yaImpute: An R Package for kNN Imputation

By N. Crookston, Andrew O. Finley. 2008

399 citations recorded by the source corpus.

This article introduces yaImpute, an R package for nearest neighbor search and imputation. Although nearest neighbor imputation is used in a host of disciplines, the methods implemented in the yaImpute package are tailored to imputation-based forest attribute estimation and mapping. The impetus to writing the yaImpute is a growing interest in nearest neighbor imputation methods for spatially explicit forest inventory, and a need within this research community for software that facilitates comparison among different nearest neighbor search algorithms and subsequent imputation techniques. yaImpute provides directives for defining the search space, subsequent distance calculation, and imputation rules for a given number of nearest neighbors. Further, the package offers a suite of diagnostics for comparison among results generated from different imputation analyses and a set of functions for mapping imputation results.

Subfields: Environmental Engineering, Nature and Landscape Conservation, Signal Processing

View Paper: https://www.semanticscholar.org/paper/70cb67c39c53ebf750a873c91eb9a7d1aded159d

How researchers see this paper

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

In Environmental Engineering

In Nature and Landscape Conservation

In Signal Processing

Citations in the corpus

A random forest guided tour (2015, methodology): “3.2.Data imputation based on random forests has further been explored by Rieger et al. (2010), Crookston and Finley (2008), and extended to unsupervised classification by Ishioka (2013).”
Variable selection strategies for nearest neighbor imputation methods used in remote sensing based forest inventory (2012, methodology): “The sudden influx of papers in this area was probably due to the release of the R package ‘‘yaImpute’’ (Crookston and Finley, 2008).”
Evaluation of most similar neighbour and random forest methods for imputing forest inventory variables using data from target and auxiliary stands (2012, methodology): “As a k-NN imputation method, the distance between target and reference units is calculated as ‘one minus the proportion of terminal nodes from all regression trees where the target observation is in the same terminal node as the specific reference unit’ (Crookston and Finley 2008).”
Comparison of nearest neighbour approaches for small area estimation of tree species-specific forest inventory attributes in central Europe using airborne laser scanner data (2010, methodology): “We used the yaImpute package (Crookston and Finley 2008) that calls the randomForest package (Liaw and Wiener 2002) for the MSN and RF approaches and the party package (Hothorn et al.”
Comparison of airborne laser scanning methods for estimating forest structure indicators based on Lorenz curves (2014, methodology): “A combination of RF and k-NN is an approach where a distance metric used in k-NN is determined based on RF proximity matrix (NN– RF) (Crookston and Finley, 2008).”
Predicting the spatial pattern of trees by airborne laser scanning (2013, methodology): “Nearest neighbours were searched for using the Random Forest (RF) distance metric implemented in the R package yaImpute (Crookston and Finley 2008).”
Non-parametric prediction and mapping of standing timber volume and biomass in a temperate forest: application of multiple optical/LiDAR-derived predictors (2010, methodology): “Recently, the regression tree-based classification method of Random Forests (RF) (Breiman, 2001) is adapted as a NN method in which the observations are treated as similar if they tend to end up in the same terminal node in a suitably constructed collection of classification and regression trees (Cr”
Modeling Species Distribution and Change Using Random Forest (2011, methodology): “Crookston and Finley (2008) derived a method for using the scaled proximities to perform nearest neighbor multiple-imputation.”
Differences in spatial predictions among species distribution modeling methods vary with species traits and environmental predictors (2009, neutral): “0 3 (Crookston and Finley 2008).”
Imputation with the R Package VIM (2016, methodology): “A wide range of single imputation algorithms are available, e.g., in the R ( R Core Team 2016) packages yaImpute (Crookston and Finley 2008), missMDA (Josse and Husson 2016), CoImp (Lascio and Giannerini 2016), as well as multiple imputation methods, e.g., in the R packages mice (van Buuren and…”