Underlying Assumptions for Process Modeling
Implicit Assumptions Underlie Most Actions
Most, if not all, thoughtful actions that people take are based on
ideas, or assumptions, about how those actions will affect the goals
they want to achieve. The actual assumptions used to decide on a
particular course of action are rarely laid out explicitly, however.
Instead, they are only implied by the nature of the action itself.
Implicit assumptions are inherent to process modeling actions, just
as they are to most other types of action. It is important to
understand what the implicit assumptions are for any process modeling
method because the validity of these assumptions affect whether or not
the goals of the analysis will be met.
Checking Assumptions Provides Feedback on Actions
If the implicit assumptions that underlie a particular action are not true,
then that action is not likely to meet expectations either. Sometimes it
is abundantly clear when a goal has been met, but unfortunately that is not
always the case. In particular, it is usually not possible to obtain immediate
feedback on the attainment of goals in most process modeling applications.
The goals of process modeling, sucha as answering a scientific or engineering question,
depend on the correctness of a process model, which can often only be directly
and absolutely determined over time. In lieu of immediate, direct feedback,
however, indirect information on the effectiveness of a process modeling
analysis can be obtained by checking the validity of the underlying
assumptions. Confirming that the underlying assumptions are valid helps
ensure that the methods of analysis were appropriate and that the results will
be consistent with the goals.
Overview of Section 4.2
This section discusses the specific underlying assumptions associated with
most model-fitting methods. In discussing the underlying assumptions,
some background is also provided on the consequences of stopping the modeling
process short of completion and leaving the results of an analysis at odds
with the underlying assumptions. Specific data analysis methods that can be
used to check whether or not the assumptions hold in a particular case are
discussed in Section 4.4.4.
Contents of Section 4.2
- What are the typical underlying assumptions in process modeling?
- The process is a statistical process.
- The means of the random errors are zero.
- The random errors have a constant standard deviation.
- The random errors follow a normal distribution.
- The data are randomly sampled from the process.
- The explanatory variables are observed without error.