ARBIMETRA · Financial intelligence, made practical.

ARBIMETRA LAB

SARIMA

Extends ARIMA with seasonal terms for series with repeating patterns.

What it does

Extends ARIMA with seasonal terms for series with repeating patterns.

Use it for monthly or quarterly series with seasonality.

Data you need

  • One series
  • Orders p, d, q, P, D, Q and s

Supported data: Time series. Level: Advanced.

Formula and method

φ(L)Φ(Lˢ)(1−L)ᵈ(1−Lˢ)ᴰyₜ = θ(L)Θ(Lˢ)εₜ

Ordinary and seasonal polynomials are multiplied into one state-space model, with differencing at lag 1 and at the seasonal lag. The parameters maximise the Gaussian likelihood after excluding observations lost to differencing.

Assumptions

  • The series is stationary after any differencing
  • Errors are uncorrelated with constant variance
  • The seasonal pattern is stable

Input checks

  • Enough observations for seasonal differencing
  • Convergence is required

How to read the result

The airline model (0,1,1)(0,1,1)₁₂ is a common starting point.

Worked example

Illustrative run on Box-Jenkins airline passengers. These figures are the actual output of this model on that example, and they say nothing about your own data.

  • AIC = -483.3929, BIC = -474.7673. Ljung-Box p = 0.4836.
  • Remaining residual autocorrelation is not statistically significant at the 5% level.

Limitations

  • Results depend on the sample period

Numerical validation

Validated 17 of 17 automated checks passed, including numerical results, invalid input, missing values, small samples, constant variables, charts and the interpretation text.

CheckReferenceResultAbs. errorToleranceSource
Airline model: θ-0.4018-0.402036992.4e-45e-3Box-Jenkins airline model, as published with R output
Airline model: Θ-0.5569-0.556983938.4e-55e-3Box-Jenkins airline model, as published with R output
Airline model: σ²0.0013480.001348077.0e-82e-2Box-Jenkins airline model, as published with R output

Computed with python 3.13.2, numpy 2.2.5, scipy 1.14.1, pandas 2.3.3, statsmodels 0.14.4, scikit-learn 1.7.0, in your browser. A passing check confirms the listed comparison only. It does not make any result suitable for your data, and it is not a claim of equivalence with other statistical software.

Questions

What does the seasonal period mean?

It is the number of observations in one cycle, such as 12 for monthly or 4 for quarterly data.

ARBIMETRA LAB is an educational and research tool. Results should be checked by the researcher and are not professional advice.