Font Size: a A A

Algorithm Of Structural Equation Model And Its Appliance In Insurance Performance

Posted on:2010-12-06Degree:MasterType:Thesis
Country:ChinaCandidate:H PengFull Text:PDF
GTID:2189360272471226Subject:Applied Mathematics
Abstract/Summary:PDF Full Text Request
Structural equation model(SEM) is one of the multi-dimensional statistical analysis methods based on path diagram. In 21st century, it's necessary to have some develop in SEM to suit the economy increase. Due to the spreading of computer technology, algorithm problem of SEM has been solved. It's greatly promoting the application of SEM. Insurance is a newly developed industry in China, which needs appropriate model to carry on the appraisal analysis.Firstly, this paper introduces the theory and algorithm of structural equation model. By adding a constraint with modular length to the structural variables, we obtain the constraint least square solution with modular length parameters (MCLS) for observation equations. Further more we can use our MCLS as the initial value in PLS iterative progress to improve its convergence. Secondly, it is reasonable to change the modular lengths of observation variables so that the path coefficients between the structure variable and its observation variables satisfy prescription conditions. This prescription conditions can guarantee the homogeneity of a structure variable with its observation variables. Our algorithm is a determinate algorithm with the least square of errors and prescription conditions for the path coefficients, although SEM is indeterminate equations. Thirdly, this kind of structural equation model and the algorithm have been extended to multilayer model. Then, multi-group SEM has been investigated and united by generalized linear model with convex constraint. Lastly, we introduces the indexes of insurance appraisement in different areas. Meanwhile, an index system has been proposed under some principles. Most important is that we have applied SEM in insurance appraisement with the index proposed by us.Totally speaking, the innovations of this paper can be showed in four aspects:(1) Find the PLS iteration initial value under the unit vector restraint, enhances the PLS convergence rate, explains the PLS iteration convergence.(2) Propose determinate algorithm of SEM with the least square of errors and prescription conditions.(3) Construct multilayer and multi-group SEM, solve their computation problem.(4) Appraise the insurance performance by SEM with PLS iteration initial value which is a new method in insurance appraising.
Keywords/Search Tags:structural equation model (SEM), partial least square (PLS), determinate algorithm, insurance performance
PDF Full Text Request
Related items