We provide a detailed review for the statistical analysis of diagnostic accuracy in a multi-category classification task.For qualitative response variables with more than two categories,many traditional accuracy measu...We provide a detailed review for the statistical analysis of diagnostic accuracy in a multi-category classification task.For qualitative response variables with more than two categories,many traditional accuracy measures such as sensitivity,specificity and area under the ROC curve are no longer applicable.In recent literature,new diagnostic accuracy measures are introduced in medical research studies.In this paper,important statistical concepts for multi-category classification accuracy are reviewed and their utilities are demonstrated with real medical examples.We offer problem-based R code to illustrate how to perform these statistical computations step by step.We expect such analysis tools will become more familiar to practitioners and receive broader applications in biostatistics.Our program can be adapted to many classifiers among which logistic regression may be the most popular approach.We thus base our discussion and illustration completely on the logistic regression in this paper.展开更多
Based on the household livelihood endowment theory and the survey of 367 farmer households in Anhui,Hubei,and Sichuan in 2016,and using the orderly multi-category logistic model,the behavioral decision of farmers in t...Based on the household livelihood endowment theory and the survey of 367 farmer households in Anhui,Hubei,and Sichuan in 2016,and using the orderly multi-category logistic model,the behavioral decision of farmers in the land circulation was discussed to explore the key parameters influencing the land transfer-out. It found that decisions of farmers on land transfer-out behavior are affected by many factors.Specifically,household non-agricultural income and per capita land area significantly reduce farmers' willingness to transfer land,while the household head age,agricultural input-output ratio,and confirmation of land right significantly promote the farmers' decision on land transferout. Therefore,increasing the allocation efficiency of household livelihood endowment has important policy value and practical significance for eliminating unreasonable land circulation and promoting large-scale agricultural production.展开更多
When there is substantial heterogeneity of treatment effectiveness for comparative treatmentselection, it is crucial to identify individualised treatment rules for patients who have heterogeneous responses to treatmen...When there is substantial heterogeneity of treatment effectiveness for comparative treatmentselection, it is crucial to identify individualised treatment rules for patients who have heterogeneous responses to treatment. Existing approaches include directly modelling clinical outcomeby defining the optimal treatment rule according to the interactions between treatment andcovariates and outcome weighted approach that uses clinical outcome as weights to maximise atarget function whose value directly reflects correct treatment assignment. All existing articles ofestimating individualised treatment rules are all assuming just two treatment assignments. Herewe propose an outcome weighted learning approach that uses a vector hinge loss to extend estimating individualised treatment rules in multi-category treatments case. The consistency of theresulting estimator is shown. We also demonstrate the performance of our approach in simulationstudies and a real data analysis.展开更多
基金Li’s work was partially supported by National Medical Research Council in Singapore and AcRF R-155-000-174-114.NNSF[grant number 11371142].
文摘We provide a detailed review for the statistical analysis of diagnostic accuracy in a multi-category classification task.For qualitative response variables with more than two categories,many traditional accuracy measures such as sensitivity,specificity and area under the ROC curve are no longer applicable.In recent literature,new diagnostic accuracy measures are introduced in medical research studies.In this paper,important statistical concepts for multi-category classification accuracy are reviewed and their utilities are demonstrated with real medical examples.We offer problem-based R code to illustrate how to perform these statistical computations step by step.We expect such analysis tools will become more familiar to practitioners and receive broader applications in biostatistics.Our program can be adapted to many classifiers among which logistic regression may be the most popular approach.We thus base our discussion and illustration completely on the logistic regression in this paper.
文摘Based on the household livelihood endowment theory and the survey of 367 farmer households in Anhui,Hubei,and Sichuan in 2016,and using the orderly multi-category logistic model,the behavioral decision of farmers in the land circulation was discussed to explore the key parameters influencing the land transfer-out. It found that decisions of farmers on land transfer-out behavior are affected by many factors.Specifically,household non-agricultural income and per capita land area significantly reduce farmers' willingness to transfer land,while the household head age,agricultural input-output ratio,and confirmation of land right significantly promote the farmers' decision on land transferout. Therefore,increasing the allocation efficiency of household livelihood endowment has important policy value and practical significance for eliminating unreasonable land circulation and promoting large-scale agricultural production.
基金The author would like to thank Jun Shao and Menggang Yu for their help with preparing the manuscript.This work was supported by the Chinese 111 Project[grant number B14019](for Lou and Shao).
文摘When there is substantial heterogeneity of treatment effectiveness for comparative treatmentselection, it is crucial to identify individualised treatment rules for patients who have heterogeneous responses to treatment. Existing approaches include directly modelling clinical outcomeby defining the optimal treatment rule according to the interactions between treatment andcovariates and outcome weighted approach that uses clinical outcome as weights to maximise atarget function whose value directly reflects correct treatment assignment. All existing articles ofestimating individualised treatment rules are all assuming just two treatment assignments. Herewe propose an outcome weighted learning approach that uses a vector hinge loss to extend estimating individualised treatment rules in multi-category treatments case. The consistency of theresulting estimator is shown. We also demonstrate the performance of our approach in simulationstudies and a real data analysis.
