This function computes a least-square linear regression suppling several output information.
X - Array of the independent variable
Y - Dependent variable. If Y is a matrix, the i-th Y row is a
repeated measure of i-th X point. The mean value will be used
verbose - Flag to display all information (default=1)
- Slope with standard error an 95% C.I.
- Intercept with standard error an 95% C.I.
- Pearson's Correlation coefficient with 95% C.I. and its
adjusted form (depending on the elements of X and Y arrays)
- Spearman's Correlation coefficient
- Regression Standard Error
- Total Variability
- Variability due to regression
- Residual Variability
- Student's t-Test on Slope (to check if slope=0)
- Student's t-Test on Intercept (to check if intercept=0)
- Modified Levene's test for homoschedasticity of residuals
- Power of the regression
- Deming's regeression
- a plot with:
o Data points
o Least squares regression line
o Red dotted lines: 95% Confidence interval of regression
o Green dotted lines: 95% Confidence interval of new y
evaluation using this regression.
- Residuals plot
SEE also myregrinv, myregrcomp
Created by Giuseppe Cardillo
To cite this file, this would be an appropriate format: Cardillo G. (2007) MyRegression: a simple function on LS linear regression with many informative outputs. http://www.mathworks.com/matlabcentral/fileexchange/15473
Giuseppe Cardillo (2023). MyRegression (https://github.com/dnafinder/myregr), GitHub. Retrieved .
MATLAB Release Compatibility
Platform CompatibilityWindows macOS Linux
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!
Versions that use the GitHub default branch cannot be downloaded
inputparser; table implementation; github link
Deming's regression added
fixed a bug in plot computation
The modified Levene's test for homoschedasticity of residuals and residuals plot were added
Now Y can be a matrix of repeated measures
change in description
To compute power, Myregr requires powerStudent by Trujillo-Ortiz, A. and R. Hernandez-Walls. If this function is not present on the computer, Sandler try to download it from FEX
Changes in description
Changes in help section
Added PowerStudent to compute the power of t-Student tests on regression parameters.