Ridge Fuzzy Regression Modelling for Solving Multicollinearity

Kim, Hyoshin; Jung, Hyuk-Sang

doi:10.3390/math8091572

Cited by 13 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One of the problems that often occurs in regression data is that there is a strong correlation between predictor variables so that the classical assumption or linear regression, namely nonmulticollinearity, is prone to being violated. A strong correlation between predictor variables will cause parameter estimates using the least squares method to be obtained with a large effect of parameter estimator variance or even cannot be obtained (H. Kim & Jung, 2020). This problem can be solved by using Principal Component Regression (PCR) method which is a combination analysis between multiple linear regression and Principal Component Analysis (PCA).…”

Section: A Introductionmentioning

confidence: 99%

Principal Component Regression Modelling with Variational Bayesian Approach to Overcome Multicollinearity at Various Levels of Missing Data Proportion

Balqis

Astutik

Solimun

2022

JTAM

View full text Add to dashboard Cite

This study aims to model Principal Component Regression (PCR) using Variational Bayesian Principal Component Analysis (VBPCA) with Ordinary Least Square (OLS) as a method of estimating regression parameters to overcome multicollinearity at various levels of the proportion of missing data. The data used in this study are secondary data and simulation data contaminated with collinearity in the predictor variables with various missing data proportions of 1%, 5%, and 10%. The secondary data used is the Human Depth Index in Java in 2021, complete data without missing values. The results indicate that the multicollinearity in secondary and original data can be optimally overcome as indicated by the smaller standard error value of the regression parameter for the PCR using VBPCA method which is smaller and has a relative efficiency value of less than 1. VBPCA can handle the proportion of missing data to less than 10%. The proportion of missing data causes information from the original variable to decrease, as evidenced by immense MAPE value and the parameter estimation bias that gets bigger. Then the cross validation (Q^2 ) value and the coefficient of determination (adjusted R^2 ) are get smaller as the proportion of missing data increases.

show abstract

Section: A Introductionmentioning

confidence: 99%

Principal Component Regression Modelling with Variational Bayesian Approach to Overcome Multicollinearity at Various Levels of Missing Data Proportion

Balqis

Astutik

Solimun

2022

JTAM

View full text Add to dashboard Cite

show abstract

“…Kim and Jung suggested α-level estimation algorithm for ridge fuzzy regression modeling. By including α-levels in the estimation process, a fuzzy ridge estimator that is independent of the distance between fuzzy numbers is created 28 . To manage water resources, Wang et al incorporated a number of risk control constraints, such as water availability, maximum permitted penalties, and allowable benefit violation limitations, into a fuzzy border interval two-stage stochastic programming framework.…”

mentioning

confidence: 99%

Fuzzy optimal control of multilayer coverage based on radon exhalation dynamics in uranium tailings

Zhang

Jian-yong

2023

Sci Rep

View full text Add to dashboard Cite

Radon exhalation from uranium tailings has seriously affected environmental safety and human health. Many uncertain parameters, such as diffusion coefficient, porosity, percolation rate, material particle size, etc., are related to the diffusion and migration of radon. Moreover, cover materials, cover layers, and cover thickness are the main instruments to control radon exhalation, and the radon reduction effect of single-layer mulching is often inferior to that of the multilayer. Hence, achieving radon control with multilayer coverage under uncertain environment is an urgent problem that must be solved in the area of nuclear safety and radiation environment. In an attempt to address the issue, a dynamic model of radon exhalation with multilayer coverage is constructed using radon percolation-diffusion migration equation, and triangular membership functions inscribe the model parameters; the objective functions of the left and right equations of the model are constructed, and their extreme value intervals are obtained using immunogenetic algorithm. Then, subject to the total cost and thickness of multilayer covering materials, the fuzzy objective and constraint models of radon exhalation are constructed, and the fuzzy aggregation function is reconstructed according to the importance of the fuzzy objective and constraint models, where ultimately, the optimal radon control decision by swarm intelligence algorithm under different possibility levels and importance conditions can be obtained. An example is then used to validate the effectiveness of the radon exhalation model, and to demonstrate that fuzzy optimization provides a database of decision-making schemes regarding multilayer coverage, and guidance for optimal control and flexible construction management.

show abstract

“…Sedangkan, metode time series umumnya membutuhkan lebih banyak data historis dengan syarat distribusi normal. Metode Fuzzy Linear Regression (FLR) adalah metode yang dapat memodelkan peramalan dengan pendekatan fuzzy yang menghasilkan akurasi tinggi dengan prediksi sesuai jumlah kasus yang sebenarnya [6][7][8][9].…”

unclassified

Model Peramalan Jumlah Penyakit Demam Berdarah Dengan Pendekatan Metode Fuzzy Linear Regression (Flr)

Khotimah¹,

Rochman²

2021

NERO

View full text Add to dashboard Cite

Peramalan sangat penting pada data time series, yang diperlukan dalam proses pengambilan keputusan. Penelitian ini memprediksi jumlah demam berdarah sebagai output variabel terikat (Y) dan faktor keterangan kondisi pasien parah (X1) dan kondisi ringan X2 sebagai variabel bebas. Peramalan time series menggunakan fuzzy untuk menjelaskan data dalam bentuk nilai-nilai lingusitik. Regresi fuzzy digunakan untuk memperbaiki adanya error dalam permodelan klasik. Hasil peramalan konvensional terdapat perbedaan antara nilai yang diamati dan nilai yang diestimasi yang dikenal error, tetapi dalam regresi fuzzy dikenal sebagai kerancuan (ambiguity) sistem. Penelitian ini menggunakan metode Fuzzy Linear Regression (FLR) untuk memodelkan peramalan jumlah penyakit demam berdarah. Penelitian ini bertujuan untuk menghasilkan parameter berupa interval (upper bound dan lower bound) pada hasil ramalan, yang dapat digunakan dalam pengambilan keputusan pada segala kemungkinan terbaik maupun terburuk. Hasil penelitian berdasarkan interval dengan mengubah-ubah nilai (h) = 0; 0,25; dan 0,5; 0.75 dihasilkan dengan metode Fuzzy linier regression Time Series pada koefisien determinasi terkecil senilai 0,238 pada h=0,25 dengan kesalahan simpangan baku terkecil 3,94.

show abstract

Ridge Fuzzy Regression Modelling for Solving Multicollinearity

Cited by 13 publications

References 34 publications

Principal Component Regression Modelling with Variational Bayesian Approach to Overcome Multicollinearity at Various Levels of Missing Data Proportion

Principal Component Regression Modelling with Variational Bayesian Approach to Overcome Multicollinearity at Various Levels of Missing Data Proportion

Fuzzy optimal control of multilayer coverage based on radon exhalation dynamics in uranium tailings

Model Peramalan Jumlah Penyakit Demam Berdarah Dengan Pendekatan Metode Fuzzy Linear Regression (Flr)

Contact Info

Product

Resources

About