MATLAB: How can one get t-stat of fitlm as an output

MATLAB

I checked

https://www.mathworks.com/help/stats/fitlm.html

but it does not seem to say how one can get t-stat as an output. Please advise.

Best Answer

It is in the top example:

load carsmall
X = [Weight,Horsepower,Acceleration];
mdl = fitlm(X,MPG);
mdl.Coefficients.tStat
ans = 4×1
   12.3699
   -5.8023
   -1.7663
   -0.0599
●

Related Solutions

MATLAB: How can one get parameters of fitlm as an output

First, see the documentation for F-Statistic, then see the documentation for anova, specifically tbl.

MATLAB: How to compute t-stat for MLE parameters

I have no idea what a Garch regression is, since my knowledge of econometrics is essentially nonexistent.

For a simple linear regression, the calculations would be:

x = 1:10;                                                   % Create Data

y = (11:20) + randn(1, 10)*0.5;                             % Create Data
N = numel(x);                                               % Number of Observations
X = [x(:) ones(size(x(:)))];                                % Define Design Matrix
B = X \ y(:)                                                % Estimate Parameters
rsd = y(:) - X*B;                                           % Residuals
Var_rsd = var(rsd);                                         % Residual Variance
CovB = Var_rsd*inv(X'*X);                                   % Parameter Covariance Matrix (Eqn. 18)
tstat = tinv(0.975, N-2);                                   % Estimating 2 Parameters, so (N-2) Degrees-Of-Freedom
CI95 = B + sqrt(diag(CovB))*[-tstat tstat]                  % 95% Confidence Intervals
CI95_Slope = CI95(1,:)
CI95_Intercept = CI95(2,:)

The result is close to the results the Statistics and Machine Learning Toolbox function regress (link) produces. They are not the same because regress ‘Studentizes’ the residuals. (I will let you pursue that at your leisure.)

The ‘Eqn. 18’ reference is to On the Covariance of Regression Coefficients.

Long day here, with much travel. My apologies for the delay.

EDIT — ‘CovB’ clarification.

Best Answer

Related Solutions

MATLAB: How can one get parameters of fitlm as an output

MATLAB: How to compute t-stat for MLE parameters

Related Question