DESCRIPTION

Package: panelNNET
Type: Package
Title: Semiparametric panel data models using neural networks
Version: 1.0
Date: 2017-10-10
Author: Andrew Crane-Droesch
Maintainer: Andrew Crane-Droesch <andrew.crane-droesch@ers.usda.gov>
Description: Fits fixed-effects models for panel data, in which some terms may enter linearly and others may enter non-parametrically.  The nonparametric terms are represented by either feed-forward or convolutional neural networks, with arbitrarily-many hidden layers and hidden units per layer.  Disclaimer:  this code is that of the author and should not be attributed to the Economic Research Service or USDA.
License: GPL (>= 2)
Depends: lfe, foreach, MASS, Matrix, doBy, matrixStats
Imports: Rcpp (>= 0.12.13), RcppEigen (>= 0.3.3.3.0)
LinkingTo: Rcpp, RcppEigen
RoxygenNote: 6.0.1