All About that Bayes: Probability, Statistics, and the Quest to Quantify Uncertainty

[@morganweiss2477]

Can't believe I watched this just because I was randomly interested, AND I thoroughly enjoyed learning and watching the entire lecture. If only I could learn more things from her! A fantastic presentation with just the right amount of humor. Being an expert does not always mean being a good teacher. She clearly is both!

[@ShellyDeForte]

"Most people view statisticians as a hybrid between an accountant and a wizard, which is ridiculous, we have nothing in common with accountants." OMG, this woman.

[@petemurphy7164]

I want a shirt that says this......

[@tarnopol]

Right out of the gate, she's hilarious, witty, and immediately engaging.

[@janaldencornish]

@@tarnopolHer engaging, well versed style certainly helps with an almost 1 hour long presentation

[@strongpresence]

This is absurdly good...

[@cej3940]

@@janaldencornish barely noticed it was 1 hour long haha, she's bloody great

[@qwosters]

I am in awe. This is my new favorite person ever.

[@tarnopol]

Me, too!

[@gergerger53]

Not many people could make this topic both funny and yet informative. I am so happy I found this video.

[@miglriccardi]

I came here expecting to learn about Bayes Theorem. I did not expect I'd fall in love.

[@maiconlourenco4849]

What a confident, smart and bright woman. The most amazing and enlightening lecture or class about bayesian and frequentist statistics ever.

[@stephenpuryear]

I have been re-watching this for years now. I still get new insights from this tremendous hour. Over time I have come to believe that a sense of humor is perhaps the single most important tool in the Lennox toolbox.

[@sach214]

There is lots of noise out there about Bayesian and Frequentist methods. This talk clearly lays out the different approaches. And she is hilarious to boot!

[@mrdennis1038]

This was an amazing talk. Thanks so much for making this available. Bring her back to discuss more topics.

[@duyng1022]

She is definitely one of the best statistics speaker.

[@juliocardenas4485]

This is the best stats talk I’ve ever seen !! I’m a fan

[@charlesaydin2966]

Phenomenal talk! This should be added to the material for any statistics / probability course!

[@iirolenkkari9564]

Great talk! It is untrivial to find a knowledgeable person that knows how to communicate knowledge. There are plenty of smart people who can't explain things to less equipped people such as myself. There are also plenty of not so smart people who give 'entertaining' talks, but which don't translate any true information. Where smart meets the ability to communicate, therewithin lies gold.

[@Rhoude7695]

What are the odds? 🙂

[@billwindsor4224]

@Kristin Lennox - awesome job on this talk; clear presentation and juxtapositions on Bayesian and Frequentist Statistics, and a great example application on the successful search for the submarine 'Scorpion' in the Atlantic -- *thank you!*

[@jaijeffcom]

Delightful. I came back to watch again and saw I had marked it with a thumbs down. I didn’t mean to do that! What’s not to like? A clear lecture, and with jokes.

[@roelofvuurboom5939]

Starting at 39:40: "De Finetti never actually worked with quantum physics...might of changed his mind." Lennox is talking about the belief that randomness as an objective reality does not exist and so probability based on the concept of randomness does not exist either but only probability as a description of our uncertainty in our beliefs or knowledge about a certain event. Lennox makes the statement that if De Finetti had met up with quantum physicists then he might have changed his mind because a lot of quantum physics has to do with fundamental randomness. The fundamental irony here is that in fact the opposite has occurred: there is now a branch of physics called quantum bayesianism - qbism for short - which has, in fact, followed De Finetti. Qbism believes that was is touted to be objective randomness of processes in quantum physics can be better explained by our (the observers) lack of certainty in what is going on at the quantum level. Although there are issues with this interpretation (as with any interpretation) it does provide intuitive - almost trivial - explanations for some highly non-intuitive - and literally incomprehensible - explanations in "classical" quantum physics including the concept of an instantly collapsing probability wavefront across all of space and the concept of quantum entanglement. This last concept has to do with the idea that if one particle is observed to have a particular property value then an entangled particle will instantly display a related property value no matter how far the particles are apart. Qbism states that all that is happening is our knowledge is being updated. So for example, if I have a pair of socks, one of which is red and one of which is blue and with my eyes closed I put one in one suitcase and the other in another suitcase and close the suitcases. I then send one suitcase to my cousin across the world. If I then open the suitcase I kept and see that the sock is blue then I instantly know that the sock in the other suitcase is red. In Qbism there is no randomness as to the color of the sock before being observed but simply the degree of certainty of our knowledge about the colors of the socks in each suitcase.

[@vleessjuu]

I've heard of qbism before, but does it already have a good explanation for the Bell experiments? Last time I checked, they didn't really seem to be able to provide a good underpinning for that. The Bell experiments show that QM is more subtle than ordinary probability theory would lead you to believe, so I think it's absolutely essential that their theory can deal with them.

[@roelofvuurboom5939]

@@vleessjuu A supposition of the Bell theorem is the objectivity of probabilistic behaviour (i.e. quantum behaviour really is probabilistic). If you reject this supposition (which is what QBism does) then the Bell theorem (and its results) become no longer applicable. This is how QBism deals with the Bell theorem. QBism provides an intuitive and trivial explanation for quantum entanglement, it says in effect that it doesnt exist. The only thing that is instantaneous is the update of my knowledge: if i have a red marble and a blue marble and I have one in my hand but don't know which one, the moment I look at it and discover it is blue then I "instantaneously" know that the other one is red irrespective of how far away it is (even if it is on the other side of the universe). This is precisely how QBism explains the phenomenon of quantum entanglement and is (in my view) one of its most powerful features. It provides a trivial and intuitive explanation for something that is non-intuitive and downright mysterious in the competing interpretation. It is a long held scientific principle that when choosing between two theories/interpretations one should apply Occam's razor principle: choose the theory/interpretation that is simpler, more intuitive and easier to understand if they both have the same explanatory power. P.S. Seeing your monniker I'm guessing you're Dutch :-).

[@TangerineTux]

E. T. Jaynes also discusses this in his posthumous book: “Those who cling to a belief in the existence of ‘physical probabilities’ may react to the above arguments by pointing to quantum theory, in which physical probabilities appear to express the most fundamental laws of physics. Therefore let us explain why this is another case of circular reasoning. […] What is done in quantum theory today is [that] when no cause is apparent one simply postulates that no cause exists - ergo, the laws of physics are indeterministic and can be expressed only in probability form. The central dogma is that the light determines not whether a photoelectron will appear, but only the probability that it will appear. The mathematical formalism of present quantum theory - incomplete in the same way that our present knowledge is incomplete - does not even provide the vocabulary in which one could ask a question about the real cause of an event. […] Quantum physicists have only probability laws because for two generations we have been indoctrinated not to believe in causes - and so we have stopped looking for them. Indeed, any attempt to search for the causes of microphenomena is met with scorn and a charge of professional incompetence and ‘obsolete mechanistic materialism’. Therefore, to explain the indeterminacy in current quantum theory we need not suppose there is any indeterminacy in Nature; the mental attitude of quantum physicists is already sufficient to guarantee it.² […] In current quantum theory, probabilities express our own ignorance due to our failure to search for the real causes of physical phenomena; and, worse, our failure even to think seriously about the problem. This ignorance may be unavoidable in practice, but in our present state of knowledge we do not know whether it is unavoidable in principle; the ‘central dogma’ simply asserts this, and draws the conclusion that belief in causes, and searching for them, is philosophically naïve. If everybody accepted this and abided by it, no further advances in understanding of physical law would ever be made […].”

[@aNytmare]

I love the descriptions of the pictures of Thomas Bayes

[@hermioned1304]

This is the best I've watched on this topic. Thank you!

[@joshuaerkman1444]

I think I'd really like to fall in love with someone through their lectures.

[@jrlauri]

Brilliant lecture!

[@maiconlourenco4849]

6:40: Probability is a measure. Distribution, Parameter and Likelihood.

[@pappaflammyboi5799]

I'm a full-blown Bayesian, but I will look to priors derived from Frequentist techniques if I can't derive nor find one of my own that I deem reasonably believable.

[@Rainstorm121]

Thanks much. Can anyone use an analogy in the context of football match to explain Bayesian statistics for prediction purposes.

[@geethanarayanan2896]

Love it. She emanates inspiration.

[@maiconlourenco4849]

17:00:The word frequentist referes to the long range frequency of experiments.

[@maiconlourenco4849]

8:00: Statisticians define distribution according to a thing called parameters.

[@RajivSambasivan]

Amazing, amazing talk!

[@redbeangreenbean]

I wish I watched this lecture seven years ago

[@maiconlourenco4849]

24:40:They calculate the conditional distribution of a parameter theta given the observed data X.

[@mryan2010]

Really really nice presentation.

[@afterthought138]

Really fantastic.

[@maiconlourenco4849]

4:40: The central difference between frequentist and bayesian is what they mean when they say that they are quantifying uncertainty.

[@haraldurkarlsson1147]

Laplace's 5,000 years for the Sun may be rooted in that time's belief that the Earth was created in 4004 BC.

[@Rhoude7695]

Bayes Theorem of subjective probability has also been employed to locate lost nuclear weapons in the Mediterranean and a lost Russian lost sub in the Pacific Ocean.

[@smeldrick]

this is great

[@mikaelcarneholm6705]

I'm going to take a Bayesian approach and say the probability that her next presentation is fantastic is greater than 0.5 and that all other predictions are ignorant.

[@maiconlourenco4849]

34:00: Bayesian: credible interval. Frequentist: confidence interval.

[@MUHAMMAD-ny1ym]

its credible stunning ..i love statistics being statistician

[@maiconlourenco4849]

43:00 Some people use probably as intermediate step. One example of bayesian search.

[@maiconlourenco4849]

18:20: When I say I want to use. Bayesian is about a state of belief.

[@maiconlourenco4849]

28:10: The confusion involving Bayesian statistics is you are calculating probability distributions on probabilities.

[@maiconlourenco4849]

42:40: We take the interpretation of probability very seriously. Because we have to. Statitisian deliver probability products. Any time you get a statistical interval, or a result of a statistical hypothesis test, that is wether explicity statistical probability or a function of a probability.

[@alexandrechen3081]

Great talk!

[@Justin-zw1hx]

brilliant woman

[@hank-uh1zq]

You can’t assess if your hypothesis is true (accept H0) you can only not reject H0. It’s a fallacy to believe a hypothesis is true merely because it isn’t contradicted by facts.

[@TangerineTux]

Under the Neyman-Pearson framework, you do in fact accept H₀, having calculated the probability (power) of detecting H₁ if it is true.

[@hank-uh1zq]

Why is the top subjective?

[@bralis2]

There is a mistake on likelihood slide. It should be Pr(theta | x).

[@jaydawg4732]

Not a mistake, she was testing you. You passed.

[@jgrtrx]

I was going to comment that.. thanks for clarification.

[@mathieubeliveau2936]

Funny she noticed it and didn't say anything.

[@myfelicidade]

No mistake there, the slide is correct. Likelihood of the data is its probability given theta, i.e., P(x|theta). The thing is that the likelihood is usually considered when doing maximum likelihood estimation, that is, estimating theta as the value that maximizes the likelihood. In this search we are varying theta while the data x is fixed, hence the notation l(theta). P(theta|x) would be the "posterior" probability of theta given x, that bayesians would use maybe to estimate theta as the value maximizing it (MAP=maximum a posteriori estimation)

[@maiconlourenco4849]

24:30: What bayesians do is to use bayesian theorem to perform inference about distribution of parameters.

[@theriversexitsense]

subjective =/= judgement. it means that uncertainty is a product of the subject: ignorance. As opposed to objective uncertainty of frequentism.

[@theriversexitsense]

But yea judgement is needed in priors.

[@maiconlourenco4849]

27:17: The only way of doing inference on small data.

[@maiconlourenco4849]

7:50: The way you allocate those fraction of probability, among individual events or a set of events, is call probably distribution. Distribution defines the measure of events.

[@abdulelahaljeffery6234]

am I the only one who didn't quite get the difference between the blue die, and golden top? @17:15

[@davidbalakirev5963]

For the golden top it was more about to purchase it not so much about the spin I think.

[@redberries8039]

I don't see how throwing a dice and spinning a top are different?

[@redberries8039]

I ca see it's an ornate top and we can't easily know everything about its structure [as we can with the die] ...but the acts of throwing and spinning are equally difficult to quantify ...so they're effectively the same? ....but is that supposed to be the difference the ornate-ness of the top?

[@redberries8039]

...hmm i suppose the throwing and spinning will cancel out over time ...ummmm yup I guess so.

[@nicoloparacini633]

She is referring to the probability of her purchasing the spinning top not to the probability related to the outcome of spinning it!

[@donfox1036]

Green Eggs and Ham, try spinning a die on its corner.

[@Friemelkubus]

This is epic.

[@petersmall1574]

(at 51:08) " . . . I was raised Frequentist . . ."

[@imzhaodong]

purely awsome

[@navneeth9]

[@ericchang9568]

I thought I was playing at 1.25 speed in the beginning :)

[@mipsuperk]

If you're not fighting, are you really doing statistics?

[@maiconlourenco4849]

33:40: Uncertainty of 5 %.

[@donfox1036]

Is she really confused about the words die and dice, or is she just trying to reflect most people’s problem deciding which is similar and which is plural?

[@kyrgyzsanjar]

I have a crush in this lady :)

[@donfox1036]

Sanjarbek Hudaiberdiev, does that mean you intend to crush one of her internal organs?

[@NitinSingh-xr7ft]

In?

[@sujukrish]

great!

[@HarukiYamamoto]

😂 I like her. Good talk.

[@hayednarmashiri2685]

My thing.

[@egbertjanvierkant4708]

There is no fight between frequentists and Bayesians; there is only Bayesians and the ignorant

[@williambailey4904]

Baysean can theoretically model any problem however it may be too cumbersome so frequentism will yield practical results as a shortcut to a reasonable answer.

[@RichardFeinman-yf7lx]

Accepting a particular confidence interval is subjective decision. No? Doing a statistical calculation is a human behavior which has a personal belief. No?

[@sam_cha]

The introducer sounded like Owen Wilson the whole time.

[@ЛюдмилаКшнясева-я5ш]

то, что можно прочитать за 5(10) минут - пересказывать целый час... PR?

[@ЛюдмилаКшнясева-я5ш]

журналистика

[@samferrer]

I don't like her, but she is freaking awesome ... By the way, smoking can cause cancer .. but cancer (a terminal one, for instance) could make you start smoking ...

[@zdog1566]

Quantum mechanics isn't relevant in the macroscopic world. For anything outside the subatomic world, Laplace was correct and all uncertainty is ignorance

[@maiconlourenco4849]

40:26: All bayesians do subjective probability.

[@ProfFeinman]

53:40 tells the story of why medical literature is total mess. If you don’t introduce science, the statistics will lead you astray

[@kodowdus]

I'm still seeing far too much of the opposite problem in peer-reviewed medical literature (not to mention FDA review panels) - particularly studies being deemed "positive" or "negative" on the basis of P values.

[@PeerArt]

_________________

[@jordymaas565]

so where the fk is mh370...

[@LokendraSingh-bo2nv]

John kriek ww2

[@raminekhteiarisalmas4766]

She's under a lot of stress.

[@pcgenie-la]

I think that's her personality. For her connecting or working with people is stressful. Not a people person.

[@stephengibert4722]

More of this silly Bayesian vs frequentist garbage.