2023
DOI: 10.1038/s43856-023-00356-z
|View full text |Cite
|
Sign up to set email alerts
|

The impact of imputation quality on machine learning classifiers for datasets with missing values

Tolou Shadbahr,
Michael Roberts,
Jan Stanczuk
et al.

Abstract: Background Classifying samples in incomplete datasets is a common aim for machine learning practitioners, but is non-trivial. Missing data is found in most real-world datasets and these missing values are typically imputed using established methods, followed by classification of the now complete samples. The focus of the machine learning researcher is to optimise the classifier’s performance. Methods We utilise three simulated and three real-world … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

1
0
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 20 publications
(1 citation statement)
references
References 37 publications
1
0
0
Order By: Relevance
“…The distribution of imputed and observed data were similar, which suggest that the imputed values were plausible [ 50 ]. This is in agreement with the previous finding that MICE performs better compared to deep learning imputation methods such as generative adversarial imputation network (GAIN), and multiple imputation using denoising autoencoders (MIDA) [ 51 , 52 ]. Comparisons of model performance include several aspects.…”
Section: Limitationssupporting
confidence: 92%
“…The distribution of imputed and observed data were similar, which suggest that the imputed values were plausible [ 50 ]. This is in agreement with the previous finding that MICE performs better compared to deep learning imputation methods such as generative adversarial imputation network (GAIN), and multiple imputation using denoising autoencoders (MIDA) [ 51 , 52 ]. Comparisons of model performance include several aspects.…”
Section: Limitationssupporting
confidence: 92%