Question: Univariate testing before or after feature selection
gravatar for ab123
10 weeks ago by
ab12330 wrote:

Hi there,

Wondering if univariate have to be run before features are selected or can be applied to the selected features? The latter gives me better results.

I understand that we select features to build the best predictive models, but in my case they also seem to bring out the most significant variables.

Am I missing something? Sorry couldn't find the answer googling this so asking you guys.


ttest stats • 119 views
ADD COMMENTlink modified 10 weeks ago by Kevin Blighe28k • written 10 weeks ago by ab12330
gravatar for Kevin Blighe
10 weeks ago by
Kevin Blighe28k
USA / Europe / Brazil
Kevin Blighe28k wrote:

There is no standard way to do it. Obviously your method of feature selection is important, as it is undoubtedly already applying some kind of statistical test to your data. I gave a long answer on this topic, here: A: What is the best way to combine machine learning algorithms for feature selectio

However, my answer should not be regarded as the 'gold standard' by any means.

One could easily make the argument that 'unbiased' feature selection, i.e., performing feature selection on your entire unfiltered data, is best, whilst, in other situations, it may prove beneficial to first filter out genes based on some comparison, e.g., between cases and controls.


ADD COMMENTlink written 10 weeks ago by Kevin Blighe28k

Great answer! Thank you Kevin!

ADD REPLYlink written 10 weeks ago by ab12330
Please log in to add an answer.


Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 2.3.0
Traffic: 618 users visited in the last hour