Page 197 - DCAP601_SIMULATION_AND_MODELING

Unit 11: Design and Evaluation of Simulation Experiments (I)

11.1.4 Windows Properties Notes

1. Window properties define the appearance of the presentation window, that will be shown,
when the user starts the experiment.
2. Title: The title of the presentation window.

3. Enable panning: If selected, the user will be allowed to pan the presentation window.
4. Enable zoom: If selected, the user will be allowed to zoom the presentation window.
5. Width: [Enabled if Maximized size is not selected] The width of the presentation window.
If Maximized size option is selected, this setting makes no sense, since the window will be
maximized.
6. Height: [Enabled if Maximized size is not selected] The height of the presentation window.
If Maximized size option is selected, this setting makes no sense, since the window will be
maximized.

7. Maximized size: If selected, the presentation window will be maximized on model launch.
8. Show Toolbar sections properties section defines, what sections of the toolbar of the
presentation window are visible. To make some toolbar section visible, just select the
corresponding checkbox.
9. Show Statusbar sections properties section defines, what sections of the status bar of the
presentation window are visible. To make some status bar section visible, just select the
corresponding checkbox.

11.1.5 Parameters Properties

Parameters properties are available only when the root active object class of the experiment has
any parameters. Here you can define actual values for these parameters using expressions.
However, if you want just to initialize a parameter with a static value, we recommend you to use
controls on the General property page of the experiment.

11.2 Length of Simulation Run

To design a stochastic simulation experiment, it is caring to have an estimate of the simulation
run lengths required to achieve desired statistical precision. Preliminary estimates of required
run lengths can be obtained by approximating the stochastic model of interest by a more
elementary Markov model that can be analyzed analytically. When steady-state quantities are
to be estimated by sample means, we often can estimate required run lengths by calculating the
asymptotic variance and the asymptotic bias of the sample mean in the Markov model.
To design a stochastic simulation experiment, it is helpful to have an estimate of the simulation
run lengths required to achieve desired statistical precision. Preliminary estimates of required
run lengths can be obtained by approximating the stochastic model of interest by a more
elementary Markov model that can be analyzed analytically. When steady-state quantities are
to be estimated by sample means, we often can estimate required run lengths by calculating the
asymptotic variance and the asymptotic bias of the sample mean in the Markov model.

Simulation experiments are like exploring trips. We usually have initial goals, but the interesting
discoveries often come from the unexpected. We typically do not know in advance precisely
how we will proceed and we cannot predict all the benefits. In reality, most simulation
experiments are sequences of experiments, with new goals being based on successive discoveries;
see Albin (1984). Thus, there obviously is a limit to what can be planned; nevertheless simulation

LOVELY PROFESSIONAL UNIVERSITY 191