How Not To Sort By Average Rating
evanmiller.org
How Not To Sort By Average Rating
1–10 of 159 posts
Re: How Not To Sort By Average Rating
#2Every time I see that page, I see the equation, I read statistical terms and I get overwhelmed. I use PHP so I have no pnormaldist. Would love to use it for some random page I run.
Re: How Not To Sort By Average Rating
#3Every time I see that page, I see the equation, I read statistical terms and I get overwhelmed. I use PHP so I have no pnormaldist. Would love to use it for some random page I run.
See this example: http://www.derivante.com/2009/09/01/php-content-rating-confi...
However, if you install the stats package for PHP you can use stats_cdf_normal() as well.
Re: How Not To Sort By Average Rating
#4Every time I see that page, I see the equation, I read statistical terms and I get overwhelmed. I use PHP so I have no pnormaldist. Would love to use it for some random page I run.
I was overwhelmed too (here's simple wrong solution #1, here's simple wrong solution #2, here's incredibly complicated but more correct statistical solution #3 that you may not understand) but since this is relevant to my day job and we use PHP, I did find this:
http://www.derivante.com/2009/09/01/php-content-rating-confi...
I'm not a statistician so I can't speak to the correctness of this implementation.
Re: How Not To Sort By Average Rating
#5While it is good to look at these sorts of mathematically rigorous algorithms, I think I would be frustrated if it was used everywhere. Or, well, maybe not me perhaps, but a non technical user.
The beauty of the second algorithm for rating products is that it is straightforward. Having never seen it before I can deduce that 5 stars come before 4 stars and more reviews come before fewer. If I want to skip ahead to the 4 stars I know what to do. I can internalize the sorting algorithm easily. And as a user, understanding the order items are presented to me is important.
If Amazon were to use the last algorithm and present items in that order (assuming we accounted for the 5 star vs positive/negative issue), it would like a random order to most users and would be frustrating.
So I guess what I am saying is that this algorithm is very clever, but in some cases, it may be too clever. Sometimes you just want to keep it Simple Stupid.
Re: How Not To Sort By Average Rating
#6Every time I see that page, I see the equation, I read statistical terms and I get overwhelmed. I use PHP so I have no pnormaldist. Would love to use it for some random page I run.
Googling "Wilson score confidence interval php" returns an implementation as the top result.
Re: How Not To Sort By Average Rating
#7Every time I see that page, I see the equation, I read statistical terms and I get overwhelmed. I use PHP so I have no pnormaldist. Would love to use it for some random page I run.
"if you don't have a statistics package handy or if performance is an issue you can always hard-code a value here for z. (Use 1.96 for a confidence level of 0.95.)"
Re: How Not To Sort By Average Rating
#8Every time I see that page, I see the equation, I read statistical terms and I get overwhelmed. I use PHP so I have no pnormaldist. Would love to use it for some random page I run.
Aren't there libraries for PHP like for other languages?
Re: How Not To Sort By Average Rating
#9Every time I see that page, I see the equation, I read statistical terms and I get overwhelmed. I use PHP so I have no pnormaldist. Would love to use it for some random page I run.
Here's my version that we use on MyBankTracker.com. We hardcode the z variable using a power of 0.05.
Re: How Not To Sort By Average Rating
#10I love it and I hate it.
Why I love it: It's precise. It's elegant. It's rigorous. It's based upon solid, proven science & theory. It's a perfect application for a computer. And most of all, it does what's intended: it works.
Why I hate it: What human can understand it?
I used to implement the first manufacturing and distribution systems that used thinking like this. They figured, "We finally have the horsepower to apply complex logic to everyday problems." Things like safety stock, economic order quantities, reorder points, make/buy decisions, etc.
But the designers of these systems overlooked one critical issue: these systems included humans. And as soon as humans saw that decision making formulas were too complex to understand, they relieved themselves of responsibility for those decisions. "Why didn't we place an order?" "Because the computer decided not to and I have no idea why."
I suppose the optimal solution is somewhere in between: a formula sophisticated enough to solve 95% of the problem but simple enough for any human's reptile brain to "get it". This isn't it.