The generic accessor functions `coef`

, `effects`

,
`fitted`

and `residuals`

can be used to extract
various useful features of the value returned by `lm`

.

The working and response residuals are ‘observed - fitted’. The
deviance and pearson residuals are weighted residuals, scaled by the
square root of the weights used in fitting. The partial residuals
are a matrix with each column formed by omitting a term from the
model. In all these, zero weight cases are never omitted (as opposed
to the standardized `rstudent`

residuals, and the
`weighted.residuals`

).

How `residuals`

treats cases with missing values in the original
fit is determined by the `na.action`

argument of that fit.
If `na.action = na.omit`

omitted cases will not appear in the
residuals, whereas if `na.action = na.exclude`

they will appear,
with residual value `NA`

. See also `naresid`

.

The `"lm"`

method for generic `labels`

returns the
term labels for estimable terms, that is the names of the terms with
an least one estimable coefficient.