I am having trouble deciphering the equation from SPSS Output for a time series model. In particular this concerns two outpust.

  1. The expert model suggest for a time series of monthly sales a MA 1 process and a difference 1 and ln transformation. The MA 1 process has a beta of 0.687. I feel that I miss information from the output.

$$ \Delta ln{(sales_t)} = 0.687 \Delta \ln{(sales_{t-1})} $$

  1. For another sales series, the expert modeler suggests an ARIMA (1,0,0). For the sales series, it is a simple AR 1 process with beta 0.352 and a constant 15.524. An independent variable 'ad budget' is included as well. It suggests for the 'ad budget with Lag 0 as a numerator with 0.407 and with Lag 1 as a denominator with -0.811. I am particularly unsure if it is -0.811 or $\frac{1}{-0.811}$

This is what I came up with so far.

$$ ln{(sales_t)} = 15.524 + 0.352 \ln{(sales_{t-1})} + 0.407 \ln{(budget_{t})} - 0.811 \frac{1}{\ln{(budget_{t-1})}} $$

Thanks for any input regarding both outputs.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.