Ghost CATS

The ghost of LSE’s Centre for the Analysis of Time Series in the Department of Statistics. A small centre that did big things in time series analysis.

[Prof Paul Williams @DrPaulDWilliams]

Reading's only known tornado fatality was a carpenter who was blown off the roof while helping to build the train station in 1840.

I photographed this memorial to him while heading to London this week.

Worth looking out for next time you are on Platform 7 at Reading station.

[Dr. Hansi Singh @DrHansiSingh]

Do global ocean initial conditions matter for large Earth System Model ensembles? This is a question that we explored in our recent paper in Journal of Climate. The short answer: in the Southern Ocean, they do matter, even over long time scales.
https://t.co/321yXWppIt

[Leonard Smith @lynyrdsmyth]

@CColose That we understand the basics (in an “as-good-as-it-gets science” kind of way) yet there remains vast uncertainty of the future.
And that those overselling detailed predictions to downstream sciences, glossing over shortcomings of today’s models, do not cast doubt on the basics.

[LSE Data Science Institute @LSEDataScience]

Since algorithms learn from human data, are they bound to recreate biases that are present in the real world? 🤔

Join the next #CIVICADataScience seminar that will discuss how the internet is fundamentally changing our lives.

🔗 https://t.co/RjpFFbXWzW | #LSE #DataScience

[LSE Data Science Institute @LSEDataScience]

Should AI have a role in the production of research papers? 📑

Rebecca Lawrence and Sabina Alam consider the significant consequences for research integrity.

🔗 https://t.co/hy7fB0Chox | @tandfonline @rnl_s @LSEImpactBlog @LSE_RI #LSE #DataScience

[MCNP at Northumbria @McnpNorthumbria]

We are glad to announce the @LondMathSoc-funded workshop on the #Mathematics of Delayed Phenomena that will take place @NorthumbriaUni on 22-23 March 2023. Limited funding available to support PhD and postdocs. Contact Stefan Ruschel or @BenHuardMath. https://t.co/fNreCp6MZt.

[Andrew Krause @BlindMath]

I would highly recommend any math(s)-enthusiast friends of any persuasion take a look at this magazine. Despite being UK-based, the level of excellent mathematical humour found in its pages is incredible!

[Kyle Wedgwood @kyz1024]

Delighted to announce the next Mathematics in Life Sciences meeting on "Linking Mathematics, Experiments and Data" at @UniofExeter, 8-9th March 2023. The schedule can be found here: https://t.co/bzhCCCRSwt
Co-funded by @LondMathSoc and @HealthcareHubEX.
Please share!

[Leonard Smith @lynyrdsmyth]

One challenge #Bayesian forecasters must face is how to update their probabilities having inadvertently adopted a zero prior probability on some phenomenon that occurs.

The chain just broke in an #NFL #Divisional #playoff game; zero #probability in my model. Yours?
#Statistics

[Shane Ross @RossDynamicsLab]

Some say, why read fiction?

“Fiction gives us empathy: it puts us inside the minds of other people, gives us the gift of seeing the world through their eyes.

Fiction is a lie that tells us true things, over and over.”

— Neil Gaiman

<Grateful to @H4wkm0th’s book for the quote

[Leonard Smith @lynyrdsmyth]

@mocreevy @cubic_logic @H4wkm0th @LSEDataScience @LSEpublicevents I’d phrase it along the lines that mathematically it is irrelevant whether or not your axioms are true.
Or stronger still: that to discuss whether your axioms are true is to make a category error.

[Leonard Smith @lynyrdsmyth]

@jrderbyshire1 @cubic_logic @mocreevy @H4wkm0th @LSEDataScience @LSEpublicevents Mathematics would still be discoverable.

[Leonard Smith @lynyrdsmyth]

@ClimateAdam * avoid overselling the fidelity of today’s models after being beaten about the head and neck by Machiavellian deniers for several decades.

Overselling how much we know and failing to criticise downstream sciences is arming the deniers of tomorrow.

https://t.co/YAvgnzJTaB

[Leonard Smith @lynyrdsmyth]

@gallois_sophie @ClimateAdam In maths the more you know the harder it is to explain things to someone who doesn’t see how it all fits together; it is hard for you to remember what it was like not seeing that things all fit together.
Physics is easier as it doesn’t fit together as well & one can read Feynman.

[Predictability of Weather and Climate @OxPredict]

We now have a global circulation model developed @OxfordAOPP! Not to replace existing forecast models, but as a computational playground to develop and test new ideas! Looking good already 🥳

[Predictability of Weather and Climate @OxPredict]

Tim Palmer explains why we don't need more climate models but a massive international Earth simulator on an #exascale supercomputer. Regarding the climate emergency, $1.1bn is well invested to inform us precisely about the climate change we are facing.

https://t.co/sjp5pwt0tV

[Leonard Smith @lynyrdsmyth]

Thanks Glen.
I keep trying to remap model-land from this hand drawing to something more “professional” looking, but it always loses too much in transition.

Then again, it is only a model of model-land. I should not make the mistake of thinking it could be perfect.

[Alisa Bokulich ➡️ 🦋🌤️ @AlisaBokulich]

🤩 Mapping time...

[Leonard Smith @lynyrdsmyth]

“Before we get to the maths, what is going on here?” @H4wkm0th on ethical questions in science and simulation.
@LSEDataScience

[LSE Data Science Institute @LSEDataScience]

"...we have both a legal and ethical responsibility to do better." 🖊

Dr Erica Thompson asks urgent questions about how we use data to inform decisions and public policy.

🆕 https://t.co/7ScdVq7oZx | @H4wkm0th @LSEforBusiness #LSE #LSEModelLand