wilmott.com

QuoteOriginally posted by: deimanteRI don't remember needing the CLT in the construction of Brownian motion....Functional CLT - also called Donsker's theorem - is needed to construct BM.Yeah, one construction uses Donker's theorem, but I don't think that you need it for Levy's construction.

QuoteYeah, one construction uses Donker's theorem, but I don't think that you need it for Levy's construction.Yes, I think there are several constructions that do not use Donsker's theorem. I am not familiar with Levy's constructions. There is another one that uses Haar functional basis, I think it also does not need CLT...

QuoteOriginally posted by: farmerSuppose I hire you, and ask you what is a typical monthly spread between two wheat futures months, and two corn futures months. Are you going to come back and say fuck if I know, the numbers are all over the place? I want to know where to implement my spread strategy wheat or corn. But I need to have some idea of the mean spread, or whether there is a mean spread. How are you going to express to me in an objective way whether there even is a useful mean? Are you just going to show me a plot and say look, these numbers are all over the place. I want to know, wheat or corn? Which one?If the numbers on the plot are all over the place, it's likely that CLT won't give you a useful answer.

QuoteOriginally posted by: katastrofaIf the numbers on the plot are all over the place, it's likely that CLT won't give you a useful answer.You have 2 minutes to explain to me why any choice of corn or wheat is no more than 50% likely to be right, or your ass is fired.

I quit myself, don't want to work for a moron who can't see the obvious thing on a plot

QuoteOriginally posted by: katastrofaI quit myself, don't want to work for a moron who can't see the obvious thing on a plot Like a taxi driver refusing to work for someone who doesn't have a car.

I don't think it's a good analogy. If you need maths to tell you what is already visible by naked eye, you're either a moron or you just need me to confirm a decision you've already made.Hmm, come to think of it, that's what usually quants are paid to do! But then giving a 2 minutes time limit is unnecessary cruelty.

QuoteOriginally posted by: farmerQuoteOriginally posted by: katastrofaIf the numbers on the plot are all over the place, it's likely that CLT won't give you a useful answer.You have 2 minutes to explain to me why any choice of corn or wheat is no more than 50% likely to be right, or your ass is fired.If the explanation was that the error/standard deviation of the estimate you get from these data is larger than the difference between the average prices and that's why you cannot tell the difference, would it be sufficient for you? Sorry, if you expected something deeper and my answer insults your intelligence.QuoteOriginally posted by: katastrofaI quit myself, don't want to work for a moron who can't see the obvious thing on a plot I like visual explanations - you can present any complex problem as a bunch of figures and lines. When you describe it, you can see the audience nodding their heads thinking that they follow and grasp the whole idea, while in fact they understood just your colourful picture. Fortunately, they realize it only if they try to go back to the idea and rethink it - after your presentation. Then you can respond by attaching 15 pages of mathematical calculations.

QuoteOriginally posted by: UltravioletIf the explanation was that the error/standard deviation of the estimate you get from these data is larger than the difference between the average prices and that's why you cannot tell the difference, would it be sufficient for you? Sorry, if you expected something deeper and my answer insults your intelligence.I want you to pick one. And given that I am only paying you $33,000 a year, I want you to prove you are using something more trustworthy than your own stupid eyeballs. Preferably a theorem or something, designed by a person much smarter than you.

QuoteOriginally posted by: farmerPreferably a theorem or something, designed by a person much smarter than you.That makes you by definition unable to understand the UV's justification.

QuoteOriginally posted by: katastrofaThat makes you by definition unable to understand the UV's justification.I don't know what an assay is either. But if UV starts telling me she never had a sore that looks like herpes, I am going to tell her get an assay.If you can be a good little recipe quant, you are going to make a lot more than shoveling horse stalls. And I am going to make a lot more than if I had to give my whole $41,500 in trading profits to a smart person. We will be a long time together.

I'm afraid farmer is trying to hire a wrong woman.

QuoteOriginally posted by: UltravioletI'm afraid farmer is trying to hire a wrong woman.$33,000 as a percentage of his trading profits ($41,500) is not bad though.What does this say to you?(He can't do it without you! Go for $35,000/year for one hour a week of your time and see how it goes.) BTW, as your representative, I get $5,000 for this negotiation!

QuoteOriginally posted by: trackstarsee how it goes

UV has signed a non-compete with me and I require a $100,000 payment to cancel the contract. See farmer, it adds up.