Current location - Training Enrollment Network - Mathematics courses - What is the main difference between classical linear regression and nonlinear regression?
What is the main difference between classical linear regression and nonlinear regression?
The classical linear regression model assumes the following:

1, zero mean hypothesis. That is, given xt, the mathematical expectation (mean) of the random error term is 0, that is, E(ut)=0.

2. Homovariance hypothesis. The variance of the error term ut has nothing to do with t and is a constant.

3. There is no autocorrelation hypothesis. In other words, different error terms are independent of each other.

4. Explain the hypothesis that variables have nothing to do with random error terms.

5. Normality assumption, that is, assume that the error term ut obeys a normal distribution with a mean of 0 and a variance of the square of the west tower.

Relevant standards:

1, the independent variable must have a significant influence on the dependent variable and show a close linear correlation.

2. The linear correlation between independent variables and dependent variables must be true, not formal.

3. Independent variables should be mutually exclusive, that is, the degree of correlation between independent variables should not be higher than that between independent variables and dependent variables.

4. Independent variables should have complete statistical data, and their predicted values are easy to determine.