Introduction to Statistical Analysis and Outlier Detection Methods

White Papers > Data Science > Introduction to Statistical Analysis and Outlier Detection Methods

Our friends over at Noah Data have written a research style paper, Introduction to Statistical Analysis and Outlier Detection Methods, that discusses how statistical data can generally be classified in terms of number of variables as Univariate, Bivariate or Multivariate. Univariate data has only one variable, Bivariate data has two variables and Multivariate data has more than two variables.

The paper addresses Multivariate Outlier detection which is a ubiquitous use case across industries. These can be used on summarized (moving average, standard deviation etc.) high frequency IoT variables to calculate outlier source of those variables. These can be used for machine learning based predictive maintenance of physical equipment assets. The same can be applied in oil & gas industry for very similar use case. This topic is extremely critical to a data scientist. R code is included to demonstrate the principles outlined in the paper.

 

 

Contact Info

Work Email*
First Name*
Last Name*
Address*
City*
State*
Country*
Zip/Postal Code*
Phone*

Company Info

Company*
Company Size*
Industry*
Job Role*

Survey

Custom Question*

All information that you supply is protected by our privacy policy. By submitting your information you agree to our Terms of Use.
* All fields required.