Optimal Buy-and-Hold Trading Algorithms

Abstract

For data with correlation across space and over time, the literature concerning the estimation of fixed effects is limited. In this talk, I utilize the concept of quasi-likelihood functions to develop an estimating equation to estimate parameters. Under separable correlation models, the quasi-likelihood estimate is shown to be asymptotically optimal among all unbiased linear estimates. A series of simulations is conducted to assess the finite sample properties of the proposed estimating equation, and to evaluate how the efficiency varies with the regression coefficients. We also compare the relative efficiency with another estimating equation by simulations. The proposed method is applied to an ecological study of forest decline to test independence of two spatial-temporal binary outcomes.