linear regression statistical parameters

Hello,

This is a question following my previous one but I explain the problem here as well. I am trying to use linear and nonlinear regression to predict a response. I am wondering how I can get the most possible statistical results from regress or nlinfit (like durbin watson, probabilities, R2, adjusted R2, etc.).

y=(c.^4+2*c.*p+3*p.^3-c+2*d.^0.5)'; % a sample response

X = [c;p;d]';

beta0 = [1 -2 0 -1 0 1 1];

X = [ones(size(c)); c.^4 ;c.*p; p.^3 ;c; d.^0.5]';

[b,stats] = regress(y,X)

Results: b =

         0
    1.0000
    2.0000
    3.0000
   -1.0000
    2.0000

stats = (how to interpret these?)

     0     0
   NaN   NaN
   NaN   NaN
   NaN   NaN
   NaN   NaN
   NaN   NaN

Answer 1

[Ahmet Cecen]

There is a good chance there are other things wrong with your problem, but first off, it is:

[b,bint,r,rint,stats] = regress(y,X)

not:

[b,stats] = regress(y,X)

in your case, your stats is actually bint...

if you do not want the other results, do this instead:

[b,~,~,~,stats] = regress(y,X)

[Reza S]

Thanks Ahmet. Here is the results now but still need to be interpreted (particularly for stats).

b =

         0
    1.0000
    2.0000
    3.0000
   -1.0000
    2.0000

bint =

     0     0
   NaN   NaN
   NaN   NaN
   NaN   NaN
   NaN   NaN
   NaN   NaN

r =

1.0e-012 *

   -0.1776
   -0.0391
   -0.0568
    0.0284
         0

stats =

   NaN   NaN
   NaN   NaN
   NaN   NaN
   NaN   NaN
   NaN   NaN

[Ahmet Cecen]

Now your stats looks like its actually rint. Stats would look like:

 stats=

 number  <- R2 statistic
 number  <- the F statistic
 number  <- p value of F statistic 
 number  <- estimate of the error variance

[Reza S]

Thanks