User:Dunny49/sandbox

Heading text
Big text Econometric Automata Theory

Heading text
The purpose of Econometric Automata Theory or (EAT) is a two stage method of bootstrapping econometric models.

The first stage is the production of unique econometric estimations from data subsets having independent variables corresponding to categoration enables data subsets to be created by the catagoration variable(s). An example of this is observed in panel data sets whereby categoration is essential. Each data subset is required to be identical in observation size and solely derived from the overall data set used. Note that the normal assumptions used for generalized econometric estimation are assumed to

The second stage the uses the unique values estimated from each data subset, to create a new set of forecasted observations unique to each categoration variable. In the example of panel data used, the data subsets allow estimation of dependent variables that are refined and more accurate than using the entire dataset to produce a singular econometric estimation of the overall panel data used. The corresponding variance and covariance data generated from each subset estimation is assumed to be unique but consistent with traditional statistical analysis of panel data.

corresponding to a relevant category of unique subsets of data derived from the data set from the unique to each subset of data for the using unique data corresponding to a specific subset of data used for each dependent variable observation used by combining demographic data in panel form with time-series data to create econometric forecasts by (for example) a panel data category. As an example, consider a grid with ∑ i=1 to n cells placed over the map of a city. Each grid element gi corresponds to a category of demographic panel data. This implies a unique array with. The surrounding cells are estimated in the same manner using the proposed econometric model with each cell producing a unique forecast. Then each cell surrounding the