You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

IlyaShpitser comments on Group Rationality Diary, March 22 to April 4 - Less Wrong Discussion

6 Post author: gjm 23 March 2015 12:17PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (16)

You are viewing a single comment's thread. Show more comments above.

Comment author: Gunnar_Zarncke 29 March 2015 08:21:05PM 1 point [-]

Using a (stochastic) time tagger has not worked for me. Apparently I'm not compulsively checking my phone enough. I miss lots of pings.

At first I thought I could just build enough habit. Didn't work.

Then I thought just enough data would solve it. Until I noticed that there are times where I don't reliably track as realiably as in other times (e.g. at home when the phone is out of earshot).

Then I thought I could salvage pings by smartly analysing them - evaluating tags relativ to the hour they come it thus compensating high-miss times. Until I realized that they correlate with the type of tag.

Then I gave up.

The last use of the ping right now is to remind me of writing this post.

Comment author: IlyaShpitser 16 April 2015 09:54:25PM *  0 points [-]

There is an interesting missing data problem here. Not necessarily unsolvable either. A lot of causal inference stuff is precisely dealing with this kind of data.