Primary Author: Dr. Sang-Hoon Lee, PE
Co-Author(s): Matthew T. Reiland; James D. Whiteside, II PE FAACE
Audience Focus: Advanced
Application Type: Application
Venue: 2014 AACE International Annual Meeting, New Orleans, LA, USA
Abstract: Correlation does not prove causality. Many companies and individuals make significant decisions based on statistical correlation in an attempt to defend change to systems, investments, methodologies, staffing, performance evaluation, corrective action, etc. and to prove a point. Taking action based on “statistically significant” events may be misleading and nothing more than the inappropriate use of math and “science” to justify an opinion of a dominate player.
The methodology outlined in this paper is based on the time-tested approach to data analysis to prove causality. There are several steps that need to be performed to prepare the data population before causality can be investigated. This paper requires the reader to have a very good understanding of the theory and application of statistical analysis and multivariate regression.
Outlined in this paper is:
1) Brief review of the purpose and application of statistics
2) Benchmarking Rules
3) Data filtering and population analysis
4) Reiland Format for benchmarking transparency
5) Calculation of an index based on the data population
6) Determining causality using multivariate regression
Co-Author(s): Matthew T. Reiland; James D. Whiteside, II PE FAACE
Audience Focus: Advanced
Application Type: Application
Venue: 2014 AACE International Annual Meeting, New Orleans, LA, USA
Abstract: Correlation does not prove causality. Many companies and individuals make significant decisions based on statistical correlation in an attempt to defend change to systems, investments, methodologies, staffing, performance evaluation, corrective action, etc. and to prove a point. Taking action based on “statistically significant” events may be misleading and nothing more than the inappropriate use of math and “science” to justify an opinion of a dominate player.
The methodology outlined in this paper is based on the time-tested approach to data analysis to prove causality. There are several steps that need to be performed to prepare the data population before causality can be investigated. This paper requires the reader to have a very good understanding of the theory and application of statistical analysis and multivariate regression.
Outlined in this paper is:
1) Brief review of the purpose and application of statistics
2) Benchmarking Rules
3) Data filtering and population analysis
4) Reiland Format for benchmarking transparency
5) Calculation of an index based on the data population
6) Determining causality using multivariate regression