Imputation of missing values for compositional data using classical and robust methods

By Karel Hron, Matthias Templ, Peter Filzmoser. Computational Statistics & Data Analysis, 2010

295 citations recorded by the source corpus.

How researchers see this paper

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

robCompositions: An R‐package for Robust Statistical Analysis of Compositional Data (2011, methodology): “Furthermore, methods to improve the quality of compositional data sets are implemented, like outlier detection (Filzmoser et al., 2008), and imputation of missing values (Hron et al, 2010).”
Bayesian-multiplicative treatment of count zeros in compositional data sets (2015, methodology): “RD–1 (Egozcue et al., 2003), e.g., the transformation defined in Hron et al. (2010) where , , …, .lnz D i D i x x i D1 1 1i j j i D D i i 1 = - + - = - = + - % (1.1) 136 Josep-Antoni Martín-Fernández et al. Statistical Modelling 2015; 15(2): 134–158 Since the 1990s, numerous publications have…”
On the Interpretation of Orthonormal Coordinates for Compositional Data (2011, background): “This is a popular choice of balances as z1 contains all the relative information of the part x1 with respect to other parts in the composition; that is, it stands for all the ratios of x1 to the remaining parts (Egozcue and Pawlowsky-Glahn 2006; Filzmoser et al. 2009b; Hron et al. 2010).”
Flexible Imputation of Missing Data (2012, background): “Imputation of compositional data has only recently received attention (Tempelman, 2007; Hron et al., 2010; De Waal et al., 2011).”
Linear regression with compositional explanatory variables (2012, background): “One choice which is used in different contexts [10,11,15] results in a (D − 1)-dimensional real vector z = (z1, .”