Parameter Estimation Problem Based On Multiple Strategies Cognitive Diagnosis Of DINA Model

Cognitive diagnosis and evaluation in the field of psychology and education evaluation is an important field in the rapid development of modern measurement theory.The main purpose of cognitive diagnosis evaluation is to measure the specific knowledge state and processing skills of the subjects,so as to provide the relevant information of the cognitive strength and the weakness of the subjects.Cognitive diagnosis models（CDMS）,as alternative approaches to unidimensional item response models,have received increasing attention in recent years.CDMS are developed for the purpose of identifying the mastery or nonmastery of multiple fine-grained attributes or skills required for solving problems in a domain.For CDMS to receive wider use,researchers and practitioners need to understand the basic properties of these models.In the current literature,the commonly used models usually involve silps parameterss_j,guesses parametersg_j and capability parameters λ_0k,λ_1k,but generally,the parameters are given directly,only the slips parameters and the guesses parameters are estimated,and the estimation is not simultaneously estimated.But we know that in reality,the parameters are unknown frequently,in order to solve this problem,this paper establishes a cognitive diagnostic model—multiple strategies DINA（MS-DINA）model,which can be evaluated the parameters ofs_j,g_j,λ_0k,λ_1ksimultaneously,which is easy to process and interpret.The MS-DINA model was used to analyze the project cognitive attributes of subjects.The attribute joint distribution is generic to simulate the MS-DINA model.This paper focuses on the estimation of MS-DINA model and its parameters.An effective EM estimation algorithm is adopted to simulate the effect of sample size and test length on MS-DINA model fitting,and the parameters of MS-DINA model are estimated.We give the algorithm estimation process,and give the corresponding simulation.The simulation shows that our estimation has good statistical properties.