Do Amazon book ranks tell us anything?  Sure, they convey something about the popularity of a given book, but looking a the current rank of a book on Amazon is just a snapshot of a fairly volatile number.  It would be much more useful if we could see how the ranks of books have changed over time.  Fortunately, that is fairly easy to do.

 The site www.metricjunkie.com allows anyone to track Amazon sales ranks of up to ten books.  I track my books on Metric Junkie and I see how the ranks change when my publisher does a promotion, when an ad comes out in a magazine, when I’m interviewed by a radio host, when I speak at a conference, and so on.  Since I also track some other books in similar categories, I can even see that their are seasonal and weekly cycles that affect all business books.

This site made me wonder if this could tell us even more.  Can the ranks of books about a topic like buying homes or how to interview for a job tell use something about bigger trends than the sales of a single book?  I think it is possible and that is part of the topic of my next book.

Stay posted,

Doug

Who really knows what drives Amazon’s decisions about how books should be categorized?  Not me.  The first edition of How to Measure Anything was categorized on Amazon as “math for business” and it was virtually always able to hold the #1 rank in that category for the three years since its publication.

Now the second edition has been categorized, instead, as “statistics”.   I was concerned that the new category might exclude more readers but it hasn’t seem to have that effect.  Statistics is also a more competitive category.  But my concerns seemed to be misplaced.  It has held the #1 rank in statistics almost every day since its release and the overall Amazon rank has also been consistently better.  Perhaps the new category will help it reach more people after all.  What was I thinking questioning Amazon’s judgment, anyway?

Doug Hubbard

Wiley has decided to accelerate the release of the second edition of How to Measure Anything.  Instead of being released in May, it will be shipped to warehouses this month and ready for sale in early April.  Apparently, the book is a source of a lot of positive buzz in the publisher’s offices and they saw a business opportunity for getting it out faster.  I have definitely noticed a sense of getting “special attention” on every aspect of the development of the second edition. 

My readers routinely tell me that they heard about the first edition at the some big conference or, in some cases, was made required reading by their superiors.  It has been the #1 bestseller in Amazon’s math for business category for two years and is in the toop 100 of all management books.  I’m told this is unprecidented.  I’m also told that Wiley has recieved an exceptionally high number of advanced orders for the second edition.

Now all I need is a viral video…

Doug Hubbard

I’m reintroducing the Measurement Challenge for the blog.  I ran it for a couple of years on the old site and had some very interesting posts. 

Use this thread to post comments about the most difficult – or even apparently “impossible” – measurements you can imagine.  I am looking for truly difficult problems that might take more than a couple of rounds of query/response to resolve.  Give it your best shot!

Doug Hubbard

I came across more interesting research about possible “placebo effects” in decision making.  According to the two studies cited below, receiving formal training in lie detection (e.g. so that law enforcement officers are more likely to detect a untruthful statement by a suspect) has a curious effect.  The training greatly increases confidence of the experts in their own judgments even though it may decrease their performance at detecting lies.  Such placebo effects were a central topic of The Failure of Risk Management.  I’m including this in the second edition of How to Measure Anything as another example of how some methods (like formal training) may seem  to work and increase confidence of the users but, in reality, don’t work at all.

• DePaulo, B. M., Charlton, K., Cooper, H., Lindsay, J.J., Muhlenbruck, L. “The accuracy-confidence correlation in the detection of deception” Personality and Social Psychology Review, 1(4) pp 346-357, 1997
• Kassin, S.M., Fong, C.T. “I’m innocent!: Effect of training on judgments of truth and deception in the interrogation room” Law and Human Behavior, 23 pp 499-516, 1999

Thanks to my colleague Michael Gordon-Smith in Australia for sending me these citations.

Doug Hubbard

I get many emails about the validity of Risk Maps, Risk Scores and Risk Matrices in risk analsysis.  I know there are a lot of passionate proponents of these methods (and many heavily-invested vendors) but there is still no evidence that such methods improve forecasts or decisions. 

Read my skeptical look at many risk analysis methods in the OR/MS Today and Analytics articles (See the Articles page).  I compiled quite a lot of research in these articles and even more in my book that should lead any manager to be suspicious about whether the perceived effectiveness of these methods is real or imagined. 

I’ve updated the upcoming second edition of How to Measure Anything with even more research in that vein.  Stay tuned and post your comments.

Doug Hubbard

See the webinars page to sign up for intensive training sessions for Applied Information Economics.  You can take the popular “Calibration” webinar or even sign up for the full AIE Module I & II training (required for AIE Level I certification).  Each webinar is scheduled for multiple dates and times so that you are sure to find something that fits your schedule.  Contact HDR for group rates.

We have a new batch of the 4-page, color, laminated reference cards for How to Measure Anything. Some of the material is actually already updated for the upcoming second edition of the book (spring 2010). See the products page for details.

The article I co-authored with Doug Samuelson in Analytics Magazine just came out with the fall issue. “Analysis Placebos: The Difference Between Percieved and Real Benefits of Risk Analysis and Decision Models.” explains why many popular analysis methods and models may have entirely illusory benefits. See the online version of the article at http://viewer.zmags.com/publication/2d674a63#/2d674a63/15

See the Events page on www.hubbardresearch.com. The webinars in August in September did very well and demand continues to grow. There are several webinars of different lengths, topics and times that are sure to fit your needs.