Narrow search
Showing 1 - 10 of 281
Cover Image
Online action learning in high dimensions: a new exploration rule for contextual et-greedy heuristics
Flores, Claudio C.; Medeiros, Marcelo C. - 2020
Bandit problems are pervasive in various fields of research and are also present in several practical applications … one of the most popular bandit solutions, the original et-greedy heuristics, to high-dimensional contexts. Moreover, we … range of exploration of new actions. We find reasonable bounds for the cumulative regret of a decaying et-greedy heuristic …
Persistent link: https://www.econbiz.de/10012292092
Cover Image
Stable graphical model estimation with Random Forests for discrete, continuous, and mixed variables
Fellinghauer, Bernd; Bühlmann, Peter; Ryffel, Martin; … - In: Computational Statistics & Data Analysis 64 (2013) C, pp. 132-152
Random Forests in combination with Stability Selection allow to estimate stable conditional independence graphs with an error control mechanism for false positive selection. This approach is applicable to graphs containing both continuous and discrete variables at the same time. Its performance...
Persistent link: https://www.econbiz.de/10011056520
Cover Image
Short-term forecasting with mixed-frequency data: A MIDASSO approach
Siliverstovs, Boriss - 2015
-Sampling approach (U-MIDAS) (see Foroni et al., 2015; Castle et al., 2009; Bec and Mogliani, 2013), and the LASSO-type penalised …
Persistent link: https://www.econbiz.de/10011307779
Cover Image
Dissecting the Purchasing Managers' Index: Are all relevant components included? Are all included components relevant?
Siliverstovs, Boriss - 2015
We apply the novel approach of Siliverstovs (2015) to modelling data sampled at different frequencies in order to scrutinise the composition of one of the most influential economic indicators in Switzerland. The Purchasing Managers' Index consists of eight sub-indices out of which only five...
Persistent link: https://www.econbiz.de/10011307780
Cover Image
Program evaluation with high-dimensional data
Belloni, Alexandre; Chernozhukov, Victor; … - 2013
We consider estimation of policy relevant treatment effects in a data-rich environ ment where there may be many more control variables available than there are observations. In addition to allowing many control variables, the setting we consider allows heterogeneous treatment effects, endogenous...
Persistent link: https://www.econbiz.de/10010368188
Cover Image
Google data in bridge equation models for German GDP
Götz, Thomas B.; Knetsch, Thomas A. - 2017
partial least squares and LASSO appear most promising. Also, the forecast potential of Google search terms vis-avis survey …
Persistent link: https://www.econbiz.de/10011667607
Cover Image
LASSO-type penalization in the framework of generalized additive models for location, scale and shape
Groll, Andreas; Hambuckers, Julien; Kneib, Thomas; … - 2018
options are provided: the conventional least absolute shrinkage and selection operator (LASSO) for metric covariates, and both … group and fused LASSO for categorical predictors. The methods are investigated both for simulated data and for two real data …
Persistent link: https://www.econbiz.de/10011930753
Cover Image
LASSO-driven inference in time and space
Chernozhukov, Victor; Härdle, Wolfgang; Huang, Chen; … - 2018
of large-scale regressions with LASSO is applied to reduce the dimensionality, and an overall penalty level is carefully …
Persistent link: https://www.econbiz.de/10011941488
Cover Image
A Hodrick-Prescott filter with automatically selected jumps
Maranzano, Paolo; Pelagatti, Matteo - 2024
The Hodrick-Prescott filter is a popular tool in macroeconomics for decomposing a time series into a smooth trend and a business cycle component. The last few years have witnessed global events, such as the Global Financial Crisis, the COVID-19 pandemic, and the war in Ukraine, that have had...
Persistent link: https://www.econbiz.de/10014581212
Cover Image
Arellano-Bond lasso estimator for dynamic linear panel models
Chernozhukov, Victor; Fernández-Val, Iván; Huang, Chen; … - 2024
most informative moment conditions, motivating the following approach to remove the bias: First, apply LASSO to the cross …
Persistent link: https://www.econbiz.de/10014581834