Sample size: the number of (selected) data pairs.Function not defined for all values of independent variable: the calculation of the model resulted in an error, for example a division by zero.Bad model or bad initial parameters: the program failed to find a solution for the given model using the supplied initial parameters.This may indicate a poor model fit or poor initial parameter values. Maximum numbers of iterations exceeded: the iteration process stopped because the maximum number of iterations was reached.Convergence tolerance criterion met: the iteration process has completed because the difference between successive model fits became less than the Convergence tolerance value.Next the reason of iteration process termination is given: This section shows the tolerance and iterations settings. Show residuals window: option to create a residuals plot.Show scatter diagram & fitted line: option to create a scatter diagram with fitted line.Maximum numbers of iterations: the iteration process stops when the maximum number of iterations is reached (when the number of iterations is unexpectedly large, the model or initial parameter values may be inaccurate).You can enter a small number in E-notation: write 10 ×10 as 1E-10 The convergence tolerance influences the precision of the parameter estimates. Convergence tolerance: the iteration process completes when the difference between successive model fits is less than this value. These symbols do not have any significance in any other part of the program. Note: &X, &Y, and &FILTER can only be used in the manner described here in the context of parameter initialization for nonlinear regression. For example: when "Response" is selected as the dependent variable, then you can use the function VMAX(&Y) as the initial value of a parameter, and VMAX(&Y) will return the Maximum value of the variable "Response". The symbol &FILTER can be used to refer to the selected data filter. These functions can refer to the selected X- and Y-variables by means of the symbols &X and &Y respectively. To enter initial values, you can make use of the different statistical spreadsheet functions on variables. Parameters list and initial values: enter initial values (best estimates) for the different parameters.When not all intended parameters are extracted, you probably have made some error(s) in naming the parameters or in the regression equation. Get parameters from equation: let the program extract the parameter names from the regression equation.Filter: space for an optional filter to include a subset of data in the analysis.Variable X: select the independent variable.Variable Y: select the dependent variable. In addition, parameter names should not start with a number and must be different from reserved words such as TRUE, FALSE, ROW and COLUMN. Parameter names must not be equal to any variable name in the spreadsheet, but just like variables, parameter names cannot include spaces, nor the following characters: - + / * = # & $ | ^ :. The parameters can also be represented by more meaningful names such as for example 'slope'. The different parameters can be represented by single characters a. The nonlinear regression equation must include the symbol x, which refers to the independent variable that is selected in a different input box (see below). In this example, a and b are the parameters to be estimated.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |