ABSTRACT
OBJ ECTIVE To introduce adjusted limited dependent variable mixed model （ALDVMM）and study its application in mapping research ，so as to provide reference for pharmacoeconomic evaluation that needs to obtain health utility value through mapping. METHODS Using the method of literature research ，ALDVMM was introduced from the aspects of development background，model principle ，model determination and test ，model advantages and the current application of the model in empirical research. RESULTS & CONCLUSIONS ALDVMM is a mixed model developed by foreign scholars for the truncation and multimodality phenomenon of EuroQoL group ’s 5D（EQ-5D）at the health utility value 1. Compared with the traditional model，ALDVMM is feasible and has more advantages ，and can more effectively and flexibly capture the actual distribution of EQ-5D and deal with the boundary value problem ，which is helpful to obtain the health utility value more accurately and efficiently and carry out high-quality pharmacoeconomic evaluation.
ABSTRACT
OBJECTIVE：To know about the research status of health utility value obtained by mapping method in pharmacoeconomic evaluation ，and to provide reference for bibliometric study in pharmacoeconomic evaluation . METHODS ： Using“Mapping method ”“Health utility value ”“Cost-utility”“Utility point system ”as Chinese and English keywords ，retrieved from CNKI ，Wanfang database ，PubMed，Medline，Ebsco，Ovid and Wiley database ，empirical journal documents published from the inception to Dec. 31st，2018 about using mapping method to obtain health utility value were collected. The bibliometrics was used to statistically analyze basic information of included literature ，the construction and test of the model ，the type of the best model and so on. RESULTS ：The 124 included documents were all published in English journal. In the construction and testing of the mapping model ，the most frequently used econometric methods ，performance evaluation indicators and model testing methods were ordinary least squares （OLS），mean absolute error （MAE）and residual normality test ，application frequency of which were 97 times（31.60％），89 times（24.93％）and 62 times（21.09％）. There are 117 articles that define the best mapping model ，of which 101 articles（86.32％）have the best direct mapping effect. Most of the non-utility measurement scales adopted specific scales （92 articles，77.97％），and a few literatures adopted the universal scale （26 articles，22.03％）. The most utility measurement scales were 3-level European 5-dimensional health scale （79 articles，66.95％）. CONCLUSIONS ：The domestic empirical researches that use the mapping method to obtain health utility values need to be developed yet. A series of mapping models successfully developed by foreign scholars not only provide the feasibility of using non-utility measurement scales for cost-utility analysis ，but also provide more ideas for China to choose the corresponding econometric methods ，evaluation indicators and mapping methods in the empirical research of the mapping method in the future.
ABSTRACT
OBJECTIVE:To provide methodological reference for converting non-utility scale measurement results into health utility values. METHODS:Referring to domestic and foreign literatures,mapping methods and relevant models in health utility measurement were summarized. The effect of each model on probability mapping was introduced by taking the Medical outcomes study 12-item short form health survey measurement results converting into the EuroQol group's 5-domain utility values as exam-ple.RESULTS:The mapping methods can be adopted to obtain the health utility values by establishing the mapping relationship be-tween non-utility scale and utility scale. The common models included ordinary least square(OLS)model,censored least absolute deviations(CLAD)model,Tobit model,multinomial Logistic regression(MNL)model,Bayesian networks(BN)model,etc. OLS model was relatively simple with a good predictive validity,but it would be limited by the ceiling effect;Tobit model was not limit-ed by the ceiling or floor effect,when the error term satisfied the variance homogeneity and normality,prediction result of Tobit model was better than OLS model;CLAD model can be used for the situation of Tobit model unsuitable for non-variance homoge-neity of the error term;MNL model firstly determined a health state by regression analysis and then determined its utility value;the prediction validity of BN model was good and it didn't involved many assumptions and restrictions condition in econometrics, but the construction of BN model was greatly influenced by domain experts. Main methods for the calculation of health utility value with MNL or BN model were Monte Carlo simulation method,expected-utility method,most-likely probability methed,etc. We can carry out the model performance evaluation by using the R2,the adjusted R2,the mean error,the mean squared error and the mean absolute error,and then select the optimal model to calculate health utility values. CONCLUSIONS:Due to the advantages and disadvantages of each mapping model,it is necessary to select different mapping models based on the actual conditions.
ABSTRACT
OBJECTIVE:To provide methodological reference for converting non-utility scale measurement results into health utility values. METHODS:Referring to domestic and foreign literatures,mapping methods and relevant models in health utility measurement were summarized. The effect of each model on probability mapping was introduced by taking the Medical outcomes study 12-item short form health survey measurement results converting into the EuroQol group's 5-domain utility values as exam-ple.RESULTS:The mapping methods can be adopted to obtain the health utility values by establishing the mapping relationship be-tween non-utility scale and utility scale. The common models included ordinary least square(OLS)model,censored least absolute deviations(CLAD)model,Tobit model,multinomial Logistic regression(MNL)model,Bayesian networks(BN)model,etc. OLS model was relatively simple with a good predictive validity,but it would be limited by the ceiling effect;Tobit model was not limit-ed by the ceiling or floor effect,when the error term satisfied the variance homogeneity and normality,prediction result of Tobit model was better than OLS model;CLAD model can be used for the situation of Tobit model unsuitable for non-variance homoge-neity of the error term;MNL model firstly determined a health state by regression analysis and then determined its utility value;the prediction validity of BN model was good and it didn't involved many assumptions and restrictions condition in econometrics, but the construction of BN model was greatly influenced by domain experts. Main methods for the calculation of health utility value with MNL or BN model were Monte Carlo simulation method,expected-utility method,most-likely probability methed,etc. We can carry out the model performance evaluation by using the R2,the adjusted R2,the mean error,the mean squared error and the mean absolute error,and then select the optimal model to calculate health utility values. CONCLUSIONS:Due to the advantages and disadvantages of each mapping model,it is necessary to select different mapping models based on the actual conditions.