Related Concept Videos
Residuals and Least-Squares Property
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
Variance
The standard deviation measures the spread in the same units as the data....
Variation
When independent and dependent variables are plotted on a scatter plot, the slope of a line is a value that describes the rate of change between the two...
Standard Deviation
Correlation and Regression
Residual Plots
When the residual values are plotted against the variable x, it is called a residual...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Related Experiment Video
Updated: Nov 27, 2025

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach
Published on: July 3, 2020
Relative Entropy and Minimum-Variance Pricing Kernel in Asset Pricing Model Evaluation.
Javier Rojo-Suárez1, Ana Belén Alonso-Conde1
1Department of Business Administration, Rey Juan Carlos University, 28032 Madrid, Spain.
This study introduces relative entropy as a robust method for testing asset pricing models, addressing issues with traditional procedures. The entropy-based approach offers a more accurate decomposition of model performance compared to generalized least squares R-squared statistics.
Area of Science:
- Quantitative Finance
- Econometrics
- Financial Modeling
Background:
- Traditional asset pricing model tests often yield spurious rejections due to model misspecification or data characteristics.
- Existing methods struggle to accurately assess model performance and identify sources of error.
Purpose of the Study:
- To propose relative entropy as an alternative framework for testing asset pricing models.
- To investigate the relationship between pricing kernel entropy and mean-variance efficiency of factor-mimicking portfolios.
- To develop an entropy-based decomposition for assessing model explanatory power.
Main Methods:
- Utilizing the relative entropy of pricing kernels, specifically Kullback-Leibler divergence.
- Examining the connection between the generalized least squares (GLS) R-squared statistic and pricing kernel entropy.
- Developing an entropy-based decomposition to analyze model performance.
Main Results:
- Relative entropy provides a robust alternative to traditional testing procedures for asset pricing models.
- The entropy-based decomposition explicitly separates model performance into pricing kernel entropy and its correlation with asset returns.
- While correlated with GLS R-squared, relative entropy offers a more nuanced understanding of model fit.
Conclusions:
- Relative entropy is a versatile tool for constructing reliable tests in asset pricing.
- The proposed decomposition enhances the interpretability of asset pricing model performance.
- This framework addresses limitations in existing methods for evaluating financial models.

