# Software Downloads for "Compare Linear Regression"

**Non-linear regression GUI**- License: Freeware

The non-**linear** **regression** problem (univariate or multivariate) is easily posed using a graphical user interface (GUI) that solves the problem using one of the following solvers:
- nlinfit: only univariate problems.
- lsqnonlin: can deal with multivariate problems (more than one dependent fitting variable, ydata is a matrix).
- patternsearch: this solver is useful to obtain a good start point, before using nlinfit or lsqonolin; this way, the global minimum is determined easier.
Data is introduced in the GUI as vector or matrix from the workspace.

**Platform:**Matlab, Scripts**Publisher:**Pablo MardoTsn**Date:**14-05-2013**Size:**31 KB

**Linear Regression with Errors in X and Y**- License: Shareware

Calculates slope and intercept for **linear** **regression** of data with errors in X and Y. The errors can be specified as varying point to point, as can the correlation of the errors in X and Y.
The uncertainty in the slope and intercept are also estimated.
This follows the method in D. York, N. Evensen, M. Martinez, J. Delgado "Unified equations for the slope, intercept, and standard errors of the best straight line" Am. J. Phys. 72 (3) March 2004.
The package includes an example and a Monte Carlo simulation verifying the estimated uncertainties.

**Platform:**Matlab, Scripts**Publisher:**Travis Wiens**Date:**23-04-2013**Size:**10 KB

Orthogonal **Linear** **Regression** in 3D-space by using Principal Components Analysis
This is a wrapper function to some pieces of the code from the Statistics Toolbox demo titled "Fitting an Orthogonal **Regression** Using Principal Components Analysis"
(http://www.mathworks.com/products/statisti...thoregdemo.html),
which is Copyright by the MathWorks, Inc.
Input parameters:
- XData: input data block -- x: axis
- YData: input data block -- y: axis
- ZData: input data block -- z: axis
- geometry: type of approximation ('line','plane')
- visualization: figure ('on','off') -- default is 'on'
- sod: show orthogonal distances ('on','off') -- default is 'on'
Return parameters:
- Err: error of approximation - sum of orthogonal distances
- N: normal vector for plane, direction vector for line
- P: point on plane or line in 3D space...

**Platform:**Matlab, Scripts**Publisher:**Ivo Petras**Date:**13-01-2013**Size:**10 KB

**Statsar**- License: Demo

The Statsar statistics library allows you to add high-performance statistics calculations to your .NET platform applications. The object-oriented library was designed and implemented by numerical experts with proven expertise in the financial industry. Providing a simple and intuitive object model, the library allows you to rapidly analyze your data by importing familiar data objects such as ADO.NET data tables. A powerful and robust CSV reader is also included with the component, allowing you to work with existing data files.

**Platform:**Windows**Publisher:**Simplexar Software**Date:**14-04-2008**Size:**2144 KB

**MyRegrComp**- License: Shareware

MYREGCOMP: **Compare** two **linear** **regression**.
This function compares two least-square **linear** **regression**. Tests are implementes as reported by Stanton A. Glantz book "Primers of biostatistics". This routine uses MYREGR function. If it is not present on the computer, MyregrINV will try to download it from FEX..

**Platform:**Matlab, Scripts**Publisher:**Giuseppe Cardillo**Date:**26-01-2013**Size:**10 KB

**quantreg.m - quantile regression**- License: Shareware

Quantile Regression
USAGE: [p,stats]=quantreg(x,y,tau[,order,nboot]);
INPUTS:
x,y: data that is fitted. (x and y should be columns)
Note: that if x is a matrix with several columns then multiple
**linear** **regression** is used and the "order" argument is not used.
tau: quantile used in **regression**.
order: polynomial order. (default=1)
nboot: number of bootstrap surrogates used in statistical inference.(default=200)
stats is a structure with the following fields:
.pse: standard error on p.

**Platform:**Matlab, Scripts**Publisher:**Aslak Grinsted**Date:**08-06-2013**Size:**10 KB

**PIL**- License: Freeware

This Simulink library is a collection of
blocks that perform Parameter Identification
through the most rewarded frequency and time
domain **linear** **regression** methods. It works
in Matlab 5.3.1 as well as in later versions.
Main examples are:
-) Recursive Least Squares (RLS).
-) Simple Windowed **Regression** (LLS).
-) Local Weighted **Regression** (LWR).
-) Fourier Transform **Regression** (FTR).
Two example on **Linear** and Nonlinear Aircraft
Parameter Identification are included in the library.
IMPORTANT, all of these blocks REQUIRE SMXL
(the Simulink Matrix Library) freely available in the File exchange section of the MATLAB Central website.

**Platform:**Matlab, Scripts**Publisher:**Giampiero Campa**Date:**18-04-2013**Size:**215 KB

**Linear Median Squared Error**- License: Shareware

This routine calculates the median squared error of a **linear** function, and can be used with fminsearch as a robust **linear** **regression** (see help LinearMedianSquaredError).
It should be very easy to extend the example code to handle nonlinear functions and to minimize other error functions (least absolute error, for instance)..

**Platform:**Matlab, Scripts**Publisher:**Will Dwinnell**Date:**11-06-2013**Size:**10 KB

**Box-Cox power transformation for Linear Models**- License: Shareware

Helps choose a Box-Cox power transformation for a multivariate **linear** **regression**.
Assume you are looking at the residuals of [b,bint,r] = regress(y,X) and it seems a transformation is in place. Use:
boxcoxlm(y,X) to find the best lambda for a Box-Cox power transformation (y^lambda, or log(y) for lambda=0)
The function will also plot the Maximum Log-Likelihood as a function of lambda, and a 95% confidence region for the best value of lambda
More control can be obtained using:
[LambdaHat,LambdaInterval]=boxcoxlm(y,X,PlotLogLike,LambdaValues,alpha)
which allows ommiting the plot, a different region or precision, and a different alpha value for the confidence interval.

**Platform:**Matlab, Scripts**Publisher:**Hovav Dror**Date:**26-01-2013**Size:**10 KB

**mregress**- License: Shareware

Performs multiple **linear** **regression**. Includes option for setting the
y-intercept to zero. Returns the F-statistic, p-value for the F,
t-distribution for the coefficients, and covariance matrix for the
regression..

**Platform:**Matlab, Scripts**Publisher:**Tony Reina**Date:**04-03-2013**Size:**10 KB

**Linear Least Squares**- License: Freeware

This application calculates the angular and **linear** coefficients of a **linear** **regression** considering the **Linear** Least Squares methodology..

**Platform:**Android 2.x, Android 3.x, Android 4.4, Android 4.x**Publisher:**Prof. Braga**Date:**22-03-2014**Size:**282 KB

**Rt-Plot**- License: Shareware

Rt-Plot is a tool to generate Cartesian X/Y-plots from scientific data. You can enter and calculate tabular data. View the changing graphs, including **linear** and non **linear** **regression**, interpolation, differentiation and integration, during entering. Rt-Plot enables you to create plots fast and easily. The options can be changed interactively. A powerful reporting module generates ready to publish documents..

**Platform:**WinOther**Publisher:**Rt-Science**Date:**16-05-2003**Size:**7442 KB

**ESBPCS-Stats for VCL - Trial**- License: Shareware

ESBPCS-Stats is a subset of ESBPCS (ESB Professional Computation Suite) containing Components and Routines for Statistical Analysis and Matrix/Vector Manipulation in Borland Delphi and C++ Builder.
This subset is ideal for people who just want the Stats and/or Matrix/Vector parts of ESBPCS, though you can upgrade to the full version at any time. Also includes Components and routines covering Probability Distributions, **Linear** **Regression**, Hypothesis Analysis, Equation Solving and more.
The subset includes a good collection of Edits, SpinEdits, ComboBoxes, Memos, CheckBoxes, RadioGroups, CheckGroups as well as a huge collection of routines.

**Platform:**Windows**Publisher:**ESB Consultancy**Date:**22-02-2005**Size:**8608 KB

**ESBStats - Statistical Analysis Software**- License: Shareware

Statistical Analysis and Inference Software for Windows covering everything from Average, Mode and Variance through to Hypothesis Analysis, Time Series and **Linear** **Regression**. Includes Online Help, Tutorials, Graphs, Summaries, Import/Export, Customisable Interface, Calculator, Live Spell Check, Install/Uninstall and much more.
- Single, Dual (paired and unpaired) and Multiple Data Analysis (Multivariate analysis not in Lite Version).
- Data can be either for Sample or Population.
- Data can be Time Based for Time Series Analysis.

**Platform:**Windows**Publisher:**ESB Consultancy**Date:**13-05-2008**Size:**6715 KB

**NMath Matrix**- License: Demo

NMath Matrix is an advanced matrix manipulation library that extends NMath Core to include structured sparse matrix classes (triangular, symmetric, Hermitian, banded, tridiagonal, symmetric banded, and Hermitian banded), factorizations (LU, Bunch-Kaufman, and Cholesky), orthogonal decompositions (QR and SVD), advanced least squares classes (Cholesky, QR, and SVD), and solutions to symmetric, Hermitian, and nonsymmetric eigenvalue problems.Fully compliant with the Microsoft Common Language Specification, all NMath routines are callable from any .

**Platform:**Windows**Publisher:**CenterSpace Software**Date:**20-9-2009**Size:**3891 KB

**NMath Core**- License: Demo

NMath Core contains foundational classes for object-oriented numerics on the .NET platform. Product features include: Single- and double-precision complex number classes; full-featured vector and matrix classes for single- and double-precision floating point numbers and single- and double-precision complex numbers; flexible indexing using slices and ranges; cubic spline interpolation; extension of standard mathematical functions, such as Cos(), Sqrt(), and Exp(), to work with vectors, matrices, and complex number classes; LU factorization for a matrix, as well as functions for solving **linear** systems, computing determinants, inverses, and condition numbers; least squares solutions; random number generation from various probability distributions, including the uniform, normal, Poisson, gamma, binomial, exponential, Pareto, and log normal...

**Platform:**Windows**Publisher:**CenterSpace Software**Date:**06-10-2009**Size:**14745 KB

**PDL-Stats**- License: Freeware

Statistics modules in Perl Data Language, with a quick-start guide for non-PDL people. They make the PDL shell work like R, but with PDL threading (fast automatic iteration) of procedures including t-test, **linear** **regression**, and k-means clustering..

**Platform:**WinOther**Publisher:**pdl-stats.sourceforge.net**Date:**06-05-2012**Size:**64 KB

**statsmodels**- License: Freeware

Statistical models with python using numpy and scipy. Currently covers **linear** **regression** (with ordinary, generalized and weighted least squares), robust **linear** **regression**, and generalized **linear** model..

**Platform:**WinOther**Publisher:**statsmodels.sourceforge.net**Date:**23-06-2012**Size:**4193 KB

**MyRegressionINV**- License: Shareware

MYREGRINV: Resolve a calibration problem (inverse **regression** problem) that is: to estimate mean value and confidence interval of x since y.
This function computes a least-square **linear** **regression** using the supplied calibration points and then computes the X values for a supplied y observed vector. This routine use MYREGR function. If it is not present on the computer, MyregrINV will try to download it from FEX.
References:
Sokal R.R. and Rohlf F.J. 2003 BIOMETRY. The Principles and Practice of Statistics in Biological Research (3rd ed.

**Platform:**Matlab, Scripts**Publisher:**Giuseppe Cardillo**Date:**27-04-2013**Size:**10 KB

**arsoswod**- License: Shareware

Comparision of simple **linear** **regression** equations without data. As well as the before file arsos.m this procedure is suffice to test the homogeneity of k **regression** coefficients (Ho: b1 = b2 =...= bk). It do not needs to input data, but the sample statistics as sample size, **regression** coefficients, means and variances. The variability among the **regression** coefficients requires the F-statistic. If the null hypothesis is rejected, it can proceeds with a Tukey's q multiple comparision test to determine which of the k slopes differ from which other.

**Platform:**Matlab, Scripts**Publisher:**Antonio Trujillo-Ortiz**Date:**18-06-2013**Size:**10 KB