term trends in urban-neighbourhood inequalities in cause-specific mortality and hospitalisation - multilevel analyses among individuals nested in Finnish post-code areas, 1991-2018.

Tarkiainen L, Martikainen P SSM Popul Health. 2023; 21:101323.

PMID: 36589271 PMC: 9798161. DOI: 10.1016/j.ssmph.2022.101323.

Effects of climate variables on the COVID-19 mortality in Bangladesh.

Karim R, Akter N Theor Appl Climatol. 2022; 150(3-4):1463-1475.

PMID: 36276261 PMC: 9579573. DOI: 10.1007/s00704-022-04211-4.

Assessing Entomological and Epidemiological Efficacy of Pyriproxyfen-Treated Ovitraps in the Reduction of Species: A Quasi-Experiment on Dengue Infection Using Saliva Samples.

Ligsay A, Tambio K, Aytona M, Alejandro G, Regencia Z, Baja E Int J Environ Res Public Health. 2022; 19(5).

PMID: 35270720 PMC: 8910485. DOI: 10.3390/ijerph19053026.

Generalizability of randomized controlled trials in heart failure with reduced ejection fraction.

Lim Y, Molnar M, Vaartjes I, Savarese G, Eijkemans M, Uijl A Eur Heart J Qual Care Clin Outcomes. 2021; 8(7):761-769.

PMID: 34596659 PMC: 9603541. DOI: 10.1093/ehjqcco/qcab070.

Radon and cancer mortality among underground uranium miners in the Příbram region of the Czech Republic.

Kelly-Reif K, Sandler D, Shore D, Schubauer-Berigan M, Troester M, Nylander-French L Am J Ind Med. 2021; 63(10):859-867.

PMID: 33448434 PMC: 8256848. DOI: 10.1002/ajim.23167.

References

Steenland K, Deddens J, Zhao S . Biases in estimating the effect of cumulative exposure in log-linear models when estimated exposure levels are assigned. Scand J Work Environ Health. 2000; 26(1):37-43. DOI: 10.5271/sjweh.508. View

Krewski D, Cardis E, Zeise L, Feron V . Empirical approaches to risk estimation and prediction. IARC Sci Publ. 1999; (131):131-78. View

Richardson D . Power calculations for survival analyses via Monte Carlo estimation. Am J Ind Med. 2003; 44(5):532-9. DOI: 10.1002/ajim.10310. View

Steenland K, Deddens J . A practical guide to dose-response analyses and risk assessment in occupational epidemiology. Epidemiology. 2004; 15(1):63-70. DOI: 10.1097/01.ede.0000100287.45004.e7. View

McDonald J, Harris J, Armstrong B . Mortality in a cohort of vermiculite miners exposed to fibrous amphibole in Libby, Montana. Occup Environ Med. 2004; 61(4):363-6. PMC: 1740743. DOI: 10.1136/oem.2003.008649. View

Richardson D, LOOMIS D . The impact of exposure categorisation for grouped analyses of cohort data. Occup Environ Med. 2004; 61(11):930-5. PMC: 1757839. DOI: 10.1136/oem.2004.014159. View

Frome E, Checkoway H . Epidemiologic programs for computers and calculators. Use of Poisson regression models in estimating incidence rates and ratios. Am J Epidemiol. 1985; 121(2):309-23. DOI: 10.1093/oxfordjournals.aje.a114001. View

Pearce N, Checkoway H, Dement J . Exponential models for analyses of time-related factors, illustrated with asbestos textile worker mortality data. J Occup Med. 1988; 30(6):517-22. View

Checkoway H, Pearce N, Dement J . Design and conduct of occupational epidemiology studies: II. Analysis of cohort data. Am J Ind Med. 1989; 15(4):375-94. DOI: 10.1002/ajim.4700150403. View

10.

Dosemeci M, Wacholder S, Lubin J . Does nondifferential misclassification of exposure always bias a true effect toward the null value?. Am J Epidemiol. 1990; 132(4):746-8. DOI: 10.1093/oxfordjournals.aje.a115716. View

11.

Wing S, Shy C, Wood J, Wolf S, Cragle D, Frome E . Mortality among workers at Oak Ridge National Laboratory. Evidence of radiation effects in follow-up through 1984. JAMA. 1991; 265(11):1397-402. View

12.

Wartenberg D, Northridge M . Defining exposure in case-control studies: a new approach. Am J Epidemiol. 1991; 133(10):1058-71. DOI: 10.1093/oxfordjournals.aje.a115815. View

13.

Flegal K, Keyl P, Nieto F . Differential misclassification arising from nondifferential errors in exposure measurement. Am J Epidemiol. 1991; 134(10):1233-44. DOI: 10.1093/oxfordjournals.aje.a116026. View

14.

Gilbert E, Cragle D, Wiggs L . Updated analyses of combined mortality data for workers at the Hanford Site, Oak Ridge National Laboratory, and Rocky Flats Weapons Plant. Radiat Res. 1993; 136(3):408-21. View

15.

Loomis D, Peipins L, Browning S, Howard R, Kromhout H, Savitz D . Organization and classification of work history data in industry-wide studies: an application to the electric power industry. Am J Ind Med. 1994; 26(3):413-25. DOI: 10.1002/ajim.4700260314. View

16.

Brenner H, LOOMIS D . Varied forms of bias due to nondifferential error in measuring exposure. Epidemiology. 1994; 5(5):510-7. View

17.

Savitz D, Loomis D . Magnetic field exposure in relation to leukemia and brain cancer mortality among electric utility workers. Am J Epidemiol. 1995; 141(2):123-34. DOI: 10.1093/oxfordjournals.aje.a117400. View

18.

Kromhout H, Loomis D, Mihlan G, Peipins L, Kleckner R, Iriye R . Assessment and grouping of occupational magnetic field exposure in five electric utility companies. Scand J Work Environ Health. 1995; 21(1):43-50. DOI: 10.5271/sjweh.7. View

19.

Greenland S . Dose-response and trend analysis in epidemiology: alternatives to categorical analysis. Epidemiology. 1995; 6(4):356-65. DOI: 10.1097/00001648-199507000-00005. View

20.

Loomis A, Kromhout H, Kleckner R, Savitz D . Effects of the analytical treatment of exposure data on associations of cancer and occupational magnetic field exposure. Am J Ind Med. 1998; 34(1):49-56. DOI: 10.1002/(sici)1097-0274(199807)34:1<49::aid-ajim7>3.0.co;2-l. View