MATLAB: Does stepwisefit function is able to evaluate using adjusted R-squared instead p-value

regressionStatistics and Machine Learning Toolboxstepwisefit

I want to select the most relevant variables for a model. I use stepwise fit which evaluates individually by p-value, instead I want to evaluate by using adjusted R-Squared to have an idea of how much the selected variables explain the model.

Best Answer

There is a newer function that can do that:

load hald
stepwiselm(ingredients,heat,'Criterion','adjrsquared')

Related Solutions

MATLAB: How to obtain the R-squared and adjusted R-squared values from STEPWISEFIT in the Statistics Toolbox R2011a (Statistics Toolbox version 7.5)

The R-squared and adjusted R-squared statistics are not available in the ‘stats’ output of the programmatic STEPWISEFIT function. As a workaround, you can derive the values of the R-squared and adjusted R-squared statistics from other values that are in the output, by using the following commands

[b,se,pval,inmodel,stats,nextstep,history] = stepwisefit(XX,y);
% To obtain R-squared values
n = length(y);
rsq = 1 - (history.rmse.^2/var(y)) .* ((n-1-history.df0)/(n-1))
% To obtain Adjusted R-Squared values. 
adjrsq = 1 - history.rmse.^2/var(y)

Note that the RMSE field in "history" corresponds to the root mean square errors for the model at each step. Hence, "rsq" and "adjrsq" will be vectors, where the elements correspond to the R-squared values at different steps.

MATLAB: Plot polyfit R-squared

Because

>> fittedXA(1),fittedXA(end)
ans =
    10
ans =
    20
>>

and that's what you plotted as the abscissa for some reason whereas the data are plotted versus ImagingDepth which has range of

>> min(d_rel_mM),max(d_rel_mM)
ans =
     0
ans =
  345.4000
>>

You've mixed up x and y for the prediction line evaluation...use

coeffs_a = polyfit(d_rel_mM, time_a, 1);
fittedXA = linspace(min(d_rel_mM), max(d_rel_mM), 200);
fittedYA = polyval(coeffs_a, fittedXA);

and all will be well...

Best Answer

Related Solutions

MATLAB: How to obtain the R-squared and adjusted R-squared values from STEPWISEFIT in the Statistics Toolbox R2011a (Statistics Toolbox version 7.5)

MATLAB: Plot polyfit R-squared

Related Question