1
$\begingroup$

I’m trying to project TPES (Total Primary Energy Supply) by country in Africa up to the year 2100 under different SSP (Shared Socioeconomic Pathways) scenarios, the same framework used in the latest IPCC reports.

Here’s the data I currently have:

Population by country and SSP scenario, up to 2100

GDP by country and SSP scenario, up to 2100

CO₂ emissions by country and SSP scenario, up to 2100

Historical TPES data by country, up to around 2022–2023

I have already tried several methods such as linear regression, XGBoost, and Random Forest to predict future TPES values by country.

However, I also have an additional dataset: aggregated TPES by SSP scenario for the combined Africa + Middle East region (not disaggregated by country). I’d like to use this extra information to refine or inform my country-level projections.

Do you know of a suitable statistical or Bayesian method that could efficiently leverage both the country-level and regional-level data?

I was considering a hierarchical Bayesian linear model, where the country-level parameters are partially pooled toward the regional estimates, but I’m having trouble understanding how to implement this kind of model correctly for my data structure.

Any suggestions or references on how to structure such a model would be greatly appreciated.

Improve this question
$\endgroup$

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.