We focus on in this paper the convergence rate of the L-N estimators for the fixed effect β in Poisson-Gamma models which are typical hierarchical generalised linear models（HGLMs）. Under the proper assumptions on r...We focus on in this paper the convergence rate of the L-N estimators for the fixed effect β in Poisson-Gamma models which are typical hierarchical generalised linear models（HGLMs）. Under the proper assumptions on response variables and some smoothing conditions, we obtain the strong consistency and the convergence rate of the L-N estimator based on the combination of L-N and quasi-likelihood.展开更多
Changsha was one of the most affected areas during the 2009 A(H1N1)influenza pandemic in China.Here,we analyze the spatial–temporal dynamics of the 2009 pandemic across Changsha municipal districts,evaluate the relat...Changsha was one of the most affected areas during the 2009 A(H1N1)influenza pandemic in China.Here,we analyze the spatial–temporal dynamics of the 2009 pandemic across Changsha municipal districts,evaluate the relationship between case incidence and the local urban spatial structure and predict high-risk areas of influenza A(H1N1).We obtained epidemiological data on all cases of influenza A(H1N1)reported across municipal districts in Changsha during period May 2009–December 2010 and data on population density and basic geographic characteristics for 239 primary schools,97 middle schools,347 universities,96 malls and markets,674 business districts and 121 hospitals.Spatial–temporal K functions,proximity models and logistic regression were used to analyze the spatial distribution pattern of influenza A(H1N1)incidence and the association between influenza A(H1N1)cases and spatial risk factors and predict the infection risks.We found that the 2009 influenza A(H1N1)was driven by a transmission wave from the center of the study area to surrounding areas and reported cases increased significantly after September 2009.We also found that the distribution of influenza A(H1N1)cases was associated with population density and the presence of nearest public places,especially universities(OR=10.166).The final predictive risk map based on the multivariate logistic analysis showed high-risk areas concentrated in the center areas of the study area associated with high population density.Our findings support the identification of spatial risk factors and highrisk areas to guide the prioritization of preventive and mitigation efforts against future influenza pandemics.展开更多
基金Supported by the National Natural Science Foundation of China(10371005)Scientific Research Funds of the Excellent Young Teachers Program of the Ministry of Education China(VE00074)
文摘We focus on in this paper the convergence rate of the L-N estimators for the fixed effect β in Poisson-Gamma models which are typical hierarchical generalised linear models（HGLMs）. Under the proper assumptions on response variables and some smoothing conditions, we obtain the strong consistency and the convergence rate of the L-N estimator based on the combination of L-N and quasi-likelihood.
基金supported by the Key Discipline Construction Project in Hunan Province(2008001)the National Natural Science Foundation of China and the Scientific Research Fund of Hunan Provincial Education Department(13A051)
文摘Changsha was one of the most affected areas during the 2009 A(H1N1)influenza pandemic in China.Here,we analyze the spatial–temporal dynamics of the 2009 pandemic across Changsha municipal districts,evaluate the relationship between case incidence and the local urban spatial structure and predict high-risk areas of influenza A(H1N1).We obtained epidemiological data on all cases of influenza A(H1N1)reported across municipal districts in Changsha during period May 2009–December 2010 and data on population density and basic geographic characteristics for 239 primary schools,97 middle schools,347 universities,96 malls and markets,674 business districts and 121 hospitals.Spatial–temporal K functions,proximity models and logistic regression were used to analyze the spatial distribution pattern of influenza A(H1N1)incidence and the association between influenza A(H1N1)cases and spatial risk factors and predict the infection risks.We found that the 2009 influenza A(H1N1)was driven by a transmission wave from the center of the study area to surrounding areas and reported cases increased significantly after September 2009.We also found that the distribution of influenza A(H1N1)cases was associated with population density and the presence of nearest public places,especially universities(OR=10.166).The final predictive risk map based on the multivariate logistic analysis showed high-risk areas concentrated in the center areas of the study area associated with high population density.Our findings support the identification of spatial risk factors and highrisk areas to guide the prioritization of preventive and mitigation efforts against future influenza pandemics.
