Testing for measurement equivalence of human values across online and paper-and-pencil surveys

The following study investigates the measurement equivalence of an online and paper-and-pencil (PAP) survey of human values. For this purpose, a total of 250 respondents completed the 21-item version of the Portrait Value Questionnaire either online (n = 125) or by PAP (n = 125). This questionnaire was developed by Schwartz (Advances in experimental social psychology, Academic Press, New York, 1992) and has been included in the European Social Survey since 2002 to test his theory of basic human values. Measurement invariance was tested via a multiple group confirmatory factor analysis. The assessment of invariance included the three levels of configural, metric, and scalar invariance, and the latent means of the values between both samples were compared. Results of this study show that the measurements are invariant at the three levels (configural, metric, and scalar), but there are latent mean differences between the values across the surveys. These differences may be partly explained by age and level of education differences between the two samples. Based on these findings we conclude that the methods of measurement are essentially invariant.     

PANEL PROBIT WITH FLEXIBLE CORRELATED EFFECTS: QUANTIFYING TECHNOLOGY SPILLOVERS IN THE PRESENCE OF LATENT HETEROGENEITY

In this paper, we introduce a Bayesian panel probit model with two flexible latent effects: first, unobserved individual heterogeneity that is allowed to vary in the population according to a nonparametric distribution; and second, a latent serially correlated common error component. In doing so, we extend the approach developed in Albert and Chib (Journal of the American Statistical Association 1993; 88 : 669–679; in Bayesian Biostatistics, Berry DA, Stangl DK (eds), Marcel Dekker: New York, 1996), and in Chib and Carlin (Statistics and Computing 1999; 9 : 17–26) by releasing restrictive parametric assumptions on the latent individual effect and eliminating potential spurious state dependence with latent time effects. The model is found to outperform more traditional approaches in an extensive series of Monte Carlo simulations. We then apply the model to the estimation of a patent equation using firm‐level data on research and development (R&D). We find a strong effect of technology spillovers on R&D but little evidence of product market spillovers, consistent with economic theory. The distribution of latent firm effects is found to have a multimodal structure featuring within‐industry firm clustering. Copyright © 2012 John Wiley & Sons, Ltd.     

Confirmatory and Structural Categorical Latent Variables Models

The paper proposes a general framework for modeling multiple categorical latent variables (MCLV). The MCLV models extend latent class analysis or latent transition analysis to allow flexible measurement and structural components between endogenous categorical latent variables and exogenous covariates. Therefore, modeling frameworks in conventional structural equation models, for example, CFA and MIMIC models are feasible in the MCLV circumstances. Parameter estimations for the MCLV models are performed by using generalized expectation–maximization (E–M) algorithm. In addition, the adjusted Bayesian information criterion provides help for model selections. A substantive study of reading development is analyzed to illustrate the feasibility of MCLV models.     

Replicating the Results in ‘A New Model of Trend Inflation’ Using Particle Markov Chain Monte Carlo

An article by Chan et al. ( 2013 ) published in the Journal of Business and Economic Statistics introduces a new model for trend inflation. They allow the trend inflation to evolve according to a bounded random walk. In order to draw the latent states from their respective conditional posteriors, they use accept–reject Metropolis–Hastings procedures. We reproduce their results using particle Markov chain Monte Carlo (PMCMC), which approaches drawing the latent states from a different technical point of view by relying on combining Markov chain Monte Carlo and sequential Monte Carlo methods. To conclude: we are able to reproduce the results of Chan et al. ( 2013 ). Copyright © 2015 John Wiley & Sons, Ltd.     

Segmenting university alumni using a person‐centered methodology

Higher education leaders in the United States increasingly rely on relationships with alumni to advance multiple institutional goals. Scholars have traditionally relied on variable‐centered approaches to understand associations among alumni experiences, personal attributes, and support behaviors. Departing from this tradition, this study draws on a person‐centered approach, latent class analysis, to segment groups of alumni by their non‐monetary support behaviors. We define non‐monetary support as engaging in actions outside of charitable giving that advance institutional objectives. Drawing on past literature, we conceptualize alumni non‐monetary support behaviors as falling into 4 categories: (a) volunteerism: charitable preferences, (b) political advocacy: social change preferences, (c) multimode engagement: charity and social change, and (d) disengagement: nonsupport. Relying on an alumni survey from a research‐intensive university in the United States, our analysis found support for a 4‐class model of alumni supporters and nonsupporters. These groupings include the classes of Political Advocates, Apolitical Recruiters, Super Engaged Alumni, and Disengaged Alumni. Using cross‐tabulation analysis, we explore attributes of each class by age, gender, and involvement in religious, political, and volunteer organizations in college. We find that groups of alumni exhibit the same patterns of engagement while they were students. For example, students who were engaged in political action in college are those who are likely to become Political Engagers as alumni. Students who volunteered in college and stayed clear of politics emerge as Apolitical Recruiters after college. Super Engaged Alumni are those who were engaged in multiple domains in college. Implications for advancement practice are discussed.     

I didn't tell,and I won't tell: dynamic response error in the SIPP

Using state administrative records matched to the 1984 Survey of Income and Program Participation, we examine intertemporal relationships in response errors. False negative errors in reporting food stamps are highly correlated across interviews for the same household. Hypotheses that the error process can be explained by learning behaviour are not supported. Bivariate probit of response error in two periods reveals that responses to covariates are stable over time and the latent error terms are positively correlated. These findings support the hypothesis that respondents have a latent tendency to cooperate (or not cooperate) with surveys. Copyright © 2005 John Wiley & Sons, Ltd.     

Induced families of choice probabilities

Let be a family of choice probabilities that are caused by compatible latent factors. Then, there should exist an underlying common probability measure that in some degree induces each choice probability P_S. The problem of the existence of P will be considered with respect to a general concept of induced probability. In addition, the relevance of this concept for Mathematical Economics and the Social Sciences will be discussed.     

Imputation of Missing Item Responses: Some Simple Techniques

Among the wide variety of procedures to handle missing data, imputingthe missing values is a popular strategy to deal with missing itemresponses. In this paper some simple and easily implemented imputationtechniques like item and person mean substitution, and somehot-deck procedures, are investigated. A simulation study was performed based on responses to items forming a scale to measure a latent trait ofthe respondents. The effects of different imputation procedures onthe estimation of the latent ability of the respondents wereinvestigated, as well as the effect on the estimation of Cronbach'salpha (indicating the reliability of the test) and Loevinger'sH-coefficient (indicating scalability). The results indicate thatprocedures which use the relationships between items perform best,although they tend to overestimate the scale quality.     

On estimating true change interrelationships with other variables

This article is concerned with the estimation of indexes of interrelationship between true change in repeatedly assessed latent constructs and other variables. In the social and behavioral sciences this theoretically and empirically important issue arises commonly in research aimed at studying correlates and predictors of growth or decline in a context of a longitudinal research design. A structural equation modeling approach is described that is useful in empirical situations where identifying variables correlated with change in longitudinally followed latent constructs is of interest. The issue of discerning between correlates and predictors of change using the structural equation modeling methodology is discussed. The described approach is used to study correlative aspects of ability growth in a cognitive intervention study (Balteset al., 1986).     

Testing measurement invariance using multigroup CFA: differences between educational groups in human values measurement

This article applies the testing procedures for measurement invariance using multigroup confirmatory factor analysis (MGCFA). It illustrates these procedures by investigating the factorial structure and invariance of the Portraits Value Questionnaire (PVQ, Schwartz et al.: J. Cross Cult. Psychol. 32(5), 519–542 (2001)) across three education groups in a population sample (N  =  1,677). The PVQ measures 10 basic values that Schwartz postulates to comprehensively describe the human values recognized in all societies (achievement, hedonism, self-direction, benevolence, conformity, security, stimulation, power, tradition and universalism). We also estimate and compare the latent means of the three education groups. The analyses show partial invariance for most of the 10 values and parameters. As expected, the latent means show that less educated respondents attribute more importance to security, tradition, and conformity values.     

Semiparametric Estimator for Binary‐outcome Sample Selection: Prejudice Matters in Election

a semiparametric estimator for binary‐outcome sample‐selection models is proposed that imposes only single index assumptions on the selection and outcome equations without specifying the error term distribution. I adopt the idea in Lewbel (2000) using a ‘special regressor’ to transform the binary response Y so that the transformed Y becomes linear in the latent index, which then makes it possible to remove the selection correction term by differencing the transformed Y equation. There are various versions of the estimator, which perform differently trading off bias and variance. A simulation study is conducted, and then I apply the estimators to US presidential election data in 2008 and 2012 to assess the impact of racial prejudice on the elections, as a black candidate was involved for the first time ever in the US history.     

Bayes estimates of distance‐to‐market: transactions costs,cooperatives and milk‐market development in the Ethiopian highlands

Rationalizing non‐participation as a resource deficiency in the household, this paper identifies strategies for milk‐market development in the Ethiopian highlands. The additional amounts of covariates required for positive marketable surplus—‘distances‐to market’—are computed from a model in which production and sales are correlated; sales are left‐censored at some unobserved threshold; production efficiencies are heterogeneous; and the data are in the form of a panel. Incorporating these features into the modeling exercise is important because they are fundamental to the data‐generating environment. There are four reasons. First, because production and sales decisions are enacted within the same household, both decisions are affected by the same exogenous shocks, and production and sales are therefore likely to be correlated. Second, because selling involves time and time is arguably the most important resource available to a subsistence household, the minimum sales amount is not zero but, rather, some unobserved threshold that lies beyond zero. Third, the potential existence of heterogeneous abilities in management, ones that lie latent from the econometrician's perspective, suggest that production efficiencies should be permitted to vary across households. Fourth, we observe a single set of households during multiple visits in a single production year. The results convey clearly that institutional and production innovations alone are insufficient to encourage participation. Market‐precipitating innovation requires complementary inputs, especially improvements in human capital and reductions in risk. Copyright © 2008 John Wiley & Sons, Ltd.     

Asset Pricing with Observable Stochastic Discount Factors

The stochastic discount factor model provides a general framework for pricing assets. By specifying the discount factor suitably it encompasses most of the theories currently in use, including CAPM and consumption CAPM. The SDF model has been based on the use of single and multiple factors, and on latent and observed factors. In most situations, and especially for the term structure, single factor models are inappropriate, whilst latent variables require the somewhat arbitrary specification of generating processes and are difficult to interpret. In this paper we survey the principal different implementations of the SDF model for bonds, equity and FOREX and propose a new approach. This is based on the use of multiple factors that are observable and modelling the joint distribution of excess returns and the factors using a multi–variate GARCH–in–mean process. We argue that in general single equation and VAR models, although widely used in empirical finance, are inappropriate as they do not satisfy the no–arbitrage condition. Since risk premia arise from conditional covariation between the returns and the factors, both a multi–variate context and having conditional covariances in the conditional mean process, is essential. We explain how apparent exceptions, such as the CIR and Vasicek models, in fact meet this requirement — but at a price. We explain our new approach, discuss how it might be implemented and present some empirical evidence, mainly from our own researches. Partly, to enable comparisons to be made, the survey also includes evidence from recent empirical work using more traditional approaches.     

Nonlinear Structural Equation Models with the Theory of Planned Behavior: Comparison of Multiple Group and Latent Product Term Analyses

Nonlinear relationships in structural equation analysis became moreinteresting for applied researchers since the implementation of nonlinearconstraints in software programs (i.e., LISREL). This article provides acomprehensive application of the expectancy × value part of the Theory of Planned Behavior (Ajzen, 1991) including interactions of latent variables.The main purpose of the study is to overcome limitations of similarprevious analyses of Baumgartner and Bagozzi (1995) and Yang Jonsson (1997,1998) with an empirical example from representative survey data. Nonlinearrelationships of the theories' constructs (Attitude toward the behavior, subjectivenorm and perceived behavioral control) are analyzed one upon another withmultiple group comparisons and latent interaction models. Results confirmthe strategy to use multiple group techniques for preliminary analyses(i.e., detection of an interaction effect). With latent interaction models thestrength and the significance of the interaction is estimated under controlfor random measurement error. Parameters, standard errors, andgoodness-of-fit statistics are compared between three estimationtechniques (ML, GLS and WLS). Multiple group analyses and latentinteraction modeling detect a significant interaction for perceivedbehavioral control but not for attitude toward the behavior and subjective norm. Variations of the estimators of the perceived behavioral controlsubmodel is proved by bootstrapping. Further model improvements andalternative model techniques are discussed in the final chapter.     

A parametric test of the negativity of the substitution matrix

The negativity of the substitution matrix implies that its latent roots are non-positive. When inequality restrictions are tested, standard test statistics such as a likelihood ratio or a Wald test are not X²-distributed in large samples. We propose a Wald test for testing the negativity of the substitution matrix. The asymptotic distribution of the statistic is a mixture of X²-distributions. The Wald test provides an exact critical value for a given significance level. The problems involved in computing the exact critical value can be avoided by using the upper and lower bound critical values derived by Kodde and Palm (1986). Finally the methods are applied to the empirical results obtained by Barten and Geyskens (1975).     

Identifiability of mean‐reverting measurement error with instrumental variable

In the context where one main regressor is measured with error and at least one instrumental variable is available for the correction of measurement error, this paper provides, to the best of our knowledge, a first point‐identification result on the variance of measurement error, the variance of latent variable, and their covariance. We show that the parameters are identified if the regression model is not de facto linear. We illustrate the method in an application to identify mean‐reverting measurement error, a typical issue in reported income where the measurement error of income is negatively correlated with the true income.     

Extracting a common stochastic trend: Theory with some applications

This paper investigates the statistical properties of estimators of the parameters and unobserved series for state space models with integrated time series. In particular, we derive the full asymptotic results for maximum likelihood estimation using the Kalman filter for a prototypical class of such models—those with a single latent common stochastic trend. Indeed, we establish the consistency and asymptotic mixed normality of the maximum likelihood estimator and show that the conventional method of inference is valid for this class of models. The models we explicitly consider comprise a special–yet useful–class of models that may be employed to extract the common stochastic trend from multiple integrated time series. Such models can be very useful to obtain indices that represent fluctuations of various markets or common latent factors that affect a set of economic and financial variables simultaneously. Moreover, our derivation of the asymptotics of this class makes it clear that the asymptotic Gaussianity and the validity of the conventional inference for the maximum likelihood procedure extends to a larger class of more general state space models involving integrated time series. Finally, we demonstrate the utility of this class of models extracting a common stochastic trend from three sets of time series involving short- and long-term interest rates, stock return volatility and trading volume, and Dow Jones stock prices.     

Simulation Estimation of Two‐tiered Dynamic Panel Tobit Models with an Application to the labour Supply of Married Women: A Comment

We find that the empirical results reported in Chang (Journal of Applied Econometrics 2011; 26 (5): 854–871) are contingent on the specification of the model. The use of Heckman's initial conditions combined with observed and not latent lagged dependent variables leads to a counter‐intuitive estimation of the true state dependence. The use of Wooldridge's initial conditions together with the observed lagged dependent variable and a proper modelling of censoring provides a much more natural estimate of the true state dependence parameters together with a clearer interpretation of the decision to participate in the labour market in the two‐tiered model. Copyright © 2015 John Wiley & Sons, Ltd.     

Parametric links for binary choice models: A Fisherian–Bayesian colloquy

The familiar logit and probit models provide convenient settings for many binary response applications, but a larger class of link functions may be occasionally desirable. Two parametric families of link functions are investigated: the Gosset link based on the Student t latent variable model with the degrees of freedom parameter controlling the tail behavior, and the Pregibon link based on the (generalized) Tukey λ family, with two shape parameters controlling skewness and tail behavior. Both Bayesian and maximum likelihood methods for estimation and inference are explored, compared and contrasted. In applications, like the propensity score matching problem discussed below, where it is critical to have accurate estimates of the conditional probabilities, we find that misspecification of the link function can create serious bias. Bayesian point estimation via MCMC performs quite competitively with MLE methods; however nominal coverage of Bayes credible regions is somewhat more problematic.     

Unravelling financial market linkages during crises

An empirical model of multiple asset classes across countries is formulated in a latent factor framework. A special feature of the model is that financial market linkages during periods of financial crises, including spillover and contagion effects, are formally specified. The model also captures a range of common factors including global shocks, country and market shocks, and idiosyncratic shocks. The framework is applied to modelling linkages between currency and equity markets during the East Asian financial crisis of 1997–98. The results provide strong evidence that cross‐market links are important. Spillovers have a relatively larger effect on volatility than contagion, but both are statistically significant. Copyright © 2007 John Wiley & Sons, Ltd.