finding best value for ARIMA (p,d,q) model?

function ar = checkarma(y,pp,dd,qq)
LOGL = zeros(pp+1,dd+1,qq+1);
PQ = zeros(pp+1,dd+1,qq+1);
for p = 1:pp+1
    for d = 1:dd+1
    for q = 1:qq+1
        
        mod = arima(p-1,d-1,q-1)
        [fit,~,logL] = estimate(mod,y,'print',false);
        LOGL(p,d,q) = logL;
        PQ(p,d,q) = p+d+q;
    end
    end
end

LOGL = reshape(LOGL,(pp+1)*(qq+1)*(dd+1),1);
PQ = reshape(PQ,(pp+1)*(qq+1)*(dd+1),1);
[~,bic] = aicbic(LOGL,PQ+1,100);
ar = reshape(bic,pp+1,qq+1,dd+1);

Sir, i have a univariate time-series y having 10 values and i want to estimate optimum (p,d,q) values for ARIMA model.... it is giving error 'print is not a recongnized parameter'.

[Darren Lim]

Hi Anurag,

I am pretty new to matlab , may i know how do i get the best p , d and q from the matrix ar ? Thx!

i try to use min(ar) and get the below result in my sample test.

(:,:,1) =

805.4103 811.6983 882.3894

(:,:,2) =

809.4923 815.7831 831.8577

(:,:,3) =

813.9255 820.2356 833.2110

but i am not sure how it translate to get the best p , d and q, thanks!

Darren

Answer 1

[Divya Gaddipati]

The estimate function doesn't have "print" as a Name-Value pair argument.

Instead, you can use something like this to turn off displaying the result from the function:

[fit, ~, logL] = estimate(mod, y, 'Display', 'off');

Hope this helps!

[ANURAG DEEPAK]

Thanks ma'am

[Hamed Majidiyan]

Hi Divya,

I ran the code and I got the following results, even though I don't know how to intrepret the outcomes, so any help would be highly appreciated

ARMA=checkarma(datac_chunk,2,1,2)

ARMA(:,:,1) =

1.0e+05 *

-0.9306 -1.7988 -0.9305

-1.7988 -2.5917 -1.6927

-2.6918 -3.0212 -0.0683

ARMA(:,:,2) =

1.0e+05 *

-1.7987 -0.9305 -1.7987

-2.5914 -1.6966 -2.5907

-1.7986 -1.5608 -3.1177