Research on the Prediction Method of Weighted Regression Based on Sample Size

Regression analysis is a prediction method to determine the dependence between controllable variables and expected values of predictors. It is worth noting that the reality often cannot get the complete data in the study, this makes the regression analysis result is affected, although the study of classical regression model is more, but most are based on sample data integrity, data completely reliable as the basic premise, and does not take into account the sample data reliability problems caused by incomplete samples reliable degree affect the nature of the result of the regression model. This paper is based on statistical theory. The effect of sample size on prediction results is analyzed, the measurement strategy of sample credibility based on sample size is given, a sample aggregation method based on mean value is proposed, a weighted regression model based on sample size is established. Then, the comparative analysis is carried out by combining the concrete case with the common regression method. The results show that this method has good interpretability and maneuverability, and enriches the existing regression methods to some extent.