Hi, This question is for those who are familiar with the logistic regressions used in [0] https://arxiv.org/pdf/1711.01519.pdf
In this article, a multinomial logistic regression to find the optimal chunk size and prefetching distance. These variables are ordinal since they are numbers. However from what i've read, the multinomial regression is most useful to find nominal variables. [1] https://stats.idre.ucla.edu/r/dae/multinomial-logistic-regression/ From what I understand, chunk size and prefetching distance are ordinal variables. In that case, maybe a ordinal logistic regression would be a better choice since such a regression is made to work with ordinal variables instead of nominal. What do you think? Gabriel Laberge. _______________________________________________ hpx-users mailing list [email protected] https://mail.cct.lsu.edu/mailman/listinfo/hpx-users
