Comments on: StackOverflow Data Mining: Cleansing the Data http://www.brentozar.com/archive/2009/06/stackoverflow-data-mining-cleansing-the-data/ SQL Server MCM and MVP, performance tuning, consulting, training, and community building. Sun, 05 Sep 2010 19:47:40 +0000 hourly 1 http://wordpress.org/?v=3.0.1 By: Arjan http://www.brentozar.com/archive/2009/06/stackoverflow-data-mining-cleansing-the-data/#comment-16958 Arjan Sat, 23 Jan 2010 10:42:45 +0000 http://www.brentozar.com/?p=4119#comment-16958 Meanwhile, Brent got his answer at http://meta.stackoverflow.com/questions/2307/why-are-so-many-user-ages-89 (Indeed: 1920 is the minimum year that is allowed.) Meanwhile, Brent got his answer at http://meta.stackoverflow.com/questions/2307/why-are-so-many-user-ages-89

(Indeed: 1920 is the minimum year that is allowed.)

]]> By: Coding the Wheel http://www.brentozar.com/archive/2009/06/stackoverflow-data-mining-cleansing-the-data/#comment-9398 Coding the Wheel Thu, 09 Jul 2009 18:42:00 +0000 http://www.brentozar.com/?p=4119#comment-9398 Haha, I see I am on your list. I remember I had originally given it my real age, in order to get the "filled out your profile" badge. Then I decided, eh, how is that anybody's business. So I tried to change my age to the accepted "I don't want to give my age" default of 99 years. I think, but can't say for sure, that the StackOverflow UI prevented me from doing this. This is probably why there are so many 89-year-olds wandering the StackOverflow database... Haha, I see I am on your list.

I remember I had originally given it my real age, in order to get the “filled out your profile” badge. Then I decided, eh, how is that anybody’s business. So I tried to change my age to the accepted “I don’t want to give my age” default of 99 years. I think, but can’t say for sure, that the StackOverflow UI prevented me from doing this. This is probably why there are so many 89-year-olds wandering the StackOverflow database…

]]> By: Pat http://www.brentozar.com/archive/2009/06/stackoverflow-data-mining-cleansing-the-data/#comment-9313 Pat Sun, 05 Jul 2009 07:51:53 +0000 http://www.brentozar.com/?p=4119#comment-9313 because age is a stupid and intrusive question to ask. If I am old does that make me more or less right? If I am young does that make me more or less hip and happening? Age is just as stupid as asking hair-color so that all Brits can decided red-hairs should be ridiculed and all Americans can mock blondes. because age is a stupid and intrusive question to ask. If I am old does that make me more or less right? If I am young does that make me more or less hip and happening?

Age is just as stupid as asking hair-color so that all Brits can decided red-hairs should be ridiculed and all Americans can mock blondes.

]]> By: Rhys http://www.brentozar.com/archive/2009/06/stackoverflow-data-mining-cleansing-the-data/#comment-9117 Rhys Mon, 08 Jun 2009 08:26:39 +0000 http://www.brentozar.com/?p=4119#comment-9117 "They come out with filthy, misshapen rocks that might be something valuable - but might be worthless junk." Nice metaphor. I'm stealing that one for future use! “They come out with filthy, misshapen rocks that might be something valuable – but might be worthless junk.”

Nice metaphor. I’m stealing that one for future use!

]]> By: Brent Ozar http://www.brentozar.com/archive/2009/06/stackoverflow-data-mining-cleansing-the-data/#comment-9109 Brent Ozar Sun, 07 Jun 2009 11:57:19 +0000 http://www.brentozar.com/?p=4119#comment-9109 The age control is a date field where you put in your date of birth. Maybe all of those users picked a date of an event in 1920? I've got access to the database, but I steadfastly refuse to look, hahaha. That feels like it's cheating. It's like reading show recaps on the internet before you see the show on Tivo - it just spoils all the fun. That pretty much sums up my approach to this data - it's like playing a detective game. The age control is a date field where you put in your date of birth. Maybe all of those users picked a date of an event in 1920? I’ve got access to the database, but I steadfastly refuse to look, hahaha. That feels like it’s cheating. It’s like reading show recaps on the internet before you see the show on Tivo – it just spoils all the fun. That pretty much sums up my approach to this data – it’s like playing a detective game.

]]> By: John MacIntyre http://www.brentozar.com/archive/2009/06/stackoverflow-data-mining-cleansing-the-data/#comment-9107 John MacIntyre Sun, 07 Jun 2009 03:33:27 +0000 http://www.brentozar.com/?p=4119#comment-9107 Do you have any idea why so many ages are 89? I don't remember off the top of my head, but is the age control a drop down list starting at 1920? Do you have any idea why so many ages are 89?

I don’t remember off the top of my head, but is the age control a drop down list starting at 1920?

]]> By: SDC http://www.brentozar.com/archive/2009/06/stackoverflow-data-mining-cleansing-the-data/#comment-9106 SDC Sat, 06 Jun 2009 20:32:30 +0000 http://www.brentozar.com/?p=4119#comment-9106 Corey Doctorow wrote a bit of Semantic Web skepticism: 'Metacrap'. It would seem to apply here: # 2. The problems * 2.1 People lie * 2.2 People are lazy * 2.3 People are stupid * 2.4 Mission: Impossible -- know thyself * 2.5 Schemas aren't neutral * 2.6 Metrics influence results * 2.7 There's more than one way to describe something http://www.well.com/~doctorow/metacrap.htm But that's not a reason to give up. Just give up on any meaningful age-related statistics. Happy b-day to yr dad! Corey Doctorow wrote a bit of Semantic Web skepticism: ‘Metacrap’. It would seem to apply here:

# 2. The problems

* 2.1 People lie
* 2.2 People are lazy
* 2.3 People are stupid
* 2.4 Mission: Impossible — know thyself
* 2.5 Schemas aren’t neutral
* 2.6 Metrics influence results
* 2.7 There’s more than one way to describe something

http://www.well.com/~doctorow/metacrap.htm

But that’s not a reason to give up. Just give up on any meaningful age-related statistics.

Happy b-day to yr dad!

]]>