Fat tails and spurious estimation of consumption‐based asset pricing models

Abstract

The standard generalized method of moments (GMM) estimation of Euler equations in heterogeneous-agent consumption-based asset pricing models is inconsistent under fat tails because the GMM criterion is asymptotically random. To illustrate this, we generate asset returns and consumption data from an incomplete-market dynamic general equilibrium model that is analytically solvable and exhibits power laws in consumption. Monte Carlo experiments suggest that the standard GMM estimation is inconsistent and susceptible to Type II errors (incorrect nonrejection of false models). Estimating an overidentified model by dividing agents into age cohorts appears to mitigate Type I and II errors.

On the emergence of a power law in the distribution of COVID-19 cases

“…We may thus expect to observe a power law in the size distribution of a population whose members have been growing like geometric Brownian motions since birth, and whose distribution of ages is exponential. The combination of Gibrat’s law with an exponential age distribution as a generative mechanism for power laws has been used extensively in recent economics literature [7] , [8] , [27] , [28] , [29] , [30] , [31] , [32] , [33] , [34] , [35] , [36] , [37] , [38] , [39] , [40] , [41] . Related techniques have also been employed in the physics literature [42] , [43] , [44] , [45] .…”

Efficient minimum distance estimation of Pareto exponent from top income shares

“…Another example is asset pricing. In a class of consumption‐based asset pricing models, Toda and Walsh (2015, 2017) showed that the relative risk aversion must not exceed the Pareto exponent of household consumption in order for the model to be estimable. In these examples, the shape of the upper tail of the distribution characterized by the Pareto exponent plays an important role, unlike summary statistics such as top shares.…”

Pareto extrapolation: An analytical framework for studying tail inequality

“…44 Other recent applications include firm dynamics (Daron and Cao (2015)), asset pricing (Toda and Walsh (2015, 2017)), dynamics of inequality (Gabaix, Lasry, Lions, and Moll (2016), Aoki and Nirei (2017), Cao and Luo (2017), Kasa and Lei (2018)), entrepreneurship (Jones and Kim (2018)), and the spread of a new infectious disease (Beare and Toda (2020)). For reviews of generative mechanisms of Pareto tails used in these papers, see Gabaix (2009).…”