Rezaei Ghahroodi Zahra, Ganjali Mojtaba
Associate Professor of Statistics, School of Mathematics, Statistics and Computer Science, University of Tehran, Tehran, Iran.
Professor of Statistics, Department of Statistics, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran.
Expert Rev Pharmacoecon Outcomes Res. 2021 Oct;21(5):953-966. doi: 10.1080/14737167.2021.1857242. Epub 2021 Jan 6.
: The aim of the study was to investigate the effects of some covariates on different quantiles of the cost of hospitalization. The effect of the province that the individual belongs to on these quantiles will be also examined.: We employed a linear quantile-mixed model (LQMM) for analyzing the cost of hospitalization in Iranians Utilization of Health Services (IUHS) survey considering the province effect, the effects of some important covariates, and also the effect of the choice of the random-effects distribution. For this, both classical and Bayesian approaches are used for parameter estimation.: The results of data analysis show that ward, type of hospital, and duration of hospitalization are significant factors on quantiles of the cost of hospitalization, of course with different impacts on different quantiles. Our findings reveal significant discrepancies in the cost of hospitalization in different provinces and significant heterogeneity among provinces.: More works must be done related to hospitalization cost and its consequences since it is a matter of social life. To be exact, one should notice that provinces with hospitals involving high hospitalization costs may have households dealing with poverty.
本研究的目的是调查一些协变量对住院费用不同分位数的影响。还将考察个人所属省份对这些分位数的影响。
我们采用线性分位数混合模型(LQMM)来分析伊朗人卫生服务利用(IUHS)调查中的住院费用,同时考虑省份效应、一些重要协变量的效应以及随机效应分布选择的影响。为此,参数估计采用经典方法和贝叶斯方法。
数据分析结果表明,病房、医院类型和住院时长是住院费用分位数的显著影响因素,当然对不同分位数的影响不同。我们的研究结果揭示了不同省份住院费用存在显著差异,且省份之间存在显著异质性。
由于住院费用及其影响涉及社会生活问题,因此必须开展更多与住院费用及其后果相关的工作。确切地说,应该注意到那些医院住院费用高的省份可能有家庭面临贫困问题。