diff --git a/ea/ForecastingNewsletter/May2020.md b/ea/ForecastingNewsletter/May2020.md index 5f2cc16..a703e31 100644 --- a/ea/ForecastingNewsletter/May2020.md +++ b/ea/ForecastingNewsletter/May2020.md @@ -37,7 +37,7 @@ Some of the predictions I found most interesting follow. The market probabilitie - [Will Kim Jong-Un be Supreme Leader of North Korea on Dec. 31?](https://www.predictit.org/markets/detail/6674/Will-Kim-Jong-Un-be-Supreme-Leader-of-North-Korea-on-Dec-31) - [Will a federal charge against Barack Obama be confirmed before November 3?](https://www.predictit.org/markets/detail/6702/Will-a-federal-charge-against-Barack-Obama-be-confirmed-before-November-3) -Some of the interesting yet most likely wrong ones are: +Some of the most questionable markets are: - [Will Trump switch parties by Election Day 2020?](https://www.predictit.org/markets/detail/3731/Will-Trump-switch-parties-by-Election-Day-2020) - [Will Michelle Obama run for president in 2020?](https://www.predictit.org/markets/detail/4632/Will-Michelle-Obama-run-for-president-in-2020) - [Will Hillary Clinton run for president in 2020?](https://www.predictit.org/markets/detail/4614/Will-Hillary-Clinton-run-for-president-in-2020) @@ -59,18 +59,24 @@ The first week of each round is a survey round, which has some aspects of a Keyn There is a part of me which dislikes this setup: here was I, during the first round, forecasting to the best of my ability, when I realize that in some cases, I'm going to improve the aggregate and be punished for this, particularly when I have information which I expect other market participants to not have. -At first I thought that, cunningly, the results of the first round would be used as priors for the second round, but a programming mistake by the organizers revealed that they use a simple algorithm: claims with p < .001 start with a prior of 80%, p < .01 starts at 40%, and p < .05 starts at 30%. +At first I thought that, cunningly, the results of the first round would be used as priors for the second round, but a [programming mistake](https://www.replicationmarkets.com/index.php/2020/05/12/we-just-gave-all-our-forecasters-130-more-points/) by the organizers revealed that they use a simple algorithm: claims with p < .001 start with a prior of 80%, p < .01 starts at 40%, and p < .05 starts at 30%. ### Coronavirus Information Markets: [coronainformationmarkets.com](https://coronainformationmarkets.com/) For those who want to put their money where their mouth is, this is a prediction market for coronavirus related information. Making forecasts is tricky, so would-be-bettors might be better off pooling their forecasts together with a technical friend. As of the end of this month, the total trading volume of active markets sits at $26k+ (upwards from $8k last month), and some questions have been resolved already. +Further, according to their [FAQ](https://docs.google.com/document/d/1w-mzDZBHqedSCxt_T319e-JzO5jFOMwsGseyCOqFwqQ/edit#), participation from the US is illegal: *"Due to the US position on information markets, US citizens and residents, wherever located, and anyone physically present in the USA may not participate in accordance with our Terms."* Nonetheless, one might take the position that the US legal framework on information markets is so dumb as to be illegitimate. + +## Epidemic Forecasting + +As part of their efforts, the Epidemic Forecasting group had a judgemental forecasting team that worked on a variety of projects; it was made up of forecasters who have done well on various platforms, including a few who were official Superforecasters. They provided analysis and forecasts to countries and regions that needed it, and advised a vaccine company on where to locate trials with as many as 100,000 participants. + +I worked a fair bit on this; hopefully more will be written publicly later on about these processes. Now they’re looking for a project manager to take over: see [here](https://www.lesswrong.com/posts/ecyYjptcE34qAT8Mm/job-ad-lead-an-ambitious-covid-19-forecasting-project) for the pitch and for some more information. + ### Foretold: [foretold.io](https://www.foretold.io/) & EpidemicForecasting (c.o.i) -Epidemic Forecasting gathered a team of forecasters, including some of which had earnt the right to call themselves superforecasters because of their performance on the Good Judgement project. They found initial success providing analysis and forecasts to countries and regions which wouldn't otherwise have the capacity, and advising a vaccine company on where to locate trials with as many as 100,000 participants; now they're looking for a project manager to take over: see [here](https://www.lesswrong.com/posts/ecyYjptcE34qAT8Mm/job-ad-lead-an-ambitious-covid-19-forecasting-project) for the pitch and for some more information. - -For their part, Foretold has added a distribution drawer (written by myself in reasonML, inspired heavily by the open-source code of Evan Ward's [probability.dev](https://probability.dev/)) to their [Highly Speculative Estimates](https://www.highlyspeculativeestimates.com/drawer) utility, and continued their partnership with Epidemic Forecasting. +I personally added a distribution drawer to the [Highly Speculative Estimates](https://www.highlyspeculativeestimates.com/drawer) utility, for use within the Epidemic Forecasting forecasting efforts; the tool can be used to draw distributions and send them off to be used in Foretold. Much of the code for this was taken from Evan Ward’s open-sourced [probability.dev](https://probability.dev/) tool. ### Metaculus: [metaculus.com](https://www.metaculus.com/) @@ -148,8 +154,8 @@ Podcasts, blogposts, papers, tweets and other recent nontraditional media. - [Fashion Trend Forecasting](https://arxiv.org/pdf/2005.03297.pdf) using Instagram and baking preexisting knowledge into NNs. - [The advantages and limitations of forecasting](https://rwer.wordpress.com/2020/05/12/the-advantages-and-limitations-of-forecasting/). A short and sweet blog post, with a couple of forecasting anecdotes and zingers. -## The Rocky Horror Picture Show. -I have found negative examples to be useful as a mirror with which to reflect on my own mistakes; they may also be useful for shaping social norms. +## Negative role models. +I have found negative examples to be useful as a mirror with which to reflect on my own mistakes; they may also be useful for shaping social norms. [Andrew Gelman](https://statmodeling.stat.columbia.edu/) continues to produce blogposts on this topic at an unreviewable rate. Meanwhile: - [Kelsey Piper of Vox harshly criticizes the IHME model](https://www.vox.com/future-perfect/2020/5/2/21241261/coronavirus-modeling-us-deaths-ihme-pandemic). "Some of the factors that make the IHME model unreliable at predicting the virus may have gotten people to pay attention to it;" or "Other researchers found the true deaths were outside of the 95 percent confidence interval given by the model 70 percent of the time." - The [Washington post](https://www.washingtonpost.com/outlook/2020/05/19/lets-check-donald-trumps-chances-getting-reelected/) offers a highly partisan view of Trump's chances of winning the election. The author, having already made a past prediction, and seeing as how other media outlets offer a conflicting perspective, rejects the information he's learnt, and instead can only come up with more reasons which confirm his initial position. Problem could be solved with a prediction market.