Model selection to improve multiple imputation for handling high rate missingness in a water quality dataset.
Romy RatolojanaharyRaymond Houé NgounaKamal MedjaherJean Junca-BouriéFabien DauriacMathieu SebiloPublished in: Expert Syst. Appl. (2019)
Keyphrases
- model selection
- high rate
- water quality
- missing data
- cross validation
- multiple imputation
- hyperparameters
- low rate
- regression model
- missing values
- measured data
- variable selection
- statistical inference
- mixture model
- feature selection
- model selection criteria
- automatic model selection
- information criterion
- marginal likelihood
- neural network
- machine learning
- data mining
- gaussian process
- parameter determination
- water treatment
- selection criterion
- statistical databases
- incomplete data
- imputation methods
- closed form
- breast cancer
- object detection
- database