David Disatnik

Shrinking the Covariance Matrix

The subject here is construction of the covariance matrix for portfolio optimization. In terms of the ex post standard deviation of the global minimum-variance portfolio, there is no statistically significant gain in using more sophisticated shrinkage estimators rather than simpler portfolios of estimators. This finding holds whether or not the investor imposes short sale constraints to prevent portfolio weights from being negative.

Need for Cognitive Closure, Risk Aversion, Uncertainty Changes, and Their Effects on Investment Decisions

Investment decisions play a crucial role in the way consumers manage their wealth, and therefore, it is important to understand how consumers make these decisions. This research contributes to this attempt by examining consumers’ investment decisions in response to new information about changes in uncertainty in financial markets. The authors identify possible conditions under which consumers, despite having new information about changes in market uncertainty, are less likely to assimilate the new information and consequently do not make investment decisions that are in line with their risk-aversion levels. Specifically, in a series of studies, the authors show that high rather than low need for cognitive closure can lead to a lack of openness to new information and therefore may dilute consumers’ tendency to update their investment portfolios in a way that reflects their risk preferences. In addition, the authors address possible ways to influence consumers’ assimilation of new information, to help even those with high need for cognitive closure make investment decisions that are in line with their levels of risk aversion.

Portfolio Optimization Using a Block Structure for the Covariance Matrix

Implementing in practice the classical mean-variance theory for portfolio selection often results in obtaining portfolios with large short sale positions. Also, recent papers show that, due to estimation errors, existing and rather advanced mean-variance theory-based portfolio strategies do not consistently out perform the naive 1/N portfolio that invests equally across N risky assets. In this paper, I introduce a portfolio strategy that generates a portfolio, with no short sale positions, that can outperform the 1/N portfolio. The strategy is investing in a global minimum variance portfolio (GMVP) that is constructed using an easy to calculate block structure for the covariance matrix of asset returns. Using this new block structure, the weights of the stocks in the GMVP can be found analytically, and as long as simple and directly computable conditions are met, these weights are positive.

Multicollinearity is a red herring in the search for moderator variables: A guide to interpreting moderated multiple regression models and a critique of Iacobucci, Schneider, Popovich, and Bakamitsos (2016).

Multicollinearity is irrelevant to the search for moderator variables, contrary to the implications of Iacobucci, Schneider, Popovich, and Bakamitsos (Behavior Research Methods, 2016, this issue). Multicollinearity is like the red herring in a mystery novel that distracts the statistical detective from the pursuit of a true moderator relationship. We show multicollinearity is completely irrelevant for tests of moderator variables. Furthermore, readers of Iacobucci et al. might be confused by a number of their errors. We note those errors, but more positively, we describe a variety of methods researchers might use to test and interpret their moderated multiple regression models, including two-stage testing, mean-centering, spotlighting, orthogonalizing, and floodlighting without regard to putative issues of multicollinearity. We cite a number of recent studies in the psychological literature in which the researchers used these methods appropriately to test, to interpret, and to report their moderated multiple regression models. We conclude with a set of recommendations for the analysis and reporting of moderated multiple regression that should help researchers better understand their models and facilitate generalizations across studies.

The Two-Block Covariance Matrix and the CAPM

The classical assumptions of the Capital Asset Pricing Model do not ensure obtaining a tangency (market) portfolio in which all the risky assets appear with positive proportions. This paper gives an additional set of assumptions that ensure obtaining such a portfolio. Our new set of assumptions mainly deals with the structure of the covariance matrix of the risky assets returns. The structure we suggest for the covariance matrix is of a two-block type. We derive analytically sufficient conditions for a matrix of this type to produce a long-onlytangency portfolio (as well as a long-only global minimum variance portfolio).

A Note on Portfolio Optimization and the Diagonal Covariance Matrix

Recent papers show that, due to estimation errors, existing and rather advanced mean-variance theory-based portfolio strategies do not consistently outperform the naive 1/N portfolio that invests equally across N risky assets. In this paper, I introduce a portfolio strategy that can consistently outperform the 1/N portfolio. The strategy is investing in a global minimum variance portfolio (GMVP) that is constructed using the diagonal sample covariance matrix of asset returns. Like the 1/N portfolio, also the GMVP constructed using the diagonal covariance matrix has the appealing features of no short sale positions and simple implementation. Thus, from a practical point of view, when evaluating the performance of a particular portfolio strategy, the GMVP constructed using the diagonal matrix should serve at least as a first obvious benchmark.