Relative Error Linear Combination Forecasting Model Based on Uncertainty Theory

The traditional combination forecasting model has good effect, but it needs precise historical data. In fact, many random events are uncertain, and much of the data imprecise; sometimes, lacking. We need to study problems by means uncertainty theory. Uncertain least squares estimation is an important technique uncertain statistics, way deal with imprecise data, one best methods solve unknown parameters linear regression equations. On basis method estimation, this paper proposes two kinds models, which unary relative error model, respectively. set up several piecewise models according different periods and, certain weights, These combined into a better effect. new that combines estimation. Compared can problem verify feasibility through numerical example. According analysis, compared existing effect proposed better.