A Comparison of Five Methods for Missing Value Imputation in Data Sets
Journal Title: International Scientific and Vocational Studies Journal - Year 2018, Vol 2, Issue 2
Abstract
The missing values in the data sets do not allow for accurate analysis. Therefore, the correct imputation of missing values has become the focus of attention of researchers in recent years. This paper focuses on a comparison of most reliable and up to date estimation methods to imputing the missing values. Imputation of missing values has a very high priority because of its impact on next pre-processing, data analysis, classification, clustering, etc. Root mean square error (RMSE) value, classification accuracy and execution time are used to evaluate the performances of most popular five methods (mean, k-nearest neighbors, singular value decomposition, bayesian principal component analysis and missForest). When RMSE and classification accuracy values of methods were compared, it has observed that missForest method outperformed other methods in all datasets.
Authors and Affiliations
Pınar Cihan
Keywords
Related Articles
- EP ID EP35735
- DOI -
- Views 341
- Downloads 0
Thermal Stress Control in Functionally Graded Plates with Artificial Neural Network
In this study, trained models were obtained by using Artificial Neural Network (ANN) in order to determine the equivalent stress levels of one dimensional functionally graded rectangular plates. In this training set, a...
Short-Term Load Forecasting Model Using Flower Pollination Algorithm
Electricity is natural but not a storable resource and has a vital role in modern life. Balancing between consumption and production of the electricity is highly important for power plants and production facilities. Res...
Fabrication of Glazed Porcelain Using Glass Industry by Product Sodium Feldspar
Sodium feldspar (Na2O.Al2O3.6SiO2) (SF) is one of the most important melting materials used in glass fabrication due to its low iron ratios. On the other hand, SF mineral used by glass industry is subjected to classifica...
A Comparison of Five Methods for Missing Value Imputation in Data Sets
The missing values in the data sets do not allow for accurate analysis. Therefore, the correct imputation of missing values has become the focus of attention of researchers in recent years. This paper focuses on a compar...
Improved Compound Multiphase Waveforms with Additional Amplitude Modulation (periodic mode) for Marine Radars
This paper has presented the basis of a compound multiphase waveform design with additional amplitude modulation, capable of controlling a waveform pick-factor, suitable for use with marine radar. The waveform shows goo...