Bayesian estimation of multivariate panel probits with higher‐order network interdependence and an application to firms' global market participation in Guangdong

Abstract

This paper proposes a Bayesian estimation framework for panel data sets with binary dependent variables where a large number of cross-sectional units are observed over a short period of time and cross-sectional units are interdependent in more than a single network domain. The latter provides for a substantial degree of flexibility towards modeling the decay function in network neighborliness (e.g., by disentangling the importance of rings of neighbors) or towards allowing for several channels of interdependence whose relative importance is unknown ex ante. Besides the flexible parameterization of cross-sectional dependence, the approach allows for simultaneity of the equations. These features should make the approach interesting for applications in a host of contexts involving structural and reduced-form models of multivariate choice problems at micro-, meso-, and macro-economic levels. The paper outlines the estimation approach, illustrates its suitability by simulation examples, and provides an application to study exporting and foreign ownership among potentially interdependent firms in the specialized and transport machinery sector in the province of Guangdong.

Best linear and quadratic moments for spatial econometric models with an application to spatial interdependence patterns of employment growth in US counties

“…When $$$ {\beta}_0\ne 0 $$$, instrumental variables are available, and the parameters in the model are generally identifiable; when $$$ {\beta}_0=0 $$$ and there is no prior information on the magnitudes of $$$ {\lambda}_0 $$$ and $$$ {\rho}_0 $$$, for parameter identification, the set of spatial weight matrices $$$ \left\{{W}_{1n},\dots, {W}_{l_wn}\right\} $$$ for spatial lags should be different from $$$ \left\{{M}_{1n},\dots, {M}_{l_mn}\right\} $$$ for spatial errors. Model () embodies multiple spatial interdependence, which is especially useful when researchers want to investigate multiple possible channels of interdependence or allow for flexible rates of decay of interdependence (Baltagi et al, 2022; Gupta & Robinson, 2015; Lee & Liu, 2010, etc.). Furthermore, Model () considers spatial errors in a high‐order form as additional sources of spatial dependence.…”

“…There are a few merits of analyzing this class of models. First, the high‐order model allows researchers to investigate a number of channels of interdependence by estimating parameters for each channel represented by different weight matrices (Baltagi et al, 2022) and may be considered as an alternative to a poorly specified spatial weight matrix (Anselin & Bera, 1998). Second, the SARAR model allows spatial errors, which captures important spatial interdependence due to unobserved explanatory variables (Cliff & Ord, 1973; Kelejian & Prucha, 1998, 2010, to name a few).…”

Chinese regions' participation in global value chains and the associated global transmission of export price and quantity shocks

“…The latter informs us about the spillovers. Notably, $$$$ {\hat{f}}_t={\hat{Z}}_t{\iota}_{SN}, $$$$ informs us about the spillovers from other units and $$$$ {\hat{o}}_t={\hat{Z}}_t^{\prime }{\iota}_{SN}, $$$$ captures the spillovers on other units (see Baltagi et al, 2023).…”

Estimation of the Directions for Unknown Parameters in Semiparametric Models

“…In this section, we apply our proposed methodology to a real dataset that studies the influence of series exporting determined variables on the export-market participation of specialized and transport facility manufactures in the province of Guangdong, China in 2006 (Baltagi et al, 2022). The data is available on the National Bureau of Statistics of China (NBS).…”