Limits...
Statistical models for the analysis of skewed healthcare cost data: a simulation study.

Malehi AS, Pourmotahari F, Angali KA - Health Econ Rev (2015)

Bottom Line: We found that there was not one best model across all generated conditions.The results showed that the Cox proportional hazard model exhibited a poor estimation of population means of healthcare costs and the β1 even under proportional hazard data.Approximately results are consistent by increasing the sample size.

View Article: PubMed Central - PubMed

Affiliation: Department of Biostatistics and Epidemiology, School of Public Health, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran.

ABSTRACT
Skewed data is the main issue in statistical models in healthcare costs. Data transformation is a conventional method to decrease skewness, but there are some disadvantages. Some recent studies have employed generalized linear models (GLMs) and Cox proportional hazard regression as alternative estimators. The aim of this study was to investigate how well these alternative estimators perform in terms of bias and precision when the data are skewed. The primary outcome was an estimation of population means of healthcare costs and the secondary outcome was the impact of a covariate on healthcare cost. Alternative estimators, such as ordinary least squares (OLS) for Ln(y) or Log(y), Gamma, Weibull and Cox proportional hazard regression models, were compared using Monte Carlo simulation under different situations, which were generated from skewed distributions. We found that there was not one best model across all generated conditions. However, GLMs, especially the Gamma regression model, behaved well in the estimation of population means of healthcare costs. The results showed that the Cox proportional hazard model exhibited a poor estimation of population means of healthcare costs and the β1 even under proportional hazard data. Approximately results are consistent by increasing the sample size. However, increasing the sample size could improve the performance of the OLS-based model.

No MeSH data available.


Related in: MedlinePlus

Mean residual from different estimators across deciles of ‘X’ for Gamma data (n=25) with shape parameter a: 0.5, b: 1, c: 2, d: 4.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4442782&req=5

Fig2: Mean residual from different estimators across deciles of ‘X’ for Gamma data (n=25) with shape parameter a: 0.5, b: 1, c: 2, d: 4.

Mentions: Comparison goodness of fit tests (Hosmer-Lemeshow test and AIC criterion) revealed that, under a different range of data conditions, Gamma and Weibull regression models were better behaved. Finally, investigation of the pattern of the residuals as a function of X, which have been implemented by the mean of the residuals across deciles of X, showed more bias for the Cox proportional hazard model across all generated data and sample sizes (see Figures 2-15).


Statistical models for the analysis of skewed healthcare cost data: a simulation study.

Malehi AS, Pourmotahari F, Angali KA - Health Econ Rev (2015)

Mean residual from different estimators across deciles of ‘X’ for Gamma data (n=25) with shape parameter a: 0.5, b: 1, c: 2, d: 4.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4442782&req=5

Fig2: Mean residual from different estimators across deciles of ‘X’ for Gamma data (n=25) with shape parameter a: 0.5, b: 1, c: 2, d: 4.
Mentions: Comparison goodness of fit tests (Hosmer-Lemeshow test and AIC criterion) revealed that, under a different range of data conditions, Gamma and Weibull regression models were better behaved. Finally, investigation of the pattern of the residuals as a function of X, which have been implemented by the mean of the residuals across deciles of X, showed more bias for the Cox proportional hazard model across all generated data and sample sizes (see Figures 2-15).

Bottom Line: We found that there was not one best model across all generated conditions.The results showed that the Cox proportional hazard model exhibited a poor estimation of population means of healthcare costs and the β1 even under proportional hazard data.Approximately results are consistent by increasing the sample size.

View Article: PubMed Central - PubMed

Affiliation: Department of Biostatistics and Epidemiology, School of Public Health, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran.

ABSTRACT
Skewed data is the main issue in statistical models in healthcare costs. Data transformation is a conventional method to decrease skewness, but there are some disadvantages. Some recent studies have employed generalized linear models (GLMs) and Cox proportional hazard regression as alternative estimators. The aim of this study was to investigate how well these alternative estimators perform in terms of bias and precision when the data are skewed. The primary outcome was an estimation of population means of healthcare costs and the secondary outcome was the impact of a covariate on healthcare cost. Alternative estimators, such as ordinary least squares (OLS) for Ln(y) or Log(y), Gamma, Weibull and Cox proportional hazard regression models, were compared using Monte Carlo simulation under different situations, which were generated from skewed distributions. We found that there was not one best model across all generated conditions. However, GLMs, especially the Gamma regression model, behaved well in the estimation of population means of healthcare costs. The results showed that the Cox proportional hazard model exhibited a poor estimation of population means of healthcare costs and the β1 even under proportional hazard data. Approximately results are consistent by increasing the sample size. However, increasing the sample size could improve the performance of the OLS-based model.

No MeSH data available.


Related in: MedlinePlus