Dave's Free Press: Journal

violence, pornography, and rude words for the web generation

 

Recent posts

(subscribe)

Recently commented posts

(subscribe)

Journals what I read

geeky politics rant silly religion meta music perl weird drinking culture london language transport sport olympics hacking media maths web photography etiquette spam amazon film bastards books bryar holidays palm telecoms cars travel yapc bbc clothes rsnapshot phone whisky security home radio lolcats deafness environment curry art work privacy iphone linux unix go business engineering kindle gps economics latin anglo-saxon money bramble cars environment electronics
Mon, 20 Jun 2011

Star ratings revisited

Just over a year ago I started awarding books and things that I reviewed shiny gold stars. I also retrospectively scattered stars on some of my older reviews.

I thought it would be a good idea to see how many of each I'm awarding, and so how well I'm sticking to my rating system. I'm expecting a normal distribution, with the mean somewhat above 3 stars to reflect the fact that I deliberately don't read shite, and that lots of what I read is because other people have raved about it. Well, the results are in ...

17
24
24
19
1
0

I think this is good. It's roughly what I'd expect given my reviewing criteria and the small number of options available. If I had a larger scale to work with - if, say, I was awarding marks out of 20 - I'd expect a smoother drop-off, and at both ends instead of just at the bottom end.

Posted at 12:26 by David Cantrell
keywords: geeky | meta
Permalink | 2 Comments

Ah - but does a scale with few points makes the differences more meaningful than a scale with many points?

Posted by Ruth on Tue, 5 Jul 2011 at 22:03:31


Consider the pathological cases of the difference between scoring 54 and scoring 55 on a scale of 0 to 100, and the difference between scoring 0 and 1 (or bad and good) on a scale with just two possibilities. There's a happy medium somewhere, but I'm buggered if I know what it is.

There's probably actual scientific research about this in some statistical journal (and fluffy hand-wavey crap about it in marketing and social science journals). I can see it being terribly important in designing questionnaires.

Posted by David Cantrell on Wed, 6 Jul 2011 at 01:05:47


Sorry, this post is too old for you to comment on it.

Archive