Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Mathematics, Computation and Statistics (JMATHCOS)

Robust Method with Cross-Validation in Partial Least Square Regression Sibuea, Nuraini; Syamsudhuha, Syamsudhuha; Adnan, Arisman; Silalahi, Divo Dharma
Journal of Mathematics, Computations and Statistics Vol. 8 No. 1 (2025): Volume 08 Nomor 01 (April 2025)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/jmathcos.v8i1.4766

Abstract

Partial Least Squares Regression (PLSR) is a multivariate analysis technique used to handle data with highly correlated predictor variables or when the number of predictor variables exceeds the number of samples. PLSR is not robust to outliers, which can disrupt the stability and accuracy of the model. Cross-validation is an important approach to improve model reliability, particularly in data that contains outliers. This study aims to evaluate the effectiveness of K-fold cross-validation and nested cross-validation in a PLSR model using NIRS data from oil palm plantation soil that contains outliers. The methods used in this study include outlier identification using RBF kernel PCA, followed by the application of K-fold cross-validation and nested cross-validation in the PLSR model. The evaluation is based on the Root Mean Square Error (RMSE) and the Coefficient of Determination (R²). The results show that nested cross-validation performs better than K-fold cross-validation. Nested cross-validation results in lower RMSE and higher R², both with and without outliers. K-fold cross-validation is more susceptible to overfitting, whereas nested cross-validation is more effective in mitigating the impact of outliers and improving model accuracy. The conclusion of this study is that nested cross-validation outperforms K-fold cross-validation in improving prediction accuracy and the stability of the PLSR model, especially in data containing outliers. It is recommended to use nested cross-
Evaluating Statistical Power in t-Test and Welch’s Test Using Monte Carlo Simulation Approach Tengku Irfan Wira Buana; Arisman Adnan
Journal of Mathematics, Computations and Statistics Vol. 8 No. 2 (2025): Volume 08 Nomor 02 (Oktober 2025)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/jmathcos.v8i2.7407

Abstract

Statistical hypothesis testing is a key method in inferential statistics for assessing whether group differences are simply due to chance or amount to actual effect. One of the central concepts in hypothesis testing is statistical power. Statistical power is the probability of correctly rejecting the null hypothesis when the alternative hypothesis is true. Low statistical power increases the risk of Type II errors, leading to misleading conclusions. This study explores the key factors influencing statistical power, including sample size, effect size, variance, and significance level. Monte Carlo simulation method was utilized in this study to examine the statistical power associated with the two-sample t-test across various combinations of sample size, effect size (mean difference), and population variance. Simulations were conducted by generating random samples, performing variance tests, and applying either the Student’s t-test or Welch’s t-test based on variance equality. The results confirmed that statistical power increases with larger sample sizes and greater effect sizes, while higher variance and stricter significance levels reduce power. Welch’s t-test was found to be more reliable than the standard t-test in cases of unequal variances, reinforcing its importance in real-world data analysis. These findings show the importance of careful study design in hypothesis testing. Researchers must consider and plan the study so that there is enough power to detect meaningful effects. Future studies should examine different statistical methods of power, and potentially extend the simulation to different non-normal distributions for hypothesis testing.
Co-Authors ', Firdaus Abdul Somad Batubara Afrianto Daud Agus Ika Putra Agus Kurniawati Ahmad Fadli Ahmad Jamaan Amun Amri Anne Mudya Yolanda Asri Elvita Ayu Agustiani Azhari Setiawan Azra Aulia Dwiputri Bustami Bustami Defrinaldi Absari Deni Rizaldi Devri Maulana Ecelly Indriani Putri Elfaki, Faiz AM Endah Dwi Jayanti Enno Yuniarto Fatayat Feblil Huda Febrianti, Lusi Ferdian Fadly Fikri Marwansyah Firdaus ' Fitra Lestari Goldameir, Noor Ell Gustriza Erda Haposan Sirait Haposan Sirait Harison ' Harison Harison Heru Angrianto Ibnu Daqiqil ID Icha Yulia Ilyas Husti Indra, Zul Irfansyah Irfansyah Isnaini ' Isti Yuliani Iswadi HR Iwantono Iwan Barnawi Jusman, Yessi K Khairat Kesi Marseliani Khairunnisa, Siska Khairunnissa, Khairunnissa Khusnal Marzuqo Lindrianasari Liza Yarmanita Mardiyah Muhgni Maria Erna Mayangsari Mayangsari Mirza Hardian Mohammad Saeri Mustofa Usman Nabilah Fitriyyah Delfira Nike Syelfina Noor Ell Goldameir Nurhayati, Nurhayati Nurqolbi, Leliyana Ody Azis Saputra Okta Bella Syuhada Putri Sion Cahayana Putri Susanti Rahmad Kurniawan Rahmad Ramadhan Laska Rahwana Saputra Raudatul Yusra Ridho Tri Mulya Riko Febrian Rini, Ari Sulistyo Riski Rahmadani Rosma, Iswadi Hasyim Russel, Edwin Rustam Efendi Rustam Efendi S. Siswanto Satibi, Syawal Sehatta Saragih Sibuea, Nuraini Sigit Sugiarto Silalahi, Divo Dharma Sillaturahim Sirait, Tesa Theresia Siska Yuliati Soewignjo Agus Nugroho Sukma Novia Syafitri Sukoco Sukoco Sul Kantri Rahma Wanti Sunarno Syamsu Herman Syamsudhuha Syamsudhuha T, Masrina Munawarah Tengku Irfan Wira Buana Tira Mei Darnis Titi Solfitri Tuti Alawiyah Wamiliana Windy Lasma Sari Purba Windy Maya Sari Wirda Hia Yenita Roza Yennita Y Zul Indra