The three questions below will guide
the selection of appropriate methods to quantify the relationship
between total costs and length of stay and birthweight.
-
What is the response
(Y) of interest and how is it measured? Total costs is the response
variable found in the problem statement. It is a continuous variable.
-
Are predictor variables
mentioned in the problem statement? If so, how many and what are
their measurement levels? The problem statement requests a simultaneous
prediction of total costs from length of stay and birthweight. Both
of these predictor variables are continuous.
-
What are you being asked
to deliver? A data description, an interval estimate, an answer to
a question, or a predictive model? You are being asked to quantify
the relationship between total costs and length of stay and birthweight.
A predictive equation will quantify this relationship. A multiple
linear regression is a good starting point for developing a predictive
equation. Multiple regression is a flexible modeling method to predict
a continuous variable from nominal, ordinal, or continuous independent
variables.