WIND SPEED PREDICTION ARIMA Model

if the value of

p = 1
d = 1
q =1 

Now i want to create ARIMA model

MD = ARIMA('AR', { }, 'MA' { }, 'SAR', { }, 'SMA' { }, 'D' ,.., 'SEASONALITY',.., 'CONSTANT',..,'VARIANCE',..)

Can anyone tell, how can we calculate these values?

Thank you

Answer 1

[Aman]

Hi Seemant,

As per my understanding, you want to find seasonal and non-seasonal coefficients values when the degree of non-seasonal coefficients is fixed for an ARIMA model.

In order to do so, you need to first create an ARIMA model with those fixed degrees and then need to fit that model to your data. Once you have fitted your model, you can find the coefficients values using the fitted model. You can refer to the below code, where I have done the same thing to find the AR parameter value.

rng(5);
y = rand(500,1);
mdl = arima(1,1,1);
estimation = estimate(mdl,y);

 
    ARIMA(1,1,1) Model (Gaussian Distribution):
 
                  Value       StandardError    TStatistic      PValue  
                __________    _____________    __________    __________

    Constant    0.00033562     0.00055715       0.60238         0.54692
    AR{1}         0.011387       0.044693       0.25479         0.79889
    MA{1}         -0.95989       0.012375       -77.568               0
    Variance      0.087754      0.0083724        10.481      1.0519e-25

AR = estimation.AR{1};
disp("AR parameter estimated is " + string(AR));

AR parameter estimated is 0.011387

You can refer to the documentation below to learn more about the "estimate" function.

• https://www.mathworks.com/help/econ/arima.estimate.html

I hope it will help you to proceed with your workflow.