Analysing partial ranks by using smoothed paired comparison methods: an investigation of value orientation in Europe

Summary. This paper introduces the paired comparison model as a suitable approach for the analysis of partially ranked data. For example, the Inglehart index, collected in international social surveys to examine shifts in post-materialistic values, generates such data on a set of attitude items. However, current analysis methods have failed to account for the complex shifts in individual item values, or to incorporate subject covariates. The paired comparison model is thus developed to allow for covariate subject effects at the individual level, and a reparameterization allows the inclusion of smooth non-linear effects of continuous covariates. The Inglehart index collected in the 1993 International Social Science Programme survey is analysed, and complex non-linear changes of item values with age, level of education and religion are identified. The model proposed provides a powerful tool for social scientists.     

Efficient iteration procedures for maximum likelihood factor analysis

A class of fast convergent iteration procedures for ML factor analysis is presented in this paper. It includes a further development of Jöreskog’s (1971 with van Thillo, 1977) Newton-Raphson-like procedure which is widely available in statistical program packages but which is inclined to fail when solving difficult problems. In a comparison of efficiency, besides these two algorithms, our own versions of two quasi-Newton methods, namely the Davidon-Fletcher-Powell (DFP) and the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method, are tested.     

Book review on Michalis Drouvelis: "Social preferences: an introduction to behavioural economics and experimental research"

Theory and Decision -     

The effect of compulsory schooling on health—evidence from biomarkers

Using data from the Health Survey for England and the English Longitudinal Study on Ageing, we estimate causal effects of schooling on health. Our study complements earlier studies exploiting two nationwide increases in British compulsory school leaving age in 1947 and 1973, respectively, by using biological stress markers as measures of health outcomes in addition to self-reported measures. We find a strong positive correlation between education and health, both self-rated and measured by blood fibrinogen and C-reactive protein levels. However, causal effects estimates based on compulsory schooling changes are ambiguous and remain statistically insignificant.     

Factor analysis regression

In the presence of multicollinearity the literature points to principal component regression (PCR) as an estimation method for the regression coefficients of a multiple regression model. Due to ambiguities in the interpretation, involved by the orthogonal transformation of the set of explanatory variables, the method could not yet gain wide acceptance. Factor analysis regression (FAR) provides a model-based estimation method which is particularly tailored to overcome multicollinearity in an errors-in-variables setting. In this paper two feasible versions of a FAR estimator are compared with the OLS estimator and the PCR estimator by means of Monte Carlo simulation. While the PCR estimator performs best in cases of strong and high multicollinearity, the Thomson-based FAR estimator proves to be superior when the regressors are moderately correlated.     

Ein empirischer Validit?tsvergleich zwischen Adaptive Self-Explicated Approach (ASE), Pairwise Comparison-based Preference Measurement (PCPM) und Adaptive Conjoint Analysis (ACA)

The increasing complexity of many products makes high demands on methods used for measuring consumer preferences. In such cases, practitioners frequently use Adaptive Conjoint Analysis (ACA). However, compositional approaches also proved to be efficient. Recently, Srinivasan and Netzer (2011) suggested a promising compositional technique called the Adaptive Self-Explicated Approach (ASE), which significantly outperformed ACA regarding its predictive validity. Another advantageous approach, called Pairwise Comparison-based Preference Measurement (PCPM), was introduced by Scholz et al. (2010). This paper contrasts the popular ACA with these two new compositional approaches and discusses the validity results of an empirical study in the leisure industry. For two out of three criteria PCPM partly leads to a significantly higher predictive validity and a halving of the survey time. As products and services become more complex, multi-attribute preference meas urement techniques have to cope with a large number of attributes. Particularly Adaptive Conjoint Analysis (ACA) and compositional approaches are often applied to complex products. Two new alternative compositional approaches have been recently proposed, the Adaptive Self-Explicated Approach (ASE, Srinivasan und Netzer 2011) as well as Pairwise Comparison-based Preference Measurement (PCPM, Scholz et al. 2010). In first empirical applications, the authors found that the predictive validity of ASE and PCPM was significantly higher than that of ACA. In an empirical study involving theme parks, we compare ASE and PCPM as well as the benchmark ACA with respect to several criteria of validity. We find that the predictive validity is significantly higher for the PCPM with respect to two (out of three) criteria. Moreover, the PCPM survey was about half the length of the ACA survey.     

Reassessing the link between premarital cohabitation and marital instability

Premarital cohabitation has been found to be positively correlated with the likelihood of marital dissolution in the United States. To reassess this link, I estimate proportional hazard models of marital dissolution for first marriages by using pooled data from the 1988, 1995, and 2002 surveys of the National Survey of Family Growth (NSFG). These results suggest that the positive relationship between premarital cohabitation and marital instability has weakened for more recent birth and marriage cohorts. Using multiple marital outcomes for a person to account for one source of unobserved heterogeneity, panel models suggest that cohabitation is not selective of individuals with higher risk of marital dissolution and may be a stabilizing factor for higher-order marriages. Further research with more recent data is needed to assess whether these results are statistical artifacts caused by data weaknesses in the NSFG.