Analysis of Incomplete Climate Data: Estimation of Mean Values and Covariance Matrices and Imputation of Missing Values.

By Tapio Schneider. 2001

804 citations recorded by the source corpus.

Subfields: Atmospheric Science, Environmental Engineering, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/0bdb29b4786a4c95b73bbef7a69b86da8baa9396

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Environmental Engineering

In Global and Planetary Change

Citations in the corpus

Second Order Cone Programming Approaches for Handling Missing and Uncertain Data (2006, methodology): “(21) Here the setsSi are given bySi = E(x̄i ,Σi ,γi).”
Inferring Missing Climate Data for Agricultural Planning Using Bayesian Networks (2018, methodology): “In agricultural research, data gaps have been filled by combining survey and satellite information [3], spatial interpolations [4], introduction of proxy variables [5], and, in the case of climate research, by using the regularized EM algorithm for Gaussian data [6], empirical orthogonal functions [”
A Tree-Ring-Based Reconstruction of Delaware River Basin Streamflow Using Hierarchical Bayesian Regression (2013, methodology): “In this paper we consider only the continuous common record and do not consider expectation–maximization (EM) or re-lated algorithms (Dempster et al. 1977; Schneider 2001) for gap ﬁlling.”
Fuzzy c-means clustering of incomplete data (2001, methodology): “The interested reader is referred to [24] for details on that particular EM approach and to the web site: http://www.”
Matrix Completion, Counterfactuals, and Factor Analysis of Missing Data (2019, methodology): “Schneider (2001) considered a ridge-regression based regularized EM algorithm for imputing missing values in climate data.”
GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series (2019, methodology): “The actual data is then sporadic and researchers usually resort to imputation before statistical analysis (Junninen et al., 2004; Schneider, 2001).”
Millennial temperature reconstruction intercomparison and evaluation (2006, positive): “maximisation technique (Schneider, 2001) and the MBH1998 climate field reconstruction method and find only minor differences.”
Spatiotemporal filtering for regional GPS network in China using independent component analysis (2017, methodology): “In this work, before performing PCA and ICA, we used the RegEM algorithm to compute missing values (Schneider 2001).”
Genomic Selection in Wheat Breeding using Genotyping‐by‐Sequencing (2012, methodology): “While the MVN-EM algorithm is a common technique in statistics (Little and Rubin, 1987), concise matrix formulations of the problem are harder to i nd. h e following description is taken from Schneider (2001).”
Comparison of missing value imputation methods in time series: the case of Turkish meteorological data (2013, methodology): “Schneider (2001), in his mostly cited study, recommends the use of a regularized EM algorithm for the imputation of incomplete climate data, especially when the number of series to be imputed exceeds the sample size.”
Cognitive Development of Fluent Word Reading Does Not Qualitatively Differ Between Transparent and Opaque Orthographies (2010, methodology): “For the other participants, missing values were imputed with a version of expectation maximization, an imputation method described by Schneider (2001) and implemented in MatLab (Schneider, 2008).”
European summer temperatures since Roman times (2016, positive): “Missing months in the selected cells were in ﬁ lled using the reg-ularised expectation maximisation algorithm with ridge regression ( Schneider 2001 ) to yield a time-con-tinuous monthly anomaly grid over the period 1850 – 2010 CE ( see SOM for details ) .”
High-dimensional covariance matrix estimation with missing observations (2012, methodology): “Existing procedures involve complex imputation techniques to fill in the missing values through computationally intensive implementation of the EM algorithm, see [33] and the references cited therein for more details.”