Issues, problems and potential solutions when simulating continuous, non-normal data in the social sciences

Authors

  • Oscar Lorenzo Olvera Astivia

DOI:

https://doi.org/10.15626/MP.2019.2117

Keywords:

monte carlo simulation coomputer simulation non normality copula multivariate

Abstract

Computer simulations have become one of the most prominent tools for methodologists in the social sciences to evaluate the properties of their statistical techniques and to offer best practice recommendations. Amongst the many uses of computer simulations, evaluating the robustness of methods to their assumptions, particularly univariate or multivariate normality, is crucial to ensure the appropriateness of data analysis. In order to accomplish this, quantitative researchers need to be able to generate data where they have a degree of control over its non-normal properties. Even though great advances have been achieved in statistical theory and computational power, the task of simulating multivariate, non-normal data is not straightforward. There are inherent conceptual and mathematical complexities implied by the phrase "non-normality" which are not always reflected in the simulations studies conduced by social scientists. The present article attempts to offer a summary of some of the issues concerning the simulation of multivariate, non-normal data in the social sciences. An overview of common algorithms is presented as well as some of the characteristics and idiosyncrasies that implied in them which may exert undue influence in the results of simulation studies. A call is made to encourage the meta-scientific study of computer simulations in the social sciences in order to understand how simulation designs frame the teaching, usage and practice of statistical techniques within the social sciences.

Metrics

Metrics Loading ...

Author Biography

Oscar Lorenzo Olvera Astivia

My name is Oscar L. Olvera Astivia. I have a PhD in Measurement, Evaluation and Research Methodology (MERM) from the University of British Columbia. I am also an affiliated member of the Structural Equation Modeling lab in the Quantitative Methods program, so I divide my time as best as I can between both programs. As of today, I am a post-doctoral research fellow at the Human Early Learning Partnership. MERM is an intersection of Psychometrics, Statistics and research methods for the social sciences, particularly in the fields of Psychology and Education. I tend to gravitate towards the more ‘statistics-oriented’ side of research methods, so I really, really like everything that has to do with data analysis, Monte Carlo simulations, computer algorithms, etc. which goes along with my background in Math/Stats. My areas of expertise are Structural Equation Modelling, linear mixed models, Item Response Theory, some stuff about Bayesian methods, etc.

Downloads

Published

2020-07-31

Issue

Section

Original articles