Latent variable structural models and the partial least-squares (PLS) estimation procedure have found increased interest since being used in the context of customer satisfaction measurement. The well-known property that the estimates of the inner structure model are inconsistent implies biased estimates for finite sample sizes. A simplified version of the structural model that is used for the Swedish Customer Satisfaction Index (SCSI) system has been used to generate simulated data and to study the PLS algorithm in the presence of three inadequacies: (i) skew instead of symmetric distributions for manifest variables; (ii) multi-collinearity within blocks of manifest and between latent variables; and (iii) misspecification of the structural model (omission of regressors). The simulation results show that the PLS method is quite robust against these inadequacies. The bias that is caused by the inconsistency of PLS estimates is substantially increased only for extremely skewed distributions and for the erroneous omission of a highly relevant latent regressor variable. The estimated scores of the latent variables are always in very good agreement with the true values and seem to be unaffected by the inadequacies under investigation.
JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.. Biometrika Trust is collaborating with JSTOR to digitize, preserve and extend access to Biometrika. SUMMARY A superpopulation model is formulated under which the generalized difference estimator is optimal in an expected variance sense. The result is applied in the situation where an auxiliary variable is available and linear regression through the origin is assumed. A generalized regression estimator is proposed and shown to be better than a range of traditional competitors.
In previous research (e.g. Cassel et al., 1999, Journal of Applied Statistics, 26, pp. 435-446; Cassel et al., 2000, Total Quality Management, 11, pp. 897-907) the bias and precision effects, for various speczjication problems, on the structural analysis and measurement of customer perceptions have been studied. In this paper the combined effects of some of the most significant problems, misspecijications and skew response distributions, and certain types of measurement errors, are studied. The measurement errors considered reflect the bias due to the inertia of respondents in adapting to changes. In the situation of repeated measurements, the later response tends to be biased towards the former response. This effect can be modelled by implementing certain change filtering assumptions. A simulation study using the European Performance Satisfaction Index (EPSI) structure demonstrates that the EPSI measurement methodology using partial least squares is very robust with respect to the problems introduced in the simulations. This is true, in particular, when estimating the inner structure of the model and when estimating the outer measurement relations of the model. The estimated values of the the latent variables (such as the customer satisfaction index) are affected in an expected way.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.