Abstract: This paper presents a software package called BACE (BayesianAveraging of Classical
Estimates) which offers model-building strategy for various limited dependent
variable models, including logit and probit models, ordered logit and probit models,
multinomial logistic regression, Poisson regression, Tobit model, and interval
regression. BACE strategy is a model selection method that incorporates both classical
estimation and Bayesian techniques. It solves the problem of computation
speed and model uncertainty that arise when dealing with a large number of competing
advanced statistical models. Our BACE package is both fast and capable
of delivering consistent results. The package also provides implementation of the
latest proposals of BIC variants, and the latest measures of jointness. We use gretl,
a popular, free, and open-source software for econometric analysis that features an
easy-to-use graphical user interface.
Abstract: This package deals with the estimation of dynamic factor models (DFM); for the moment, three factor extraction techniques are available, but we plan to add more in future versions. Further additions will include parameter restrictions.
Paper nr. 6
Title: BAYESIAN AVERAGING OF CLASSICAL ESTIMATES (BACE) FOR GRETL
Abstract: This paper presents a software package that implements Bayesian Averaging of Classical Estimates BACE ver. 1.1 for gretl (the GNU regression, econometrics and time-series library).
Abstract: The SVAR addon is a collection of gretl functions to estimate Structural Vector Autoregressions (SVARs) and to conduct inference on the resulting magnitudes such as the impulse response functions and short-run or long-run impact matrices. For the purpose of identifying the structural shocks short-run as well as long-run restrictions are supported, including those related to the cointegration properties in the case of non-stationary systems. For the stationary case a dialog-driven graphical interface is also offered. Inference can be based on the bootstrap, optionally using a bias correction as suggested in the literature. This documentation explains the addon's usage, capabilites and limitations, and provides some necessary econometric methodological background (version 1.32).
Paper nr. 4
Title: RANDOM EFFECTS ESTIMATORS FOR UNBALANCED PANEL DATA: A MONTE CARLO ANALYSIS
Abstract: We clarify a point regarding the appropriate measure(s) of the variance of smoothed disturbances in the context of linear state-space models. This involves explaining how two different concepts, which are sometimes given the same name in the literature, relate to each other. We also describe the behavior of several common software packages is in this regard.
Paper nr. 2
Title: BAYESIAN MODEL AVERAGING AND JOINTNESS MEASURES FOR GRETL
Abstract: This paper presents a software package that implements Bayesian model averaging for gretl, the GNU regression, econometrics and time-series library. Bayesian model averaging is a model-building strategy that takes account of model uncertainty in conclusions about estimated parameters. It is an efficient tool for discovering the most probable models and obtaining estimates of their posterior characteristics. In recent years we have observed an increasing number of software packages devoted to Bayesian model averaging for different statistical and econometric software. In this paper, we propose the BMA package for gretl, which is an increasingly popular free, open-source software for econometric analysis with an easy-to-use graphical user interface. We introduce the BMA package for linear regression models with jointness measures proposed by Ley and Steel (2007) and Doppelhofer and Weeks (2009).
Paper nr. 1
Title: DPB: DYNAMIC PANEL BINARY DATA MODELS IN GRETL
Abstract: This paper presents the Gretl function package DPB for estimating dynamic binary models with panel data. The package contains routines for the estimation of the random-effects dynamic probit model proposed by Heckman (1981b) and its generalisation by Hyslop (1999) and Keane and Sauer (2009) to accommodate AR(1) disturbances. The fixed-effects estimator by Bartolucci and Nigro (2010) is also implemented. DPB is available on the Gretl function packages archive. Revision-Date: 2015-04-24