Standard Response Surface - Full 2nd-Order Polynomial

The meta-modeling algorithms are categorized as:

General Definitions
Linear Regression Analysis

General Definitions

The error sum of squares SSE is:

(1)

where:

= value of the output parameter at the sampling point
= value of the regression model at the sampling point

The regression sum of squares SSR is:

where:

The total sum of squares SST is:

For linear regression analysis the relationship between these sums of squares is:

Linear Regression Analysis

For a linear regression analysis, the regression model at any sampled location , with in the -dimensional space of the input variables can be written as:

where:

= row vector of regression terms of the response surface model at the sampled location
= = vector of the regression parameters of the regression model
= total number of regression parameters. For linear regression analysis, the number of regression parameters is identical to the number of regression terms.

The regression coefficients can be calculated from:


Release 18.2 - © ANSYS, Inc. All rights reserved.