Survey-based measures of risk attitudes and portfolio risk: Evidence from pension participants

Abstract

We use a unique dataset of pension participants in Turkey to evaluate the effectiveness of a risk questionnaire developed by the regulatory authority. Our analysis includes a reliability assessment (Cronbach’s $\alpha =0.73$) and a factor analysis that reveals two latent constructs: risk attitude and financial situation/literacy. Although both factors show a significant positive relationship with participants’ portfolio risk, the overall explanatory power remains low, with an $R^2$ of 0.134. Comparing these factors in terms of their contribution to predictive validity, we demonstrate that the risk attitude factor—formed from questions directly addressing financial risk-taking—exhibits significantly greater predictive power than the financial situation/literacy factor, which pertains to questions about the financial situation and self-assessed financial literacy. Our results imply that demographic factors like gender, education level, marital status, and age show weak predictive power for portfolio risk, suggesting that observed behavior in risky choices is more influenced by domain-specific attitudes.