This is documentation for Mathematica 8, which was
based on an earlier version of the Wolfram Language.

# Weights

 Weights is an option for various fitting and other functions which specifies weights to associate with data elements.
• Weights associates weight 1 with all data elements.
• Weights associates weight with the i data element.
• Weights->func associates weight with the i data element.
Fit a model using equal weights:
Give explicit weights to the data points:
Compute weights from values:
Compute weights from the response values:
Fit a model using equal weights:
 Out[1]=
Give explicit weights to the data points:
 Out[2]=
Compute weights from values:
 Out[3]=
Compute weights from the response values:
 Out[4]=
 Scope   (2)
Use weights in a nonlinear model:
Give explicit weights to the data points:
A generalized linear model:
Logit model:
Probit model:
Weight by a function of multiple variables:
Use default equal weights:
Compute weights from the response values:
 Applications   (1)
Fit a nonlinear model using measurement errors as weights:
Obtain standard errors for the parameters:
Compare to estimates with weights not assumed to be from measurement errors:
Weights impact the relative importance of data points on the fitting:
Scaling by a constant does not change the parameter estimates:
Obtain parameter estimates from a weighted linear fitting:
LeastSquares gives the equivalent result when weights are incorporated:
New in 7