New Partially Linear Regression and Machine Learning Models Applied to Agronomic Data
Regression analysis can be appropriate to describe a nonlinear relationship between the response variable and the explanatory variables. This article describes the construction of a partially linear regression model with two systematic components based on the exponentiated odd log-logistic normal di...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Axioms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1680/12/11/1027 |
| _version_ | 1797460166363316224 |
|---|---|
| author | Gabriela M. Rodrigues Edwin M. M. Ortega Gauss M. Cordeiro |
| author_facet | Gabriela M. Rodrigues Edwin M. M. Ortega Gauss M. Cordeiro |
| author_sort | Gabriela M. Rodrigues |
| collection | DOAJ |
| description | Regression analysis can be appropriate to describe a nonlinear relationship between the response variable and the explanatory variables. This article describes the construction of a partially linear regression model with two systematic components based on the exponentiated odd log-logistic normal distribution. The parameters are estimated by the penalized maximum likelihood method. Simulations for some parameter settings and sample sizes empirically prove the accuracy of the estimators. The superiority of the proposed regression model over other regression models is shown by means of agronomic experimentation data. The predictive performance of the new model is compared with two machine learning techniques: decision trees and random forests. These methods achieved similar prediction performance, i.e., none stands out as a better predictor. In this sense, the objective of the research is to choose the best method. If the objective is only predictive, the decision tree can be used due to its simplicity. For inference purposes, the regression model is recommended, which can provide much more information regarding the relationship of the variables under study. |
| first_indexed | 2024-03-09T17:01:15Z |
| format | Article |
| id | doaj.art-144fc73a55b24e19b2f3b4d3102a7bd2 |
| institution | Directory Open Access Journal |
| issn | 2075-1680 |
| language | English |
| last_indexed | 2024-03-09T17:01:15Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Axioms |
| spelling | doaj.art-144fc73a55b24e19b2f3b4d3102a7bd22023-11-24T14:28:55ZengMDPI AGAxioms2075-16802023-10-011211102710.3390/axioms12111027New Partially Linear Regression and Machine Learning Models Applied to Agronomic DataGabriela M. Rodrigues0Edwin M. M. Ortega1Gauss M. Cordeiro2Department of Exact Sciences, University of São Paulo, Piracicaba 13418-900, BrazilDepartment of Exact Sciences, University of São Paulo, Piracicaba 13418-900, BrazilDepartment of Statistics, Federal University of Pernambuco, Recife 50670-901, BrazilRegression analysis can be appropriate to describe a nonlinear relationship between the response variable and the explanatory variables. This article describes the construction of a partially linear regression model with two systematic components based on the exponentiated odd log-logistic normal distribution. The parameters are estimated by the penalized maximum likelihood method. Simulations for some parameter settings and sample sizes empirically prove the accuracy of the estimators. The superiority of the proposed regression model over other regression models is shown by means of agronomic experimentation data. The predictive performance of the new model is compared with two machine learning techniques: decision trees and random forests. These methods achieved similar prediction performance, i.e., none stands out as a better predictor. In this sense, the objective of the research is to choose the best method. If the objective is only predictive, the decision tree can be used due to its simplicity. For inference purposes, the regression model is recommended, which can provide much more information regarding the relationship of the variables under study.https://www.mdpi.com/2075-1680/12/11/1027agronomic experimentationcross validationdecision treemaximum likelihood estimationrandom forestresidual analysis |
| spellingShingle | Gabriela M. Rodrigues Edwin M. M. Ortega Gauss M. Cordeiro New Partially Linear Regression and Machine Learning Models Applied to Agronomic Data Axioms agronomic experimentation cross validation decision tree maximum likelihood estimation random forest residual analysis |
| title | New Partially Linear Regression and Machine Learning Models Applied to Agronomic Data |
| title_full | New Partially Linear Regression and Machine Learning Models Applied to Agronomic Data |
| title_fullStr | New Partially Linear Regression and Machine Learning Models Applied to Agronomic Data |
| title_full_unstemmed | New Partially Linear Regression and Machine Learning Models Applied to Agronomic Data |
| title_short | New Partially Linear Regression and Machine Learning Models Applied to Agronomic Data |
| title_sort | new partially linear regression and machine learning models applied to agronomic data |
| topic | agronomic experimentation cross validation decision tree maximum likelihood estimation random forest residual analysis |
| url | https://www.mdpi.com/2075-1680/12/11/1027 |
| work_keys_str_mv | AT gabrielamrodrigues newpartiallylinearregressionandmachinelearningmodelsappliedtoagronomicdata AT edwinmmortega newpartiallylinearregressionandmachinelearningmodelsappliedtoagronomicdata AT gaussmcordeiro newpartiallylinearregressionandmachinelearningmodelsappliedtoagronomicdata |