A Likelihood-Based Comparison of Macro Asset Pricing Models

Abstract

We estimate asset pricing models with multiple risks: long-run growth, long-run volatility, habit, and a residual. The Bayesian estimation accounts for the entire likelihood of consumption, dividends, and the pricedividend ratio. We find that the residual represents at least 80% of the variance of the price-dividend ratio. Moreover, the residual tracks most recognizable features of stock market history such as the 1990's boom and bust. Long run risks and habit contribute primarily in crises. The dominance of the residual comes from the low correlation between asset prices and consumption growth moments. We discuss theories which are consistent with our results.

Neural networks for estimating Macro Asset Pricing model in football clubs

“…Regarding the analysis of long-term risks, we observe that the estimates show a possible longterm risk higher than that shown by economic growth, considering the data on expected growth and consumption volatility. The persistence parameter of long-term growth risks shows values somewhat higher than 0.60, which is a high level, but not higher than that shown in previous experiences for broader analyses regarding the estimation of stock indices (Chen et al, 2017;Gu et al, 2021). The same occurs with long-term risks, which undergo temporary variations, that is, the parameters φ x y σ h that represent the long-term relative volatility of growth shocks and long-term logarithmic volatility σ h , respectively, show high persistence, since their distribution is above 0.70, being statistically significant and consistent with previous studies (Schorfheide et al, 2018).…”

“…Typically, volatility is found as a variable with a positive sign (Gu et al, 2021). The development of a single volatility process is within the line shown by previous works for the definition of long-term risks and simplifies the estimation (Bansal et al, 2012;Chen et al, 2017).…”

“…Historically, the level of residuals has played an important role in volatility, as has been proven in past experiences such as the increase in financial markets between 1980 and 2000, and the sharp fall during the 2000 crisis (Chen et al, 2017). However, compared to residual, risks and long-term habit are highly important.…”

“…where V x t jθ ½ represent the theoretical variances of the risk variables conditioned to the other parameters of the model. Is established θ 2 T ¼ 2, so that the unconditional prior variance of the price-dividend ratio is equal to the variance observed in the data (Barro & Jin, 2021;Chen et al, 2017).…”

“…So, given the insecurity in the investment of assets in the football industry, more research and instruments are required to accurately estimate the value of its stocks and to forecast the rate of return of an asset. The asset pricing model provides a way to determine the expected rate of return for an investment and can reliably deal with volatile times, as it establishes the relationship between expected dividends and the risk involved in investing in specific assets (Chen et al, 2017).…”