Arfima-MLM Estimation For Repeated Cross-Sectional Data And Pooled Cross-Sectional Time-Series Data
This package provides functions to facilitate the estimation of Arfima-MLM models for repeated cross-sectional data and pooled cross-sectional time-series data (see Lebo and Weber 2015). The estimation procedure uses double filtering with Arfima methods to account for autocorrelation in longer repeated cross-sectional data followed by multilevel modeling (MLM) to estimate both aggregate- and individual-level parameters simultaneously.
The main function of the package is
arfimaMLM, which implements Arfima and multilevel models on a repeated cross-sectional dataset as described by Lebo and Weber (forthcoming). Furthermore, the function
arfimaOLS uses the same initial procedures but estimates a simple linear model instead of the multilevel model. The package also includes
arfimaPrep, which prepares a dataset for subsequent analyses according to the Arfima-MLM framework without estimating the final model itself.
fd is a wrapper function to estimate the fractional differencing parameter using
hurstSpec of the
fractal-package as well as procedures provided by the
fracdiff-package (via ML, GPH, and Sperio) and to differentiate the series accordingly (mainly for internal use in
Patrick Kraft, with contributions from Christopher Weber
Maintainer: Patrick Kraft <firstname.lastname@example.org>
Lebo, M. and Weber, C. 2015. “An Effective Approach to the Repeated Cross Sectional Design.” American Journal of Political Science 59(1): 242-258.
Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.