A fitted value is a response predicted by a fitted statistical model at the observed values of its independent variables. In linear regression, if 
is the design matrix and
is the estimated vector of regression
coefficients, then the vector of fitted values is
The difference 
between an observed response and its fitted value
is the residual.
See also
Design Matrix,
Influential Point,
Linear Regression,
Regression
Coefficient,
Residual
Explore with Wolfram|Alpha
References
Cook, R. D. and Weisberg, S. Residuals
and Influence in Regression. New York: Chapman and Hall, 1982.
Cite this as:
Weisstein, Eric W. "Fitted Value." From
MathWorld--A Wolfram Resource. https://mathworld.wolfram.com/FittedValue.html
Subject classifications
