Graphics Reference
In-Depth Information
Figure
.
.
he let-hand panels shows data on dissolved oxygen (DO) in the Clyde estuary, plotted
against year and day within the year. he right-hand panels add smooth curves as estimates of the
underlying regression functions
ety of types of regression data. From this perspective, graphics are oriented towards
the exploration of appropriate models for data, as well as towards the display of the
observed data themselves. In Sect.
.
, simple methods of constructing smooth es-
timates are described and illustrated. he ideas are developed in the context of re-
sponse data on a continuous measurement scale, but the more general applicability
of the concept is indicated by an extension to binary response data. he graphical
methods employed are also extended beyond simple displays of the underlying re-
gression estimate to include indications of variability and of the suitability of simple
parametric models. hese concepts are extended further in Sect.
.
, where displays
of nonparametric regression surfaces relating a response variable to two explanatory
variables are discussed. he addition of information on variability and the suitability
of parametric modelsare revisited in this setting. Situations involving several covari-
atesarediscussedinSect.
.
,whereadditive modelsareusedtoprovidedescriptions
of each separate regression component. Some final discussion is given in Sect.
.
.
