#generalization

0 posts0 participants0 posts today

Sean MurthyPeople value us for the value (they believe) we (might) add to them. Generalizing of course, but it's all transactional. There's no (longer) valuing people for just who they are.<a href="https://hachyderm.io/tags/society" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#society</a> <a href="https://hachyderm.io/tags/people" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#people</a> <a href="https://hachyderm.io/tags/life" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#life</a> <a href="https://hachyderm.io/tags/generalization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#generalization</a>

Still Mad About CD PricesA post from August 2024 by <a href="https://mastodon.social/@grimalkina" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@grimalkina</a>, boosted by someone on another instance, about why to report demographics in research even when you're not studying those groups. This seems like a great primer for people who have little background in basic <a href="https://infosec.exchange/tags/sampling" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#sampling</a> and <a href="https://infosec.exchange/tags/generalization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#generalization</a> (for some reason I can't link/boost from here, so):<a href="https://mastodon.social/@grimalkina/112966685297897685" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://mastodon.social/@grimalkina/112966685297897685</a>My 2 cents (already at least partially covered by Dr. Hicks): 1. Your study is never just about your study. Good science is <a href="https://infosec.exchange/tags/open" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#open</a> and reusable. e.g., maybe your study on tech-enabled healthcare access isn't specifically about LGBTQ+ or Hispanic people, but what are you doing to help a researcher who comes along in 10 years? That information will change what they find and report.2. Marginalized groups are often minorities, meaning representative probability samples (or --uncomfortable gesture-- convenience samples) for bread-and-butter research frequently have subpopulations too small for reasonable power in correlations, group differences, etc. That's just reality. It's also a big problem for our understanding of <a href="https://infosec.exchange/tags/marginalized" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#marginalized</a> + <a href="https://infosec.exchange/tags/minority" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#minority</a> groups. Oversampling or targeted studies of those groups are important. It's also important to have a large number of less-targeted studies with relevant information that can be synthesized later (see #1): one study with 1.3% trans participants doesn't tell us much about the trans population, but 20 studies, each of which has 1.3% trans participants, could tell us meaningful things.3. Representation is important. My belief is that <a href="https://infosec.exchange/tags/marginalized" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#marginalized</a>+minoritized people need their identities and existence public and constant. In <a href="https://infosec.exchange/tags/science" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#science</a>, both they and other people consuming the research will benefit from being reminded that they are there, almost always, in our <a href="https://infosec.exchange/tags/research" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#research</a>.

JMLR'Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK', by Hongru Yang, Ziyu Jiang, Ruizhe Zhang, Yingbin Liang, Zhangyang Wang.<a href="http://jmlr.org/papers/v25/23-0831.html" rel="nofollow noopener noreferrer" translate="no" target="_blank">http://jmlr.org/papers/v25/23-0831.html</a> <a href="https://sigmoid.social/tags/sparse" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#sparse</a> <a href="https://sigmoid.social/tags/gradient" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#gradient</a> <a href="https://sigmoid.social/tags/generalization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#generalization</a>

Jan Vlug<a href="https://mastodon.social/@schizanon" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@schizanon</a> <a href="https://en.osm.town/@strebski" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@strebski</a> <a href="https://chaos.social/@fossdd" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@fossdd</a> I think <a href="https://mastodon.social/tags/nationalism" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#nationalism</a> and <a href="https://mastodon.social/tags/generalization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#generalization</a> are important factors for war and killing. I try to treat living beings as <a href="https://mastodon.social/tags/individuals" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#individuals</a>.

WIST Quotations has moved!A quotation from Martin, Judith:« Miss Manners doubts that there is anything in the world like an elegantly dressed Bostonian lurching across the room and diving face first into a bowl of guacamole dip while simultaneously disengaging her bodice from her bosom. Therefore, Miss Manners has a wee bit of trouble preparing a general rule for dealing with this eventuality. »Full quote, sourcing, notes: <a href="https://wist.info/martin-judith/62786/" target="_blank" rel="nofollow noopener noreferrer" translate="no">https://wist.info/martin-judith/62786/</a><a href="https://zirk.us/tags/quote" class="mention hashtag" rel="tag">#quote</a> <a href="https://zirk.us/tags/quotes" class="mention hashtag" rel="tag">#quotes</a> <a href="https://zirk.us/tags/quotation" class="mention hashtag" rel="tag">#quotation</a> <a href="https://zirk.us/tags/exception" class="mention hashtag" rel="tag">#exception</a> <a href="https://zirk.us/tags/generalization" class="mention hashtag" rel="tag">#generalization</a> <a href="https://zirk.us/tags/occurrence" class="mention hashtag" rel="tag">#occurrence</a>

WIST Quotations has moved!A quotation from Fry, Stephen:««««« It is a cliché that most clichés are true, but then like most clichés, that cliché is untrue. »»»»»Full quote, sourcing, notes: <a href="https://wist.info/fry-stephen/60965/" target="_blank" rel="nofollow noopener noreferrer" translate="no">https://wist.info/fry-stephen/60965/</a><a href="https://zirk.us/tags/quote" class="mention hashtag" rel="tag">#quote</a> <a href="https://zirk.us/tags/quotes" class="mention hashtag" rel="tag">#quotes</a> <a href="https://zirk.us/tags/quotation" class="mention hashtag" rel="tag">#quotation</a> <a href="https://zirk.us/tags/cliche" class="mention hashtag" rel="tag">#cliche</a> <a href="https://zirk.us/tags/generalization" class="mention hashtag" rel="tag">#generalization</a> <a href="https://zirk.us/tags/truth" class="mention hashtag" rel="tag">#truth</a>

Recent searches

Search options

Administered by:

Server stats:

#generalization