Multiply robust inference has attracted much attention recently in the context of missing response data. An estimation procedure is multiply robust, if it can incorporate information from multiple candidate models, an...Multiply robust inference has attracted much attention recently in the context of missing response data. An estimation procedure is multiply robust, if it can incorporate information from multiple candidate models, and meanwhile the resulting estimator is consistent as long as one of the candidate models is correctly specified. This property is appealing, since it provides the user a flexible modeling strategy with better protection against model misspecification. We explore this attractive property for the regression models with a binary covariate that is missing at random. We start from a reformulation of the celebrated augmented inverse probability weighted estimating equation, and based on this reformulation, we propose a novel combination of the least squares and empirical likelihood to separately handle each of the two types of multiple candidate models,one for the missing variable regression and the other for the missingness mechanism. Due to the separation, all the working models are fused concisely and effectively. The asymptotic normality of our estimator is established through the theory of estimating function with plugged-in nuisance parameter estimates. The finite-sample performance of our procedure is illustrated both through the simulation studies and the analysis of a dementia data collected by the national Alzheimer's coordinating center.展开更多
Multiply robust inference has attracted much attention recently in the context of missing response data. An estimation procedure is multiply robust, if it can incorporate information from multiple candidate models, an...Multiply robust inference has attracted much attention recently in the context of missing response data. An estimation procedure is multiply robust, if it can incorporate information from multiple candidate models, and meanwhile the resulting estimator is consistent as long as one of the candidate models is correctly specified. This property is appealing, since it provides the user a flexible modeling strategy with better protection against model misspecification. We explore this attractive property for the regression models with a binary covariate that is missing at random. We start from a reformulation of the celebrated augmented inverse probability weighted estimating equation, and based on this reformulation, we propose a novel combination of the least squares and empirical likelihood to separately handle each of the two types of multiple candidate models,one for the missing variable regression and the other for the missingness mechanism. Due to the separation, all the working models are fused concisely and effectively. The asymptotic normality of our estimator is established through the theory of estimating function with plugged-in nuisance parameter estimates. The finite-sample performance of our procedure is illustrated both through the simulation studies and the analysis of a dementia data collected by the national Alzheimer's coordinating center.展开更多
Compared with organic solar cells(OSCs) adopting conventional architecture,inverted OSCs have offered generally better stability,where Zn O is the most widely used electron transporting layer(ETL) material.For ZnO-bas...Compared with organic solar cells(OSCs) adopting conventional architecture,inverted OSCs have offered generally better stability,where Zn O is the most widely used electron transporting layer(ETL) material.For ZnO-based inverted OSCs,a welltuned interface of organic(active layer)-inorganic(Zn O film) with matched surface energy(γS) is critical for both high performance and high stability.In this work,two typical calixarenes,C4A and Bu C4A,were employed as the tuning agents to adjust this organic-inorganic interface for ZnO-based inverted OSCs.As a result,with PM6:L8-BO as the active layer,significantly promoted power conversion efficiencies(PCEs) from 17.14%(for ZnO) to 18.25%(for ZnO/C4A) and 17.80%(for ZnO/Bu C4A) were achieved.Photodynamic studies indicate that the enhanced performance is due to the faster charge extraction process,the suppressed recombination and more ideal internal electric field in ZnO/calixarene-based devices.In addition,wellmatched interface energy and more ordered molecular aggregation in active layer effectively improved photostability and thermal stability for ZnO/calixarene-based devices.These results indicate that calixarenes could act as effective modifying agents of ZnO to improve inverted OSCs’ performance and stability simultaneously,and likely also stimulate calixarenes’ and other macromolecules’ broader studies in other organic electronic devices.展开更多
文摘Multiply robust inference has attracted much attention recently in the context of missing response data. An estimation procedure is multiply robust, if it can incorporate information from multiple candidate models, and meanwhile the resulting estimator is consistent as long as one of the candidate models is correctly specified. This property is appealing, since it provides the user a flexible modeling strategy with better protection against model misspecification. We explore this attractive property for the regression models with a binary covariate that is missing at random. We start from a reformulation of the celebrated augmented inverse probability weighted estimating equation, and based on this reformulation, we propose a novel combination of the least squares and empirical likelihood to separately handle each of the two types of multiple candidate models,one for the missing variable regression and the other for the missingness mechanism. Due to the separation, all the working models are fused concisely and effectively. The asymptotic normality of our estimator is established through the theory of estimating function with plugged-in nuisance parameter estimates. The finite-sample performance of our procedure is illustrated both through the simulation studies and the analysis of a dementia data collected by the national Alzheimer's coordinating center.
基金supported by National Natural Science Foundation of China(Grant No.11301031)
文摘Multiply robust inference has attracted much attention recently in the context of missing response data. An estimation procedure is multiply robust, if it can incorporate information from multiple candidate models, and meanwhile the resulting estimator is consistent as long as one of the candidate models is correctly specified. This property is appealing, since it provides the user a flexible modeling strategy with better protection against model misspecification. We explore this attractive property for the regression models with a binary covariate that is missing at random. We start from a reformulation of the celebrated augmented inverse probability weighted estimating equation, and based on this reformulation, we propose a novel combination of the least squares and empirical likelihood to separately handle each of the two types of multiple candidate models,one for the missing variable regression and the other for the missingness mechanism. Due to the separation, all the working models are fused concisely and effectively. The asymptotic normality of our estimator is established through the theory of estimating function with plugged-in nuisance parameter estimates. The finite-sample performance of our procedure is illustrated both through the simulation studies and the analysis of a dementia data collected by the national Alzheimer's coordinating center.
基金supported by the Ministry of Science and Technology of China(MoST,2019YFA0705900)the National Natural Science Foundation of China(21935007,52025033,51873089)+1 种基金Tianjin city(20JCZDJC00740)111 Project(B12015)。
文摘Compared with organic solar cells(OSCs) adopting conventional architecture,inverted OSCs have offered generally better stability,where Zn O is the most widely used electron transporting layer(ETL) material.For ZnO-based inverted OSCs,a welltuned interface of organic(active layer)-inorganic(Zn O film) with matched surface energy(γS) is critical for both high performance and high stability.In this work,two typical calixarenes,C4A and Bu C4A,were employed as the tuning agents to adjust this organic-inorganic interface for ZnO-based inverted OSCs.As a result,with PM6:L8-BO as the active layer,significantly promoted power conversion efficiencies(PCEs) from 17.14%(for ZnO) to 18.25%(for ZnO/C4A) and 17.80%(for ZnO/Bu C4A) were achieved.Photodynamic studies indicate that the enhanced performance is due to the faster charge extraction process,the suppressed recombination and more ideal internal electric field in ZnO/calixarene-based devices.In addition,wellmatched interface energy and more ordered molecular aggregation in active layer effectively improved photostability and thermal stability for ZnO/calixarene-based devices.These results indicate that calixarenes could act as effective modifying agents of ZnO to improve inverted OSCs’ performance and stability simultaneously,and likely also stimulate calixarenes’ and other macromolecules’ broader studies in other organic electronic devices.
