Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

# Methods to make smarter simulation setups

IP.com Disclosure Number: IPCOM000240548D
Publication Date: 2015-Feb-09
Document File: 4 page(s) / 236K

## Publishing Venue

The IP.com Prior Art Database

## Abstract

Methods to analyze and incorporate (if present) the Interaction effect (besides the main effect) of categorical independent variables on the dependent simulation variable in simple (involving only two categorical independent variables) and complex (involving more than two independent categorical variables) simulation setups, under both the conditions when either the simulation is being setup by the use of automatic probability function identification using historical data sets, or when manually feeding the expressions and probability distribution function parameters to setup and initiate a simulation.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 01 of 4

Methods to make smarter simulation setups

Background and Problem Definition

In any study involving understanding the effect of categorical independent variables over the dependent variable, if the independent variable has any effect on the dependent variable it is called the Main effect . If any of these independent variables has any effect on the effect of any other independent variable's effect on the dependent variable, then this effect is called the Interaction effect.

It may also happen that such independent variable alone seems to have no direct effect on the dependent variable (i.e. No Main Effect), but it may influence the effect of other independent variable on the dependent variable at different levels of that independent variable. In such case it is said to have only Interaction effect and no Main effect. So an independent variable can demonstrate both, either or none of these Main and Interaction effects.

So if for example we have two independent categorical variables say variable A, and variable B, their effect on a dependent variable, say C can be in one of the following ways:
◦ Main Effect of A Only, But no Main Effect of B, and No Interaction Effect between A-B
◦ Main Effect of B Only, But no Main Effect of A, and No Interaction Effect between A-B
◦ Main Effect of A + Main Effect of B, But No Interaction Effect between A-B
◦ No Main Effect of B, Only Main Effect of A + Interaction Effect between A-B
◦ No Main Effect of A, Only Main Effect of B + Interaction Effect between A-B
◦ No Main Effect of A, No Main Effect of B, Only Interaction Effect between A-B
◦ No Main or Interaction Effect of either A or B

But when simulating complex scenarios involving multiple discrete events, we evaluate only the main effect of these events on the dependent variable or the result of the simulation equation, without paying any attention to the fact that such independent variables/ events can h...