Anyone is free to use these routines, no attribution (or blame)
need be placed on the author/authors.
MATLAB static spatial panel data econometrics functions for:
- OLS and Bayesian panel regressions
- Maximum Likelihood SAR, SDM, SDEM SEM, SLX and Bayesian MCMC variants
- SAR, SDM, SDEM SEM, Convex combinations of spatial weight matrices
- BMA (Bayesian model averaging for convex combination of weights models)
- See Debarsy and LeSage (2021a), Using convex combinations of
spatial weights in spatial autoregressive models, Handbook of Regional Science,
2nd Edition, M. M. Fischer and Peter Nijkamp (Eds.) Springer, Berlin 2021.
See Debarsy and LeSage (2021b), Bayesian Model Averaging for Spatial Autoregressive
Models Based on Convex Combinations of Different Types of Connectivity Matrices,
Journal of Business & Economic Statistics.
Demonstrations are provided for almost
all functions and a 150 page
manual in Acrobat PDF format (See Documentation)
The demo files consist of files with the function
name and a trailing letter d. For example: the
sar_panel_FE_g.m function demo file is named sar_panel_FE_gd.m, and
the ols_panel_FE_g.m demo file is named ols_panel_FE_gd.m
Demos are organized by 7 Chapters in the manual
Estimation functions provide printed and graphical output
and the convex combination of weight matrices functions
can be used to produce cross-sectional model estimates.
Bayesian log-marginal likelihoods for static panel data model comparison.
See LeSage (2014) Spatial econometric panel data model specification: A Bayesian approach,
Spatial Statistics Volume 9, Issue C, pp. 122-145.