Conditional autoencoder asset pricing models for the Korean stock market.

This study analyzes the explanatory power of the latent factor conditional asset pricing model for the Korean stock market using an autoencoder. The autoencoder is a type of neural network in machine learning that can extract latent factors. Specifically, we apply the conditional autoencoder (CA) model that estimates factor exposure as a flexible nonlinear function of covariates. Our main findings are as follows. The CA model showed excellent explanatory power not only in the entire sample but also in several subsamples in the Korean market. Also, because of this explanatory power, it can better explain market anomalies compared to the traditional asset pricing models. As a result of examining investment strategies using pricing error, the CA model measures the expected return of stocks better than the traditional asset pricing model. In addition, the CA model indicates that the firm characteristic variables are important in asset pricing conditional on macro-financial states, such as the global financial crisis and the coronavirus disease 2019 pandemic. The result shows that the major variables considered in the explanation of stock returns through the CA model may vary depending on the time. This is expected to provide a broader perspective on asset pricing through the CA model in the future.

How to calibrate Gaussian two-factor model using swaption.

We propose an efficient approximation of the swaption normal volatility to estimate the mean reversion separately from the other volatility parameters in the Gaussian two-factor model. We compare our two-step approach with a one-step method that calibrates all parameters simultaneously. The comparison is based on the data from interest rate market of Korea and the US. The parameter estimates of our proposed two-step method are more stable than those of the one-step method in that the latter is overly sensitive to market changes whereas the former is not. The proposed approach also eliminates many existing problems in the Gaussian two-factor model.

Complementarity in dietary supplements and foods: are supplement users vegetable eaters?

Background: The consumption of fruits, vegetables, and dietary supplements correlate. Most previous studies have aimed to identify the determinants of supplement uses or the distinct features of supplement users; this literature lacks a discussion on dietary supplement consumption as a predictor of fruit and vegetable consumption. Objective: This study examines how dietary supplement consumption correlates with fruit and vegetable consumption by combining scanner data and surveys of Korean household grocery shopping. Methods: Propensity score matching (PSM) is used to identify the relationship between dietary supplement consumption and fruit and vegetable consumption in a household. A logit regression using supplement consumption as the dependent variable is used. Then, the supplement takers (the treatment group) are matched with non-takers (the control group) based on the propensity scores estimated in the logit regression. The fruit and vegetable consumption levels of the groups are then compared. Results: We found that dietary supplement use is associated with higher fruit and vegetable consumption. This supports the health consciousness hypothesis based on attention bias, availability heuristics, the focusing effect, and the consumption episode effect. It rejects the health substitute hypothesis based on economic substitutes and mental accounting. Conclusions: Future research on the health benefits of dietary supplements should address the complementary consumption of fruits/vegetables and their health benefits to avoid misstating the health effects of supplements.