linkstream2 microblog

QT:((”
“Let me get the most important question out of the way: is AlphaFold’s advance really significant, or is it more of the same? I would characterize their advance as roughly two CASPs in one (really ~1.8x). Historically progress in CASP has ebbed and flowed, with a ten year period of almost absolute stagnation, finally broken by the advances seen at CASP11 and 12, which were substantial. What we’ve seen this year is roughly twice as much as the recent average rate of advance (measured in mean ΔGDT_TS from CASP10 to CASP12—GDT_TS is a measure of prediction accuracy ranging from 0 to 100, with 100 being perfect.) As I will explain later, there may actually be a good reason for this “two CASPs” effect, in terms of the underlying methodological breakdown. This can be seen not only in the CASP-over-CASP
improvement, but also in terms of the size of the gap between AlphaFold and the second best performer, which is unusually large by CASP standards. Below is a plot that depicts this.”
“))

https://moalquraishi.wordpress.com/2018/12/09/alphafold-casp13-what-just-happened/

QT:((”
Intuitively, IVs are used when an explanatory variable of interest is correlated with the error term, in which case ordinary least squares and ANOVA give biased results.
“))

https://en.wikipedia.org/wiki/Instrumental_variables_estimation

http://www.panoramio.com/

QT:

QT:{{”
“HOUSATONIC VALLEY, Connecticut

On this New England road trip, following Route 7 along the Housatonic River from New Milford to Canaan reveals the green beauty of Western Connecticut. There’s a covered bridge and waterfalls.
Distance: 35 miles.

THE QUIET CORNER, Connecticut

Travel back in history for bucolic tranquility on quiet CT169 from Old Norwich to Woodstock, meandering past colonial homesteads and stone walls, farmers’ fields and quaint town greens.
Distance: 40 miles.”
“}}

https://newengland.com/today/travel/new-england/things-to-do/10-best-summer-road-trips-in-new-england/

Why the Father of Modern #Statistics Didn’t Believe Smoking Caused
Cancer https://priceonomics.com/why-the-father-of-modern-statistics-didnt-believe/ Interesting article on how even geniuses can be wrong. With a great line: “If he were alive today, Ronald Fisher would have one hell of a Twitter account.”

https://en.wikipedia.org/wiki/Austin_Bradford_Hill

QT:{{”
Sir Austin Bradford Hill FRS[1] (8 July 1897 – 18 April 1991), English epidemiologistand statistician, pioneered the randomized clinical trial and, together with Richard Doll, demonstrated the connection between cigarette smoking and lung cancer. Hill is widely known for pioneering the “Bradford Hill” criteria for determining a causal association.[2][3]
“}}

https://en.wikipedia.org/wiki/British_Doctors_Study

QT:{{”
The British Doctors’ Study was a prospective cohort study which ran from 1951 to 2001, and in … Context[edit]. Although there had been suspicions of a link between smokingand various diseases, the evidence for this link had been largely circumstantial. … The original study was run by Richard Doll and Austin Bradford Hill.
“}}

https://www.ncbi.nlm.nih.gov/pubmed/19689488

QT:{{”
Recently, causal diagrams have been used to illustrate the possibility for collider-stratification bias in models adjusting for birthweight. When two variables share a common effect, stratification on the variable representing that effect induces a statistical relation between otherwise independent factors.
“}}

https://onlinelibrary.wiley.com/doi/full/10.1002/asi.22970
QT:{{”
Appendix shows the top 20 most highly cited authors based on 546,245 citations from PubMed Central. In all three periods, M. Gerstein, a professor in computational biology and bioinformatics at Yale University, is
both the most highly cited and productive author in the first author category.
“}}

Why “Many-Model Thinkers” Make Better Decisions
https://HBR.org/2018/11/why-many-model-thinkers-make-better-decisions Intuitive description of #MachineLearning concepts. Focuses on practical business contexts (eg hiring) & explains how #ensemble models & boosting can make better choices

QT:{{”
“The agent based model is not necessarily better. It’s value comes from focusing attention where the standard model does not.

The second guideline borrows the concept of boosting, …Rather than look for trees that predict with high accuracy in isolation, boosting looks for trees that perform well when the forest of current trees does not.
…
A boosting approach would take data from all past decisions and see where the first model failed. …The idea of boosting is to go searching for models that do best specifically when your other models fail.
…
To give a second example, several firms I have visited have hired computer scientists to apply techniques from artificial intelligence to identify past hiring mistakes. This is boosting in its purest form. Rather than try to use AI to simply beat their current hiring model, they use AI to build a second model that complements their current hiring model. They look for where their current model fails and build new models to complement it.”
“}}