摘要
异质性数据存在于许多领域中,例如心理学、环境科学。混合模型广泛用于探索异质性数据。本文提出了一种混合因子模型,它在探索异质性数据的过程中,可同时考虑引起的数据异质性的潜在因素和可观测到的影响因素。通过模拟研究,体现了基于该模型的两步法参数估计的有效性。同时将这些混合因子模型应用于城市空气质量的评价问题中,研究了空气污染物与气象因子之间的关系。
Heterogeneous data exist in many fields,such as psychology and environmental science.Mixture models are widely used to explore population heterogeneity.In this paper,we propose a mixture factor model to explore heterogeneous data,which simultaneously considers latent and observed sources that may induce the heterogeneity.A two-step estimation procedure is developed for the model and its effectiveness is illustrated by various simulation studies.We also apply these mixture factor models to the quality assessment of city air and study the relationship between environmental pollutants and meteorological factors.
作者
侯春羽
袁超凤
马维军
HOU Chunyu;YUAN Chaofeng;MA Weijun(School of Mathematical Sciences,Heilongjiang University,Harbin 150080,China)
出处
《黑龙江大学自然科学学报》
CAS
2019年第5期519-528,共10页
Journal of Natural Science of Heilongjiang University
基金
Supported by the Fundamental Fund for Universities in Heilongjiang Province(KJCX201802)
关键词
空气质量评价
气象因子
混合因子模型
潜在因子
air quality assessment
meteorological factors
mixture factor models
latent factors
