This is a review of a range of empirical studies that use digital text algorithms to predict and model response patterns from humans to Likert-scale items, using texts only as inputs. The studies show that statistics used in construct validation is predictable on sample and individual levels, that this happens across languages and cultures, and that the relationship between variables are often semantic instead of empirical. That is, the relationships among variables are given a priori and evidently computable as such. We explain this by replacing the idea of “nomological networks” with “semantic networks” to designate computable relationships between abstract concepts. Understanding constructs as nodes in semantic networks makes it clear why psychological research has produced constant average explained variance at 42% since 1956. Together, these findings shed new light on the formidable capability of human minds to operate with fast and intersubjectively similar semantic processing. Our review identifies a categorical error present in much psychological research, measuring representations instead of the purportedly represented. We discuss how this has grave consequences for the empirical truth in research using traditional psychometric methods.
Psychological job control has typically been negatively related to work-to-family and family-to-work conflict. Based on the job demand-resource model and boundary theory, we argue that psychological job control may indirectly be positively related to family-to-work conflict by both increasing supplemental work, that is, the rate of engagement in work outside of formal working hours without receiving compensation aided by mobile technology, and work-to-family conflict. We hypothesize that this proposed positive indirect relationship will be lower among employees who perceive a high segmentation norm at their workplace. Based on a two-wave study of 4518 employees, we obtained support for a serial moderated mediation model that suggests a dual effect of psychological job control on family-to-work conflict, such that psychological job control was positively associated with family-to-work conflict through supplemental work and work-to-family conflict at low levels of segmentation norms. By examining the dual effects of psychological job control, this study aims to further understand the mechanisms involved in determining whether and when psychological job control, together with supplemental work, encourages employees to uphold or cross boundaries between work and nonwork domains. Our findings imply that psychological job control can both be a resource and a demand depending on the levels of segmentation norms.
Iversen, Nina; Hem, Leif Egil & Olsson, Ulf H. (2022)
Willingness to buy US products in three Southeast European countries: The effects of cognitive, affective and conative components of country-of-origin image
The objective of this research is to present results from a survey conducted in Croatia, Serbia, and Bosnia-Herzegovina, addressing the negative influence of warfare by USA upon consumer behavior in the region. The results show that perceptions generated from USA's general country image influence consumers' intentions to buy American-made products. Furthermore, country "goodwill" and "bad-will" create cognitive and affective ambivalence, which concurrently promote and hamper consumers' willingness to buy foreign products. Facets of USA's general country image create mixed emotions, which influence approach and avoidance behavior towards US imports. USA's country image concurrently impacts productspecific perceptions, ethnocentric tendencies, animosity, and admiration/affinity, influencing the propensity to buy American-made products among consumers in Croatia, Serbia, and Bosnia-Herzegovina.
Hansen, Bjørn Gunnar & Olsson, Ulf H. (2021)
Specification Search in Structural Equation Modeling (SEM): How Gradient Component-wise Boosting can Contribute
Although structural equation model (SEM) is a powerful and widely applied tool particularly in social sciences, few studies have explored how SEM and statistical learning methods can be combined. The purpose of this paper is to explore how gradient component-wise boosting (GCB) can contribute to item selection. We ran 200 regressions with different farmer psychological variables collected to explain variation in an animal welfare indicator (AWI). The most frequently selected variables from the regressions were selected to build a SEM to explain variation in the AWI. The results show that boosting selects relevant items for a SEM.
Kreiberg, David; Marcoulides, Katerina & Olsson, Ulf H. (2020)
A faster procedure for estimating CFA models applying Minimum Distance Estimators with a fixed weight matrix
This paper presents a numerically more efficient implementation of the quadratic form minimum distance (MD) estimator with a fixed weight matrix for confirmatory factor analysis (CFA) models. In structural equation modeling (SEM) computer software, such as EQS, lavaan, LISREL and Mplus, various MD estimators are available to the user. Standard procedures for implementing MD estimators involve a one-step approach applying non-linear optimization techniques. Our implementation differs from the standard approach by utilizing a two-step estimation procedure. In the first step, only a subset of the parameters are estimated using non-linear optimization. In the second step, the remaining parameters are obtained using numerically efficient linear least squares (LLS) methods. Through examples, it is demonstrated that the proposed implementation of MD estimators may be considerably faster than what the standard implementation offer. The proposed procedure will be of particular interest in computationally intensive applications such as simulation, bootstrapping, and other procedures involving re-sampling.
Foldnes, Njål & Olsson, Ulf H. (2019)
The choice of normal-theory weight matrix when computing robust standard errors in confirmatory factor analysis
Robust standard errors are of central importance in confirmatory factor models. In calculating these statistics a central ingredient is the inverse of the asymptotic covariance matrix of second-order moments calculated under the assumption of normality. Currently, two ways of estimating this matrix are employed in software packages. One approach uses the sample covariance matrix, the other the model-implied covariance matrix. Previous research based on a small confirmatory factor model demonstrated that the latter approach yielded a slight improvement in standard error performance. The present study argues theoretically that the discrepancy between the two approaches increases in models where there are few model parameters relative to p(p+1)/2, where p is the number of observed variables. We present simulation results that support this claim, in both small and large correctly specified models, across a large variety of non-normal conditions. We recommend the model-implied covariance matrix for robust standard error computation.
Foldnes, Njål; Marcoulides, George A. & Olsson, Ulf H. (2019)
Examining the Performance of the Modified ADF Goodness-of-fit Test Statistic in Structural Equation Models
The asymptotically distribution-free (ADF) test statistic depends on very mild distributional assumptions and is theoretically superior to many other so-called robust tests available in structural equation modeling. The ADF test, however, often leads to model overrejection even at modest sample sizes. To overcome its poor small-sample performance, a family of robust test statistics obtained by modifying the ADF statistics was recently proposed. This study investigates by simulation the performance of the new modified test statistics. The results revealed that although a few of the test statistics adequately controlled Type I error rates in each of the examined conditions, most performed quite poorly. This result underscores the importance of choosing a modified test statistic that performs well for specific examined conditions. A parametric bootstrap method is proposed for identifying such a best-performing modified test statistic. Through further simulation it is shown that the proposed bootstrap approach performs well
Jøreskog, Karl Gustaf; Olsson, Ulf H. & Wallentin, Fan Yang (2016)
Multivariate Analysis with LISREL
Springer.
Foldnes, Njål & Olsson, Ulf H. (2016)
A simple simulation technique for non-normal data with pre-specified skewness, kurtosis and covariance matrix
Andreassen, Tor W.; Lorentzen, Bengt G. & Olsson, Ulf Henning (2006)
The impact of non-normality and estimation methods in SEM on satisfaction research in marketing
Quality & Quantity: International Journal of Methodology, 40
This paper discusses consequences of violating the normal distribution assumption imbedded in Structural Equation Modeling (SEM). Based on real data from a large sample customer satisfaction survey we follow the procedures as suggested in leading textbooks. We document consequences of this practice and discuss its impact on decision making in marketing.
Olsen, S.O.; Wilcox, J. & Olsson, Ulf Henning (2005)
Consequences of Ambivalence on Satisfaction and Loyalty
Psychology & Marketing, 22(3), s. 247- 269.
Olsson, Ulf Henning; Olsson, Ulf Henning, Foss, Tron & Breivik, Einar (2004)
Two equivalent discrepancy functions for maximum likelihood estimation: Do their test statistics follow a non-central Chi-square distribution under model misspecification?
Sociological Methods & Research, 32(4), s. 453- 500.
Over the years several discrepancy,functions have been introduced both in the literature and in the software of Structural Equation Modeling (SEM). The test statistics for the discrepancy functions associated with Maximum Likelihood (ML), Generalized Least Squares (GLS), and Normal Theory Weighted Least Squares (NWLS) are all asymptotically equivalent. These test statistics are all approximately distributed as central chi-square under correct model specification and if the observed variables are multivariate normally distributed. However, it is known that the distribution of these test statistics will not approximate a central Chi-square distribution for models containing specification error, but is more likely to follow a non-central Chi-square distribution (Browne 1984). This study investigates the empirical distributions of the ML and NWLS discrepancy functions. The study includes 13 different factor models with different types and degrees of specification error It is found, except for small samples, that the empirical distribution of the ML-test statistic outperforms the empirical distribution of the NWLS-test statistic in terms of approximation to the theoretical non-central Chi-square distribution. Furthermore, in some cases, it turned out that the non-central Chi-square approximation was not appropriate even for models that contained minor and moderate degrees of specification error. Abstract: Over the years several discrepancy,functions have been introduced both in the literature and in the softwareof Structural Equation Modeling (SEM). The test statistics for the discrepancy functions associated with Maximum Likelihood (ML), Generalized Least Squares (GLS), and Normal Theory Weighted Least Squares (NWLS) are all asymptotically equivalent. These test statistics are all approximately distributed ascentral chi-square under correct model specification and if the observed variables are multivariate normally distributed.However, it is known that the distribution of these test statistics will not approximate a central Chi-square distribution for models containing specification error, but is more likely to follow a non-central Chi-square distribution (Browne 1984). This study investigates the empirical distributions of the ML and NWLS discrepancy functions. The study includes 13 different factor models with different types and degrees of specification error It is found, except for small samples, thattheempirical distribution of the ML-test statistic outperforms the empirical distribution of the NWLS-test statistic in terms of approximation to the theoretical non-central Chi-square distribution. Furthermore, in some cases, itturned out that the non-central Chi-square approximation was not appropriate even for models that contained minor and moderate degrees of specification error.
This study was particularly designed to respond to Jaffe and Nebenzahl's (1984) suggestion to test whether and how entity-based and attribute-based semantic differential scaling formats could predict purchasing behaviour within a country-of-origin setting. The study includes recent research on survey context effects in order to explain and extend our analysis, and uses attitude consistency theory as a conceptual framework. A comparison of the fit statistics between the two scaling formats on each entity (country) indicates that the attribute-based format estimates a higher attitude response consistency and predictive validity by giving better predictors of global country image (evaluation) and buying frequency of products from the different countries investigated. This study uses data collected from a probability sample of industrial buyers within the seafood industry.
Olsson, Ulf Henning & Breivik, Einar (2001)
Adding variables to improve fit: the effect of model size on fit assessment in LISREL
Structural equation model : present and future : a festschrift in honor of Karl Jöreskog/Robert Cudeck, Stephen du Toit, Dag Sörbom (eds.)
Myrtveit, Ingunn; Stensrud, Erik & Olsson, Ulf Henning (2001)
Analysing data sets with missing data: an empirical evaluation of imputation methods and likelihood-based methods
IEEE Transactions on Software Engineering, 27(11), s. 999- 1013.
Breivik, Einar; Olsson, Ulf H. & Olsson, Ulf H. (2001)
Adding variables to improve fit: the effect of model size on fit assessment in LISREL
Structural equation model : present and future : a festschrift in honor of Karl Jöreskog/Robert Cudeck, Stephen du Toit, Dag Sörbom (eds.)
This paper focuses on the effect of model size on the performance of various fit indices in structural equation models. In particular, the paper contrasts the performance of the root mean square error of approximation index (RMSEA) and the goodness-of-fit index (GFI). RMSEA contains a parsimony adjustment whereas GFI does not. Parsimony correction has been found to work well when comparing alterntive models for the same set of variables (Mulaik, et al., 1989; Williams & Holohan, 1994). However, parsimony ratios also appear to show better overall fit when more observed and latent variables are added to the model. To investigate effects of model size, we examine the fit of models that vary with respect to the number of included variables. Different types and degrees of specification errors are also examined. The findings suggest that RMSEA tends to favor models that include more variables and constructs over models that are simpler. Similar patterns were found for other indices correcting for parsimony. GFI was found to decrease with increasing model size for models containing specification errors that involved the same method factor(s) across submodels. The results suggest that in addition to parsimony, i.e., the number of fixed parameters in relation to the number of free parameters, researchers should also consider model size, i.e.,the number of variables when assessing model fit.
Olsson, Ulf H.; Troye, Sigurd Villads, Foss, Tron & Howell, Roy D. (2000)
The Performance of ML, GLS, and WLS Estimation in Structural Equation Modeling under Conditions of Misspecification and Non-normality
Structural Equation Modeling, 7(4), s. 557- 595.
Breivik, Einar; Olsson, Ulf Henning, Cudeck, Robert, du Toit, Stephen & Sørbom, Dag (2000)
Adding Variables to improve fit: the effect of model size on fit assessment in LISRE
Structural Equation Modeling: The Present and Future. A Festchrift in honor of Karl G. Jøreskog
Olsson, Ulf Henning; Olsson, Ulf Henning, Villads Troye, Sigurd & Howell, Roy D. (1999)
Theoretic Fit and Empirical Fit: The Performance of Maximum Likelihood versus Generalized Least Squares Estima-tion in Structural Equation Models
Multivariate Behavioral Research, 34(1), s. 31- 59.
Myrtveit, Ingunn; Stensrud, Erik & Olsson, Ulf Henning (2001)
Assessing the Benefits of Imputing ERP Projects with Missing Data
[Academic lecture]. 7th International Software Metrics Symposium.
Solberg, Carl Arthur & Olsson, Ulf H. (2001)
Export Performance and Management Orientation, The Case of Norwegian IT Exporters
[Academic lecture]. The EIBA Conference.
Olsson, Ulf Henning (1999)
Three approaches for assessing performance in structural equation modeling: Evidence from simulated data and application on three models of customer satisfaction
[Academic lecture]. Advanced Research Teqniques Forum.
Gripsrud, Geir & Olsson, Ulf Henning (1999)
Markedsanalyse
[Textbook]. Cappelen Damm Høyskoleforlaget.
Olsson, Ulf Henning; Foss, Tron & Troye, Sigurd V. (1999)
Does WLS reward the researcher for using non-normal data?
[Report]. Handelshøyskolen BI.
Olsson, Ulf Henning; Foss, Tron & Troye, Sigurd V. (1998)
The Performance of alternate estimation methods in Structural Equation Modeling under conditions of misspecification and non-normality