CODEWITHSUNDEEP
pythonmachine-learningtime-seriesdata-scienceforecasting
random student
random student

Reputation: 775

PACF and ACF plot does not show any significance

I'm stuck in building my ARMA (ARIMA(p,0,q) model because of there's no significance at all in my ACF and PACF plot. I have read several articles about ARIMA but all of them at least shows significant correlation in their ACF and PACF plot. So for my case, i don't know what to do since this is my first time building times series forecasting model. My data is very stationary so i thought i could go on to build the model. But now i start to doubt if ARMA suits my problem. What should i do if i could still go on building the ARMA model? or should i use other algorithm?

ADF Statistic: -7.654896
p-value: 0.000000
Critical Values:
        1%: -3.508
        5%: -2.895
        10%: -2.585

gambar

gambar2

Upvotes: 1

Views: 3019

Answers (1)

Mehul Gupta
Mehul Gupta

Reputation: 1939

Seems you are somewhat confused on how to retrieve the values of p & q using ACF & PACF plots. If this is the case (assuming the blue region to be 95%/90%/99% confidence interval, depends on the significance level decided by you), you need to closely observe the values where they cross this blue region. the value where your plot enters the blue region for ACF gives us p & the value where the plot enters the blue region for PACF gives you q value.

I guess what is leading to the confusion is the plot type chosen. Do try to plot the same graphs using line plot. The values will be quite obvious then. In your case, I feel p=0/1, q=0/1 should do it. For exact values, you can try hit & trial on these values.

If you wish to explore more:https://medium.com/data-science-in-your-pocket/preprocessing-for-time-series-forecasting-3a331dbfb9c2

Upvotes: 1

Related Questions