Optimizely, a website optimization platform, just released what company execs describe as an innovative capability that breaks from traditional statistical methods. 

The platform -- Stats Engine -- adds to the company’s experience optimization platform by delivering test results that are "always valid" and "freed from the limitations of traditional statistical analysis," officials at the San Francisco-based provider boasted. Pete Koomen, co-founder of Optimizely, said Stats Engine "represents a breakthrough in the world of online testing."

Developed in collaboration with statisticians at Stanford University, company officials said Stats Engine relies on innovative approaches in statistical analysis. Combined with the company's own algorithms, it allows customers to interpret and act on data quicker "and more confidently than ever before," the company noted.

Stats Engine "propels statistical analysis into the Internet age," a company spokesperson told CMSWire.

Who Are These Guys?

Forrester Research characterized the online testing space as a growing one in early 2013, and it recognized Optimizely as one of the leaders.

It launched in 2010 and has more than 300 employees in its San Francisco headquarters. Company officials told CMSWire it's generated triple-digit annual revenue growth since its launch. To date, the company has raised $88 million in venture funding, most recently closing a $57 million Series B round of financing led by Andreessen Horowitz, with participation from Benchmark Capital and Bain Capital Ventures. 

Company officials said the primary benefit of Stats Engine is the ability to continuously monitor the rich stream of information created inside a web or mobile test and get to actionable results more quickly.

Stats Engine extracts valid, actionable data at any point in time rather than having to wait for an experiment to reach a pre-determined sample size, explained Helen Phung, senior public relations manager, explained.

The company claims it's the first in the industry to combine sequential hypothesis testing and multiple testing corrections and apply them to real time data sets. In so doing, Optimizely reduces the built-in limitations of traditional statistics that can result in experiment error rates of more than 30 percent.