I frequently get random ideas for LJ polls. However, many of these ideas turn out to be somewhat impractical to investigate by means of an LJ poll because the main thing I'm interested in is whether there's a correlation or interaction between two variables. For example, "Do people from country X keep their houses warmer than people from country Y?" or, "Do people who own dogs eat more vegetables?" or whatever.
It would be so nice to be able to collect results on two or more variables and then have LJ spit out a scatter graph of y against x, perhaps even colour-coded for a third variable. Oooh, you could bring in principal component analyses for lots of variables, how cool would that be?
OK, 3am brain. You are SO going to bed now. Any brain that manages to get excited about multivariate stats at this time of night needs keeping out of trouble for its own good...
It would be so nice to be able to collect results on two or more variables and then have LJ spit out a scatter graph of y against x, perhaps even colour-coded for a third variable. Oooh, you could bring in principal component analyses for lots of variables, how cool would that be?
OK, 3am brain. You are SO going to bed now. Any brain that manages to get excited about multivariate stats at this time of night needs keeping out of trouble for its own good...