Joe Chipperfield

@ipbes.net on Bluesky “We cannot withdraw from the fact that over 1 million species of plants and animals face extinction.” IPBES remains committed to its mandate to provide the most credible science and evidence about biodiversity to all decision makers and actors. — @davidobura.bsky.social , @ipbes.net Chair

Original post: bsky.app/profile/did:...

📢Please share📢 We have an opening for an exciting fully-funded PhD project on computer vision and machine learning applied to biodiversity monitoring with amazing Serge Belongie @belongielab.org and @aicentre.dk. Application deadline coming up on 15 January!
phd.tech.au.dk/for-applican...

A statistical model is supposed to be an expression of your a priori beliefs of the system. If you have hypotheses then that, by definition, means you have a priori beliefs about the system. The way you test your hypotheses is by building a model that contains a mechanism to test those beliefs.

It so pervasive that I'm thinking I need to write a paper entitled "Why model selection is (almost) always a complete waste of time". Maybe @bobohara.bsky.social would be up on the soapbox with me here.

Over the last two weeks I have been asked many times by people what they should do if the 'best performing' model as selected by AIC/VIF analysis/Forward selection doesn't include the effects that represent their hypothesis. My hot take has been to say model selection is almost always a bad idea

A statistical model is supposed to be an expression of your a priori beliefs of the system. If you have hypotheses then that, by definition, means you have a priori beliefs about the system. The way you test your hypotheses is by building a model that contains a mechanism to test those beliefs.

It so pervasive that I'm thinking I need to write a paper entitled "Why model selection is (almost) always a complete waste of time". Maybe @bobohara.bsky.social would be up on the soapbox with me here.

Over the last two weeks I have been asked many times by people what they should do if the 'best performing' model as selected by AIC/VIF analysis/Forward selection doesn't include the effects that represent their hypothesis. My hot take has been to say model selection is almost always a bad idea

Extremely interesting opinion piece by MacIvor & Irwin on "Mail-order solitary bee cocoons as a gateway for biological invasion": doi.org/10.26786/192...

Just got back from paternity leave and I feel like I've been away for a hundred years