Level: Advanced
Venue: 2019 AACE International Conference & Expo, June 16-19, 2019, New Orleans, LA, USA
Abstract: There are seven rules that define and substantiate causality. The very first task to any analysis is to define for the problem what is necessary and sufficient to define discovery boundaries. Developing a hypothesis requires problem definition. The analyst must have some experience in the subject matter to make a creditable conjecture about the phenomena that is occurring. Proving causality normally results in compromise because there is insufficient data, time, experience, etc. Therefore, when causality cannot be determined, there must be statistical safeguards in place to keep the conclusions of the analysis within the acceptable discovery boundaries. When causality cannot be proven, the study is simply a statistical analysis resulting in a correlation that may not be valid, applicable, or significant.
Venue: 2019 AACE International Conference & Expo, June 16-19, 2019, New Orleans, LA, USA
Abstract: There are seven rules that define and substantiate causality. The very first task to any analysis is to define for the problem what is necessary and sufficient to define discovery boundaries. Developing a hypothesis requires problem definition. The analyst must have some experience in the subject matter to make a creditable conjecture about the phenomena that is occurring. Proving causality normally results in compromise because there is insufficient data, time, experience, etc. Therefore, when causality cannot be determined, there must be statistical safeguards in place to keep the conclusions of the analysis within the acceptable discovery boundaries. When causality cannot be proven, the study is simply a statistical analysis resulting in a correlation that may not be valid, applicable, or significant.