Comments for Jeb Stone > Analytics PhD http://jebstone.com Observation, commentary, and helpful hints at the intersection of web analytics and social science Sun, 13 Dec 2009 19:39:46 -0700 http://wordpress.org/?v=2.8.4 hourly 1 Comment on How to identify real trends in user behavior by zyxo http://jebstone.com/2009/12/how-to-identify-real-trends-in-user-behavior/comment-page-1/#comment-25 zyxo Sun, 13 Dec 2009 19:39:46 +0000 http://jebstone.com/?p=75#comment-25 The biggest variation in the day-to-day chart are the differences between the weekdays and the weekends. So the first thing to do if you want to look at longer-term trends is making a week-to-week chart in order to gid rid of this oscillating pattern. If by then the trend still is not clear, only then you should move on to more sophisticated methods. Try explaining your EMA to a HiPPO ! The biggest variation in the day-to-day chart are the differences between the weekdays and the weekends.
So the first thing to do if you want to look at longer-term trends is making a week-to-week chart in order to gid rid of this oscillating pattern. If by then the trend still is not clear, only then you should move on to more sophisticated methods.
Try explaining your EMA to a HiPPO !

]]> Comment on How to identify real trends in user behavior by jebstone http://jebstone.com/2009/12/how-to-identify-real-trends-in-user-behavior/comment-page-1/#comment-24 jebstone Thu, 10 Dec 2009 17:02:59 +0000 http://jebstone.com/?p=75#comment-24 Hey Steve, thanks for the great question! You're a step ahead of me: I use the EMA technique to visually indicate whether overall performance is really trending up or down. To that -- as you thoughtfully point out -- it's possible to add "guardrails" based on standard deviations. The guardrails then tell you whether any single day is inside or outside a typical range, while the EMA line identifies whether the movement is reliably a trend. I'll be writing about combining EMAs with standard deviations in a subsequent post, and post some SQL and SAS code for producing EMAs as well. Thanks for reading! Hey Steve, thanks for the great question! You’re a step ahead of me: I use the EMA technique to visually indicate whether overall performance is really trending up or down. To that — as you thoughtfully point out — it’s possible to add “guardrails” based on standard deviations. The guardrails then tell you whether any single day is inside or outside a typical range, while the EMA line identifies whether the movement is reliably a trend.

I’ll be writing about combining EMAs with standard deviations in a subsequent post, and post some SQL and SAS code for producing EMAs as well.

Thanks for reading!

]]> Comment on How to identify real trends in user behavior by Casey Carey http://jebstone.com/2009/12/how-to-identify-real-trends-in-user-behavior/comment-page-1/#comment-23 Casey Carey Tue, 08 Dec 2009 21:59:32 +0000 http://jebstone.com/?p=75#comment-23 Great article, I look forward to the day when more of these capabilities are standard in web analytics products. It really crossing the chasm between data/reporting to understanding/insight. For sites with significant shifts in volume between weekdays and weekends, I either average the base data on 7 days intervals or use only the weekday data. The picture becomes much clearer and exceptions are evident. Great article, I look forward to the day when more of these capabilities are standard in web analytics products. It really crossing the chasm between data/reporting to understanding/insight.

For sites with significant shifts in volume between weekdays and weekends, I either average the base data on 7 days intervals or use only the weekday data. The picture becomes much clearer and exceptions are evident.

]]> Comment on How to identify real trends in user behavior by Steve Jackson http://jebstone.com/2009/12/how-to-identify-real-trends-in-user-behavior/comment-page-1/#comment-21 Steve Jackson Tue, 08 Dec 2009 18:08:26 +0000 http://jebstone.com/?p=75#comment-21 What is the advantage of doing this over standard deviations? Tia steve. What is the advantage of doing this over standard deviations? Tia
steve.

]]> Comment on What it takes to compete (and win!) on analytics by Randy "World Wide" Weber http://jebstone.com/2009/10/what-it-takes-to-compete-and-win-on-analytics/comment-page-1/#comment-4 Randy "World Wide" Weber Sun, 25 Oct 2009 02:28:31 +0000 http://jebstone.com/?p=159#comment-4 Great post. Social scientists over MBAs? Really...? Yes. As someone who has an undergrad and a graduate degree in in the social sciences, as well as an MBA, I can tell you that my social science studies prepared me far more for management and marketing than my MBA. Regarding access to analytics, I've yet to work somewhere that I've had enough information to make informed pricing, product, and e-mail marketing decisions without a great deal of time and effort. At times I've had to spend as much as one day every week just assembling information. Time that should have been spent analyzing the data and developing tactics based on the analysis. Keep telling it like it is. Great post.

Social scientists over MBAs? Really…?

Yes. As someone who has an undergrad and a graduate degree in in the social sciences, as well as an MBA, I can tell you that my social science studies prepared me far more for management and marketing than my MBA.

Regarding access to analytics, I’ve yet to work somewhere that I’ve had enough information to make informed pricing, product, and e-mail marketing decisions without a great deal of time and effort. At times I’ve had to spend as much as one day every week just assembling information. Time that should have been spent analyzing the data and developing tactics based on the analysis.

Keep telling it like it is.

]]>