## Monday, December 22, 2014

### Statistical Models and Econometric Models

Statistical models are the models built with statistical techniques. The counterpart can be artificial intelligence models, which are based on artificial intelligence. (Note that statistics and artificial intelligence are not mutually exclusive.) If a statistical model includes economic variables, no matter on the left or right side of the equation, the model can be called an econometric model.

Most forecasting analysts graduate from either economic department or statistics department. Depending upon their education background, they may call the same forecasting models differently. People with economics major usually call their models econometric models, while people with statistics major often call their models statistical models.

In long term load forecasting, we often hear about econometric models, because economy is a driver of long term electricity demand and many long term load forecasters are economics graduates. In short term load forecasting, we often hear about statistical models, because economic indicators are rarely used there and the forecasters are often statistics graduates.

Another way to name the models is based on the individual techniques. For example, we can call those ARIMA models time series models. If the models are built through regression analysis, we can call them regression models. Note that time series models may include regressors, such as ARMAX models. Regression models may include lagged dependent variables, such as dynamic regression models.

The terms may be confusing when people mix the naming conventions. For instance, some people like to talk about econometric regression models, which seems redundant to me. Another confusing term is time series regression models. Some people use it to refer to regression models with lagged loads, which should have been called dynamic regression models. Some people use it for regression models applied to time series data, which should have been just called regression models.

p.s., because the two areas (econometrics and statistics) are too close, some professors are associated with both departments, i.e., David Dickey.

p.p.s., Rob Hyndman had a blog post explaining the differences statisticians and econometricians.