Hello There, Guest!  

[OQSPS] Name features and social status

#6
I have been able to reproduce the statistical results and plots from the paper using the code provided. I have not attempted to retrieve the original data myself.

Comments on methods
  • Given that the feature are 3-grams, it would be interesting to see the coefficients on each, to try to pick out the ones most (independently) associated with S. I guess you will probably see "Abd". This would be helpful insofar as there are language-typical letter triplets, which may help pinpoint language-level associations, in addition to the manual testing done with the behindthename data.
  • p 8. Clarify what is meant by performance in that context
  • It would be interesting to show an R2 curve showing the changes in R2 with number of predictors, showing what % of features can be retained with minimal loss in accuracy. This could be done by selecting the best predictor triplet from a bivariate regression, then running N-1 regressions and picking the next one, and so on.
  • There is a slight mismatch between the alphas that are used and the ones that the paper mentions. The ones used are 1,0.325, 0.55, and 0.775. This does not affect the conclusions.
  • Given that you are willing to run 5k CV iterations, why not do a straight LOOCV? This would get results as good or better as 5K CVs with fewer model runs. Also, switching to K folds (With K higher than usual, say 100) would also enable faster iteration, possible allowing for an optimisation of alpha in addition to lambda. Ideally one would use bayesian optimization here, but this feels excessive. Overall, I don't expect the results to change substantially were these methods tried.
  • Regarding the conclusions and the adjusted R2 vs CV R2, I see as an interesting avenue of research to study precisely the issue you raise: Is the traditional Adjusted R2 formula good enough?
Typos:
  • "The list predictors" -> predictors
  • "The featured" -> features
 Reply
 
Messages In This Thread
[OQSPS] Name features and social status - by Emil - 2016-Nov-24, 05:07:03
RE: [OQSPS] Name features and social status - by hvc - 2017-Jan-03, 14:24:57
RE: [OQSPS] Name features and social status - by Emil - 2017-Jan-09, 01:41:00
RE: [OQSPS] Name features and social status - by Emil - 2018-Sep-03, 20:50:33
RE: [OQSPS] Name features and social status - by Dr. g - 2018-Nov-01, 06:07:47
RE: [OQSPS] Name features and social status - by JoseL - 2018-Nov-03, 22:48:31
RE: [OQSPS] Name features and social status - by Emil - 2018-Nov-04, 04:47:08
RE: [OQSPS] Name features and social status - by Dr. g - 2018-Nov-08, 17:52:35
RE: [OQSPS] Name features and social status - by JoseL - 2018-Nov-10, 23:12:34
RE: [OQSPS] Name features and social status - by Emil - 2018-Nov-11, 00:10:27
RE: [OQSPS] Name features and social status - by Dr. g - 2018-Nov-18, 04:24:02
 
Forum Jump:

Users browsing this thread: 1 Guest(s)