Forecasting a production value based on its history

[Aziz Essouaied]

Hello Stata users, I have this little data at hand:

* Example generated by -dataex-. To install: ssc install dataex
clear
input int Année long Collecte_Orge_Tendrequintal
2018  894769
2019 3329222
2020  577747
2021  203212
2022  404185
2023    5044
end
format %ty Année

As you can see, it is a little time serie about the production of soft barely from 2018 to 2023. What I want to do is construct a little forecasting model that would help me forecast the production value for 2024 and even the years after that. I guess it is going to be a forecasting that depends on the history of the production, in other words, I want the forecasting of the 2024 production to take the 2023 production in consideration.

Any Help please? With many thanks!

[Nick Cox]

From just any statistical procedure or model it should look as if soft barley will die or not to be grown within 2024.

[JJ Kovach]

Check out any intro to operations management or supply chain management textbook for the basics of time-series forecasting algorithms. For simplicity you can simply regress barley as a function of year for a linear projection. But as Nick said, if the data you show is representative of your actual data, then there is a pretty severe negative trend.

[Nick Cox]

A trend is a trend is a trend,
But the question is, will it bend?
Will it alter its course
Through some unforeseen force
And come to a premature end?

-- Alexander Cairncross

Cairncross, A. 1969. Economic forecasting. The Economic Journal, 79: 797-812. doi:10.2307/2229792 (quotation on p.797)