What is XLSTAT-CCR?

The XLSTAT-CCR module for the XLSTAT-Pro Excel Add-in

• XLSTAT-CCR develops improved regression and classification models for:
• linear regression
• logistic regression
• linear discriminant analysis
• XLSTAT-CCR handles multicolinearity due to correlated predictors effectively even with high dimensional data (more variables than cases).

---

Special Offer!    Buy XLSTAT-CCR now and receive a 20% discount* on your future purchase or renewal of CORExpress.

What Features of Regression Models are Improved?

XLSTAT-CCR improves:

• interpretation of regression coefficients (see Tutorial 1)
• out-of-sample prediction (see Tutorial 2)
• classification (see Tutorial 2)
• latent class regression models (see Tutorial 3)
• variable selection (see Tutorials 1-3)

How does XLSTAT-CCR Work?

• XLSTAT-CCR develops regression models using Correlated Component Regression (CCR) methods. CCR was developed by Dr. Jay Magidson for simultaneously estimating regression models and selecting predictors from a potentially large number of candidate predictors. Reliable models are obtained using a fast algorithm that incorporates M-fold cross-validation to optimize tuning parameters (amount of regularization K and # predictor variables P).
• Final models may even include more predictors than cases!!! (impossible with traditional regression methods)

Where can I learn more about XLSTAT-CCR?

• Technical Documentation
  • Articles
  • Magidson (2010) This article introduces the Correlated Component Regression (CCR) Approach and compares it with other method, including penalized regression and principal components regression.
  • Magidson and Wassmann (2010) This article introduces suppressor variables, captured by CCR, and the importance of including them in regression models.
  • Conference Presentations
    • 2011 Modern Modeling Methods (M3) Conference (1 hour presentation)
    • 5th ESSEC-SUPELEC Statistical Workshop on “PLS (Partial Least Squares) Developments”, 2011. (Featured presentation)
  • XLSTAT-CCR User's Guide
  • Tutorials
• Training
• 2-day workshop in Boston (Statistical Modeling Week)
• 1-day workshop in Orlando (Sponsored by American Statistical Association)
• Online Course (January 2012)

Can XLSTAT-CCR Improve Latent Class Regression Models?

Yes. Latent GOLD® can be used to obtain segments, and XLSTAT-CCR can be used to predict segment membership or to develop separate regression models for each segment. XLSTAT-CCR allows many more predictor variables to be included in the model than possible previously.

Overview

The XLSTAT-CCR module for the XLSTAT-Pro Excel Add-in focuses on regression analysis (linear regression, logistic regression, etc.) where large numbers of correlated predictors may be available. On many data sets, Correlated Component Regression (CCR) has been shown to outperform penalized regression techniques such as Lasso, and other methods such as Naive Bayes and PLS regression.

XLSTAT-CCR develops reliable regression models using CCR methods. CCR models may even include more predictors than cases, a situation that is impossible with traditional regression methods. CCR was developed by Dr. Jay Magidson for simultaneously estimating regression models and excluding irrelevant predictors. Reliable models are obtained using a fast algorithm that incorporates M-fold cross-validation for tuning model parameters (optimal number of predictors and amount of regularization).

Learn more about Correlated Component Regression (CCR) modeling

---

Features

The XSTAT-CCR module includes the following capabilities:

• Automatic model scoring of training and validation (holdout) records
• Fast step-down algorithm to simultaneously select the most important predictors and estimate the models.
• CCR-Linear – Continuous dependent variable
• CCR-Logistic – Dichotomous dependent variable
• CCR-LDA – Dichotomous dependent and continuous predictors satisfying assumptions of linear discriminant analysis (LDA)

Industry Background

Regression modeling is undergoing a revolution precipitated by the availability of hundreds and even thousands of candidate predictor variables in genomics, but increasingly vast amounts of data are becoming available in all other fields as well. Problems in traditional regression modeling occur when the number of predictors P included in a model approaches or exceeds the sample size N. In this type of situation, involving the presence of ‘high-dimensional data’, traditional regression methods become unreliable and regression coefficients may even be impossible to estimate. Recent advances with high-dimensional data show how such problems can be resolved (see: Cai and Shen (2011)). This important new field continues to evolve at a rapid pace.

Tutorials

The demo version of XLSTAT-CCR is limited to datasets with only 20 columns. No column restrictions are set for the tutorials and associated datasets below.

XLSTAT-CCR       Tutorial 1: Getting Started with Correlated Component Regression (CCR) in XLSTAT-CCR       Tutorial 2: Using CCR with a Dichotomous Y and Many Correlated Predictors       Tutorial 3: Obtaining Predictions from a 2-class Regression       Tutorial 4: Prediction with Near Infrared (NIR) Data Sample Datasets       Auto Price Data       LDAsim Data       OJ Data       Cookie NIR Data

Related Products

CORExpress

CORExpress focuses on regression analysis (linear regression, logistic regression, etc.) where large numbers of correlated predictors may be available. On many data sets, CCR has been shown to outperform penalized regression techniques such as Lasso, and other methods such as Naive Bayes and PLS regression. CORExpress® (patent pending) develops regression models using Correlated Component Regression (CCR) methods. CCR was developed by Dr. Jay Magidson for simultaneously estimating regression models (linear regression, logistic regression, etc.) and selecting predictors to be included in the model from a potentially large number of candidate predictors. Reliable models are obtained using a fast algorithm that incorporates M-fold cross-validation for tuning model parameters. Final models may even include more predictors than cases, a situation that is impossible with traditional regression methods. Learn More

XLSTAT-Pro

XLSTAT® is a complete statistics package as an Excel Add-in. Data is input into Excel and output is displayed in Excel--eliminating the risks associated with transferring your output into Excel. The user-friendly interface makes it easy to quickly analyze your data--no complicated syntax! Learn More

---

Statistical Innovations is proud to announce its partnership with Addinsoft SARL, the developer of XLSTAT.

CORExpress®, Latent GOLD®, Latent GOLD® Choice, SI-CHAID®, & GOLDMineR® are trademarks of Statistical Innovations.
XLSTAT is a trademark of Addinsoft SARL.
Excel® is a trademark of the Microsoft Corporation.
SPSS® is a trademark of the IBM Corporation.
SAS® is a trademark of the SAS Institute Inc.

---

*Special offer for purchasing CORExpress expires 2 years after the date of purchase of XLSTAT-CCR. Offer is non-transferrable and only available to customers who purchase associated XLSTAT modules directly from Statistical Innovations Inc. For full details, please contact Will Barker at will@statisticalinnovations.com.