NEAREST NEIGHBOR BIAS IN THE SUBSTITUTION OF MISSING VALUES
Schlagwörter:
Mapping, Nearest Neighbor Imputation, Nearest Neighbor Bias, Large-area Forest Inventories, Multi-source Data Fusion.Abstract
This is a short technical note illustrating the bias inherent in the general case of the Nearest Neighbor (NN) method used to substitute missing values. This presentation doesn't make any assumptions about the geometry of the sampled subjects. The general examples illustrate that the bias exists mainly at the limits of the data range and not necessarily within the center part of the range. However, the latter is also possible around any significant data gaps. The NN data domain stretches across an arbitrary subject characteristic rather than across the physical space. It is possible to reduce the discussed here biases by assuring that the domain range of the considered attribute is well-represented within its entire range, especially at its upper and lower limits and there are no major gaps in the training data.
Literaturhinweise
Czaplewski, R. 2010. Review of: Nearest Neighbor Bias -- A simple example. Mathematical and Computational Forestry & Natural-Resource Sciences (MCFNS), 2(1), Pages: 66-66 (1). Retrieved from https://mcfns.net/index.php/Journal/article/view/MCFNS.2-66
Haara, A., & Kangas, A. 2012. Comparing K Nearest Neighbours Methods and Linear Regression – Is There Reason To Select One Over the Other?. Mathematical and Computational Forestry & Natural-Resource Sciences (MCFNS), 4(1), Pages: 50-65 (16). Retrieved from https://mcfns.net/index.php/Journal/article/view/MCFNS.4%3A50
Iles, K. 2010. Nearest Neighbor Bias -- A simple example. Mathematical and Computational Forestry & Natural-Resource Sciences (MCFNS), 2(1), Pages: 18-19 (2). Retrieved from https://mcfns.net/index.php/Journal/article/view/MCFNS.2-18
Iles, K. 2009. “Total-Balancing” an inventory: A method for unbiased inventories using highly biased non-sample data at variable scales. MCFNS. 1(1):10-13. http://mcfns.com/index.php/Journal/article/view/MCFNS-1:10/18
Lowe, R., & Cieszewski, C. 2014. Multi-source K-nearest neighbor, Mean Balanced forest inventory of Georgia. Mathematical and Computational Forestry & Natural-Resource Sciences (MCFNS), 6(2), 65-79 (15). Retrieved from https://mcfns.net/index.php/Journal/article/view/6_65/184
Downloads
Veröffentlicht
Ausgabe
Rubrik
Lizenz
Authors who publish with this journal agree to the following terms:- Authors grant the journal right of first publication, with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) following the publication by the journal, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
