Predicting Health, and Earthquakes -Susan Murphy & Brendan Meade
The most surprising bit of information was this idea of hypothesis-free science. From very early on everyone learns the integral part a hypothesis plays within research and really any science experiment. You really weren’t even allowed to start a lab without first laying out a hypothesis so this was very interesting to see it backwards. It’s interesting that because we now have so much data and access to powerful computing that we can run almost black box algorithms to find interesting trends within datasets. We don’t need to start with an idea of what could happen but instead we can try and let the data tell us what’s going on. This also helps get rid of possible biases to confirm or deny the hypothesis before the study even starts.
https://www.labxchange.org/library/pathway/lx-pathway:825945a0-367c-45dc-82b7-3d160c6e6f7a/items/lx-pb:825945a0-367c-45dc-82b7-3d160c6e6f7a:lx_simulation:5ad35586?source=%2Flibrary%2Fclusters%2Flx-cluster%3AModernPrediction
Philosophy & Prediction -Ned Hall
One question I would’ve asked is about Bayesian probability and this a-priori assumption we automatically bring into and update throughout any probabilistic event. I would just ask if these assumptions assume that humans are rational and therefore update e probabilities in a rational way?? I find this interesting because a lot of behavioral Econ like expected utility assumes humans understand probabilities and will act rational. However, as Daniel Kahneman points out in thinking fast and slow, humans actually don’t always act rational and often times chose opposing results because of previous states or biases.
https://www.labxchange.org/library/pathway/lx-pathway:53ffe9d1-bc3b-4730-abb3-d95f5ab5f954/items/lx-pb:53ffe9d1-bc3b-4730-abb3-d95f5ab5f954:lx_simulation:8bf7271d?source=%2Flibrary%2Fclusters%2Flx-cluster%3AModernPrediction