作者: Karl G. Jöreskog
DOI: 10.1002/J.2333-8504.1970.TB00783.X
关键词: Residual 、 Applied mathematics 、 General method 、 Analysis of covariance 、 Errors-in-variables models 、 Mathematical model 、 Observational error 、 Goodness of fit 、 Statistics 、 Heteroscedasticity-consistent standard errors 、 Mathematics
摘要: A general method for estimating the unknown coefficients in a set of linear structural equations is described. In its most form allows both errors (residuals, disturbances) and variables (errors measurement, observational errors) yields estimates residual variance-covariance matrix measurement error variances as well equations, provided all these parameters are identified. Two special cases this discussed separately. One when there but no variables. The other equations. methods applied illustrated using artificial, economic psychological data.