Observed Data for Bayesian Analysis
Bayesian Analysis is available in UNIPASS V5.0. The Bayesian analysis is a method to estimate the
distribution parameters based on the observed data. In this approach, the
unknown distribution parameters are assumed (or modeled) to be also random
variables, a hyper parameter distribution. With this approach, subjective
judgments based on intuition, experience, or indirect information is
incorporated systematically with observed data to obtain a balanced estimation.
There are several advantages of the Bayesian analysis:
-
It allows for direct probability statements,
such as the probability that an experimental procedure is more effective than
a standard procedure.
-
It allows for calculating probabilities of
future observations.
-
It allows for incorporating evidence from
previous experience and previous experiments into overall conclusions.
-
It is subjective. This is a standard
objection to the Bayesian approach; different people reach different
conclusions from the same experiment results. There would be comfort in
giving an answer that others would also give. But differences of opinion are
the norm in science and engineering and, therefore, an approach that
explicitly recognizes such difference is realistic.
A
hyper parameter distribution (conditional distribution)
is necessary for the Bayesian Analysis as an example shown in the following
Figure.
Figure 1. A
hyper parameter distribution for Bayesian Analysis
 To enter the
observed data, click the Bayesian dada button. Then type in the observed data in
the “Input Observed Dada for Bayesian Analysis Window as an example below.
Figure 2. An
example of observed data for Bayesian Analysis
Click the Check Button to save the data.
NOTE:
-
If the Bayesian Data Button is clicked for a
random variable other than hyper parameter distribution, the following error
message will show up in the screen.
Figure 3. Error
message for a non hyper parameter distribution in Bayesian Analysis
-
The observed data input as an example shown in
Figure 2 is bonded with Variable No (see example of 3 in Figure 1). Therefore,
if users change the Variable No and, the observed data should be re-entered
before click the Update Data button to save the input information.
| 
