cranedroesch/panelNNET: Semiparametric panel data models using neural networks

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.

Getting started

Package details

AuthorAndrew Crane-Droesch
MaintainerAndrew Crane-Droesch <[email protected]>
LicenseGPL (>= 2)
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
cranedroesch/panelNNET documentation built on Aug. 31, 2018, 9:22 p.m.