Policy Models, Randomness and Free Will

In my research work I have developed a lot of policy models (see one about the US Health Care System here). If the models have any "policy recommendations" there is  very good chance that (1) no one is paying attention and (2) even if they were, they would not take advice from my models. If this is so futile, why do I keep doing it? If I have free will, maybe I should just drop my modeling fixations and play more golf.

All my policy models are based on the simple state-variable equation S(t) = F[S(t-1),X(t-1), E(t-1)] where S is the state of the system, F is some function, X are the input variables, E are the random(?) errors and t is time. In this post, I'm going to discuss the random components, E. By construction, the E are independent of the state variables, S, but what are they really? Let me take an example from Sub-Saharan African (SSA) because in an upcoming post I'm going to present an SSA model.

The state variables are constructed from the raw data in the World Development Indicators (WDI) using Principal Components Analysis (PCA). The variables are CO2E (CO2 emissions), EG.USE (Energy Use), GDP, Total Labor Force (TLF) and POP (Total Population). The numbers are weights and the choice of variables is based on the Kaya Identity. The first component state variable is overall Growth, the second is (CO2-N), and the third is (GDP-N).* The three components explain 99% of the variation in the indicators and these are typically all that are needed to construct the state space model S(t) = F[S(t-1),X(t-1), E(t-1)] . SSA2 and SSA3 are called the Error-Correcting Controllers (ECCs) that keep the system on the growth path (maybe). The E are components 4 and 5, but what are they really?

I have estimated a state space model for SSA5 and an output graph is presented above (the solid line is actual data and the dashed red line is predicted). Testing shows that it is not a Random Walk but the model doesn't do a very good job of predicting the series and misses all the turning points until after they are made. In other words, after we have exhausted 100% of the variation in the underling data, we don't find "randomness" but rather forces that we can't predict very well and, by themselves, explain little variance in the overall system. It's not that SSA5=(POP-EG.USE) is uninteresting (it is a Population Energy Demand ECC), it just doesn't explain a lot of variance in Sub-Saharan Africa. It might in other regions of the world, just not here.

What explains most of time path of SSA data? You'll just have to wait until I present the model in an upcoming post. The points I want to make here are that (1) If I try to forecast the population-energy ECC out to 2060 (above), probably the best I can say is that there is going to be a correction from 2024 and (2) when the correction will happen and to what extent it will happened,  the model cannot predict. When future data comes in, the model can detect if a correction was made. One the other hand, maybe a regional war will interrupt the adjustment process. Time will tell (not the model).

Estimating the model does not seem futile. At least it uncovers a low-variance feedback process covering population energy use. And, if you know anything about economic models, you will know that the economic models mostly do not contain feedback effects. 

Maybe another point to make to highlight Sabine Hossenfelder's video on Free Will (above) is that Sub-Saharan Africa cannot be said to have free will. I will demonstrate in a future post that it is a macro-system with many human institutions but these institutions don't have "will." Causes of policy actions might be too complex to predict ahead of time, but models can tell us what happened after the fact and clarify the underling causal forces. That is something and I want to keep doing it.

NOTES

* (CO2-N) is an Environmental ECC. (GDP-N) is a Malthusian Crisis ECC. I'll explain ECCs more fully in future posts. For the time being, these results (at least for SSA) indicate that environmental damage and Malthusian Crisis are being monitored (at least in SSA) in attempts to maintain the growth path. ECCs will be different in different regions and different countries in the World-System.