nav[aria-label="Primary Navigation"] { padding: 0; & ul { list-style: none; width: 100%; display: flex; flex-direction: row; justify-content: start; align-items: start; gap: 30px; padding: 0; & li { margin: 0; } & ul li { list-style: none; } } }

82408_en-US

liliconcom

Semi Equipment Routing Data is simulated or real data?

Hi,

in the equipment routing demo (where one compares ANOVA with Partitioning), is the data simulated by ourself or some data available from a resource like university or is it even real semi data? A customer thought about Partitioning looked too good to be real data.

Any input appreciated,

Martin

Re: Semi Equipment Routing Data is simulated or real data?

Hi Martin,

The data was created by Robert Anderson to illustrate solving what is a common problem in the semicondutor industry and the ease with which conditional effects are indentified through Partitioning (in this case a 3-way interaction effect that is easy to miss with other modelling methods). Although simulated data the key message are:

Partitioning enables easy determination of a 3-way interaction effect
The risk of missing this effect is high when using other approaches (I think there are 400 or so predictors) - how do you screen for higher order effects across so many predictors using other modelling approaches?