Thomas Lumley

Results 15 comments of Thomas Lumley

I think it's a temporary table -- and the same thing happens when the additional table only exists as the inner part of a SELECT. Stripped down, that second case...

?Yes, it helped. Also, for reasons I don't understand at all, the whole thing got faster even without that. -thomas Thomas Lumley Professor of Biostatistics University of Auckland ________________________________ From:...

I came here to report this

It's not clear how to calculate a standard error for the random effects. It's not like ordinary maximum-likelihood mixed models where you can use the Fisher information. In theory there's...

I'm interested in this. Maybe it would be best to implement simple versions of a few ideas so they can be tested with the target audience, who are probably not...

A cartogram-like approach from the Grauniad: http://www.theguardian.com/world/datablog/interactive/2013/sep/06/australian-election-results-map

![image](https://cloud.githubusercontent.com/assets/8380349/14703860/2c9e4a68-0806-11e6-92a6-3e93314d7bab.png) Some sort of outline is probably needed, but it will have to be done by hand to account for the distortions.

I've submitted a pull request with the hexmap data and an example.

Sounds like a good idea to me.

The triangular sub-binning makes a table of categories within each hex and allocates the six sub-triangles to categories using a proportional-representation voting algorithm. The rounding error resulting from allocating whole...