Spatial Panel-data Models Using Stata

Abstract

xsmle is a new command for spatial analysis using Stata. We consider the quasi-maximum likelihood estimation of a wide set of both fixed-and randomeffects spatial models for balanced panel data. Of special note is that xsmle allows to handle unbalanced panels thanks to its full compatibility with the mi suite of commands, to use spatial weight matrices in the form of both Stata matrices and spmat objects, to compute direct, indirect and total marginal effects and related standard errors for linear (in variables) specifications, and to exploit a wide range of postestimation features, extending to the panel data case the predictors proposed by Kelejian and Prucha (2007). Moreover, it also allows the use of margins to compute total marginal effects in presence of nonlinear specifications obtained using factor variables. This paper describes the command and all its functionalities using both simulated and real data.

Determinants of international tourist choices in Italian provinces: A joint demand–supply approach with spatial effects

“…We estimated all model unknowns by quasi-maximum likelihood using the Stata user-written command xsmle (Belotti, Hughes, & Piano Mortari, 2017). Unlike Florax, Folmer, and Rey (2003) we do not estimate first a simple a-spatial gravity model (δ = 0; ϑ l = 0) and introduce the complexity successively.…”

Climate Change, Salinization and High-Yield Rice Production in Coastal Bangladesh

“…Panel estimation employs the standard xtreg estimator in Stata. Spatial econometric estimation employs the xsmle estimator in Stata, developed by Belotti, Hughes, and Mortari (2014, 2016), who draw on Cameron, Gelbach and Miller (2011), Elhorst (2010), Lee and Yu (2010), and earlier work by Anselin (2001, 2002), Barrios et al (2010), Kapoor, Kelejian and Prucha (2007), Kelejian and Prucha (1998), Kelejian, Prucha, and Yuzefovich (2004), and Kelejian and Prucha (2006).…”

Avian Influenza, Public Opinion, and Risk Spillover: Measurement, Theory, and Evidence from China’s Broiler Market

“…Fourth, in column (8), squared public opinion is further added. Following the model selection criteria (R 2 , log likelihood, AIC and BIC), described in Elhorst [93] and Belotti, Hughes and Mortari [94], column (8) fits better than column (7). Squared public opinion in column (8) is still significantly negative and other coefficients remain similar to column (7), reflecting the fact that there is an inverse U-shaped relationship between broiler price and public opinion, lending support to theoretical hypothesis H3.…”