a research paper about FDSLRM modeling with supplementary materials - software, notebooks
Authors: Andrej Gajdoš, Jozef Hanč, Martina Hančová
Faculty of Science, P. J. Šafárik University in Košice, Slovakia
email: [email protected], [email protected]
Supplementary materials for EBLUP-NE
Estimating variances in FDSLRMs via EBLUPs and convex optimization
Index
Electricity consumption - toy model 1
PY-estimation-electricity1-SciPyCVXPY.ipynb, EBLUP-NE in SciPy, CVXPY
PY-estimation-electricity1-SageMath.ipynb, EBLUP-NE in SageMath
R-estimation-electricity1-CVXR.ipynb, EBLUP-NE in CVXR
R-estimation-electricity1-standardRtools.ipynb, EBLUP-NE in nlme, MMEinR, sommer, fdslrm
Electricity consumption - toy model 2
PY-estimation-electricity2-SciPyCVXPY.ipynb, EBLUP-NE in SciPy, CVXPY
PY-estimation-electricity2-SageMath.ipynb, EBLUP-NE in SageMath
R-estimation-electricity2-CVXR.ipynb, EBLUP-NE in CVXR
R-estimation-electricity2-standardRtools.ipynb, EBLUP-NE in nlme, MMEinR, sommer, fdslrm
Tourism
tourism.ipynb, FDSLRM modeling in R
PY-estimation-tourism-SciPyCVXPY.ipynb, EBLUP-NE in SciPy, CVXPY
R-estimation-tourism-CVXR.ipynb, EBLUP-NE in CVXR
R-estimation-tourism-standardRtools.ipynb, EBLUP-NE in nlme, MMEinR, sommer, fdslrm
Cyber attacks
cyberattacks.ipynb, FDSLRM modeling in R
PY-estimation-cyberattacks-SciPyCVXPY.ipynb, EBLUP-NE in SciPy, CVXPY
R-estimation-cyberattacks-CVXR.ipynb, EBLUP-NE in CVXR
R-estimation-cyberattacks-standardRtools.ipynb, EBLUP-NE in nlme, MMEinR, sommer, fdslrm
References
This notebook belongs to suplementary materials of the paper submitted to Statistical Papers and available at https://arxiv.org/abs/1905.07771.
Hančová, M., Vozáriková, G., Gajdoš, A., Hanč, J. (2019). Estimating variance components in time series linear regression models using empirical BLUPs and convex optimization, https://arxiv.org/, 2019.
Abstract of the paper
We propose a two-stage estimation method of variance components in time series models known as FDSLRMs, whose observations can be described by a linear mixed model (LMM). We based estimating variances, fundamental quantities in a time series forecasting approach called kriging, on the empirical (plug-in) best linear unbiased predictions of unobservable random components in FDSLRM.
The method, providing invariant non-negative quadratic estimators, can be used for any absolutely continuous probability distribution of time series data. As a result of applying the convex optimization and the LMM methodology, we resolved two problems theoretical existence and equivalence between least squares estimators, non-negative (M)DOOLSE, and maximum likelihood estimators, (RE)MLE, as possible starting points of our method and a practical lack of computational implementation for FDSLRM. As for computing (RE)MLE in the case of observed time series values, we also discovered a new algorithm of order , which at the default precision is times more accurate and times faster than the best current Python(or R)-based computational packages, namely CVXPY, CVXR, nlme, sommer and mixed.
We illustrate our results on three real data sets electricity consumption, tourism and cyber security which are easily available, reproducible, sharable and modifiable in the form of interactive Jupyter notebooks.
Gajdoš A., Hanč J., and Hančová M. (2019). fdslrm EBLUP-NE. GitHub repository, P.J. Šafárik University in Košice, Slovakia. https://github.com/fdslrm/EBLUP-NE