Adjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population-based research
Abstract Background In population-based cancer research, piecewise exponential regression models are used to derive adjusted estimates of excess mortality due to cancer using the Poisson generalized linear modelling framework. However, the assumption that the conditional mean and variance of the rat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2016-10-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12874-016-0234-z |
| _version_ | 1818523728564191232 |
|---|---|
| author | Miguel Angel Luque-Fernandez Aurélien Belot Manuela Quaresma Camille Maringe Michel P. Coleman Bernard Rachet |
| author_facet | Miguel Angel Luque-Fernandez Aurélien Belot Manuela Quaresma Camille Maringe Michel P. Coleman Bernard Rachet |
| author_sort | Miguel Angel Luque-Fernandez |
| collection | DOAJ |
| description | Abstract Background In population-based cancer research, piecewise exponential regression models are used to derive adjusted estimates of excess mortality due to cancer using the Poisson generalized linear modelling framework. However, the assumption that the conditional mean and variance of the rate parameter given the set of covariates x i are equal is strong and may fail to account for overdispersion given the variability of the rate parameter (the variance exceeds the mean). Using an empirical example, we aimed to describe simple methods to test and correct for overdispersion. Methods We used a regression-based score test for overdispersion under the relative survival framework and proposed different approaches to correct for overdispersion including a quasi-likelihood, robust standard errors estimation, negative binomial regression and flexible piecewise modelling. Results All piecewise exponential regression models showed the presence of significant inherent overdispersion (p-value <0.001). However, the flexible piecewise exponential model showed the smallest overdispersion parameter (3.2 versus 21.3) for non-flexible piecewise exponential models. Conclusion We showed that there were no major differences between methods. However, using a flexible piecewise regression modelling, with either a quasi-likelihood or robust standard errors, was the best approach as it deals with both, overdispersion due to model misspecification and true or inherent overdispersion. |
| first_indexed | 2024-12-11T05:48:24Z |
| format | Article |
| id | doaj.art-5e9c654d3b77483097d0252a29bfe630 |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-12-11T05:48:24Z |
| publishDate | 2016-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-5e9c654d3b77483097d0252a29bfe6302022-12-22T01:18:53ZengBMCBMC Medical Research Methodology1471-22882016-10-011611810.1186/s12874-016-0234-zAdjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population-based researchMiguel Angel Luque-Fernandez0Aurélien Belot1Manuela Quaresma2Camille Maringe3Michel P. Coleman4Bernard Rachet5Department of Non-Communicable Disease Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine, Cancer Survival GroupDepartment of Non-Communicable Disease Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine, Cancer Survival GroupDepartment of Non-Communicable Disease Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine, Cancer Survival GroupDepartment of Non-Communicable Disease Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine, Cancer Survival GroupDepartment of Non-Communicable Disease Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine, Cancer Survival GroupDepartment of Non-Communicable Disease Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine, Cancer Survival GroupAbstract Background In population-based cancer research, piecewise exponential regression models are used to derive adjusted estimates of excess mortality due to cancer using the Poisson generalized linear modelling framework. However, the assumption that the conditional mean and variance of the rate parameter given the set of covariates x i are equal is strong and may fail to account for overdispersion given the variability of the rate parameter (the variance exceeds the mean). Using an empirical example, we aimed to describe simple methods to test and correct for overdispersion. Methods We used a regression-based score test for overdispersion under the relative survival framework and proposed different approaches to correct for overdispersion including a quasi-likelihood, robust standard errors estimation, negative binomial regression and flexible piecewise modelling. Results All piecewise exponential regression models showed the presence of significant inherent overdispersion (p-value <0.001). However, the flexible piecewise exponential model showed the smallest overdispersion parameter (3.2 versus 21.3) for non-flexible piecewise exponential models. Conclusion We showed that there were no major differences between methods. However, using a flexible piecewise regression modelling, with either a quasi-likelihood or robust standard errors, was the best approach as it deals with both, overdispersion due to model misspecification and true or inherent overdispersion.http://link.springer.com/article/10.1186/s12874-016-0234-zEpidemiologic methodsRegression analysisSurvival analysisProportional hazard modelsCancer |
| spellingShingle | Miguel Angel Luque-Fernandez Aurélien Belot Manuela Quaresma Camille Maringe Michel P. Coleman Bernard Rachet Adjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population-based research BMC Medical Research Methodology Epidemiologic methods Regression analysis Survival analysis Proportional hazard models Cancer |
| title | Adjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population-based research |
| title_full | Adjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population-based research |
| title_fullStr | Adjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population-based research |
| title_full_unstemmed | Adjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population-based research |
| title_short | Adjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population-based research |
| title_sort | adjusting for overdispersion in piecewise exponential regression models to estimate excess mortality rate in population based research |
| topic | Epidemiologic methods Regression analysis Survival analysis Proportional hazard models Cancer |
| url | http://link.springer.com/article/10.1186/s12874-016-0234-z |
| work_keys_str_mv | AT miguelangelluquefernandez adjustingforoverdispersioninpiecewiseexponentialregressionmodelstoestimateexcessmortalityrateinpopulationbasedresearch AT aurelienbelot adjustingforoverdispersioninpiecewiseexponentialregressionmodelstoestimateexcessmortalityrateinpopulationbasedresearch AT manuelaquaresma adjustingforoverdispersioninpiecewiseexponentialregressionmodelstoestimateexcessmortalityrateinpopulationbasedresearch AT camillemaringe adjustingforoverdispersioninpiecewiseexponentialregressionmodelstoestimateexcessmortalityrateinpopulationbasedresearch AT michelpcoleman adjustingforoverdispersioninpiecewiseexponentialregressionmodelstoestimateexcessmortalityrateinpopulationbasedresearch AT bernardrachet adjustingforoverdispersioninpiecewiseexponentialregressionmodelstoestimateexcessmortalityrateinpopulationbasedresearch |