Journals / Physical Sciences / 2026 / Cilt: 6 Sayı: 2

DIMENSIONALITY REDUCTION METHODS: PCR, PLSR, RRR AND A HEALTH APPLICATION

BOYUT İNDİRGEME TEKNİKLERİ: PCR, PLSR, RRR VE BİR SAĞLIK UYGULAMASI

Pages
36–47
Publication Date
2011-03-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This paper provides study of three dimension reduction techniques, namely Principal Component Regression (PCR), Partial Least squares Regression (PLSR), and Reduced Rank Regression (RRR), and they were illustrated on a data set that has PCOS disease to help to choose the efficient factors (latent variables) for modeling and predicting fsh and lh hormones when the data set has small number of observation unit.)>

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Working with data set that has many variables or has fewer observation units than variables leads to difficulties in statistical analysis.
📊
Key Findings & Data:In this situation dimension reduction is a necessary part of the data analysis.
💡
Conclusion & Impact:This paper provides study of three dimension reduction techniques, namely Principal Component Regression (PCR), Partial Least squares Regression (PLSR), and Reduced Rank Regression (RRR), and they were illustrated on a data set that has PCOS disease to help to choose the efficient factors (latent variables) for modeling and predicting fsh and lh hormones when the data set has small number of observation unit.)>
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Boyut İndirgeme · Temel Bileşenler Regresyonu · Kısmi En Küçük Kareler Regresyonu

Abstract

Working with data set that has many variables or has fewer observation units than variables leads to difficulties in statistical analysis. In this situation dimension reduction is a necessary part of the data analysis. It is necessary because, it provides working with a subset of the existing features or to transform to a new reduced set of features and working with low dimensional data and simplify the data model by working with parsimonious model. There are some dimensionality reduction methods and all of them lean to use a linear combinations of m variables by reducing m dimensional data set to a dimensional data set (avariability in the variables. This paper provides study of three dimension reduction techniques, namely Principal Component Regression (PCR), Partial Least squares Regression (PLSR), and Reduced Rank Regression (RRR), and they were illustrated on a data set that has PCOS disease to help to choose the efficient factors (latent variables) for modeling and predicting fsh and lh hormones when the data set has small number of observation unit.)>

Özet

Çok fazla değişkene sahip veya değişken sayısından daha az gözlem sayısına sahip veri seti ile çalışmak istatistiksel analizde bazı zorluklara yol açmaktadır. Böyle bir durumda boyut indirgemesi analizin önemli bir parçasıdır. Boyut indirgemesi, veri setinde var olan özelliklere sahip daha küçük bir veri seti ile çalışmayı mümkün kılmaktadır. Boyut indirgeme teknikleri m boyutlu veri setini, m değişkenlerdeki değişimin büyük bir kısmını açıklayacak ve bu değişkenlerin doğrusal birleşimi olacak şekilde a boyutlu veri setine indirgemektedir. Bu çalışmada, bu tekniklerden Temel bileşenler regresyonu, Kısmi en küçük kareler regresyonu ve İndirgenmiş rank regresyonu yöntemleri anlatılarak, sağlık verisi üzerinde uygulaması gösterilmiştir.

🔖

Cite This Article

Bulut, E., Alma, Ö. G. (2011). DIMENSIONALITY REDUCTION METHODS: PCR, PLSR, RRR AND A HEALTH APPLICATION. Physical Sciences, Cilt: 6 Sayı: 2, 36–47. https://ajindex.com/articles/1657962

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...