# Did

less info
reputation
68
bio website location age member for 2 years, 11 months seen Dec 1 at 20:10 profile views 253

As somebody used to say:

Does research. Smokes. Battles administration. Smokes. Wishes he could stop battling administration so that he could have more time to do research. Smokes some more.

The same. Except I do not smoke.

This paragraph is for my personal use but freely available:

Welcome to Math.SE! Please, consider updating your question to include what you have tried and where you are getting stuck. That way, people on this site will know exactly what help you need.

# 55 Comments

 Nov13 comment I want to show $E(X)=\sum_{n=1}^{\infty}P(X\ge n)$ @whuber No, the sum must start at $n=1$ (try the case when $P[X=42]=1$). Jul29 comment An adaptation of the Kullback-Leibler distance? Jul15 comment Is there a way to find how parameters of a statistical/stochastic model mapping reality changed throughout time? There are. A lot. Thus, you need to be tremendously more specific before this question becomes suitable to the site. Dec11 comment What are the chances my wife has lupus? On the strictly mathematical side of the question, even a cursory reading reveals that some data and (in-)dependence hypotheses are missing, that are needed before one can give a mathematical answer. Sep15 comment Proving a non-stopping time Not sure I understand your comment but if one looks for an example where no W_y is a stopping time, then the simpler the better, hence, you could try (X_n) i.i.d. uniform on a finite set. Sep15 comment Proving a non-stopping time Of course this proof is valid in the generic case. But it may happen that for some $x$, $X_2=y$ never happens, then $[W_y=1]=\varnothing$ hence, with respect to $\Pr_x$, the event $[W_y=1]$ does belong to $\mathcal F_1$. Jul22 comment Optimal estimation of a mean from non-independent data .../... I very much hope readers who would be interested in that question and not know the answer themselves do NOT turn to the accepted answer for explanations. Jul22 comment Optimal estimation of a mean from non-independent data .../... Likewise, still in this gaussian context, despite the second paragraph there, the MLE is never biased. And finally, no, the solution does not require the use of Lagrange multipliers (as another answer demonstrates). Note also that the accepted post did not introduce any kind of Lagrange multipliers before these appeared in another post (but, willing to teach, I am glad they did appear later on). Finally, I hope that your own computations indeed led you to the estimator stated in another post despite some contrary comments of the author of the accepted answer, and .../... Jul22 comment Optimal estimation of a mean from non-independent data Sorry but the level of knowledge is at best secondary here: some posts answer the question, others do not, and you acknowledge the answer you accepted does not (and nothing prevented you to ask for explanations, but you never did). For your interest, note that several assertions of the accepted post are dubious or worse. To begin with, despite the two first paragraphs there, the fact that the UMVE is linear (affine, really) is not an assumption but a theoretical result (specific to the area of gaussian families) hence to consider only such estimators is not a restriction. .../... Jul19 comment Optimal estimation of a mean from non-independent data @Macro Thanks for your comment. To me, both options (here and on math.SE) have their merits. This means in particular that the question is fully "at home" on math.SE. Jul19 comment Optimal estimation of a mean from non-independent data Nikita: Where in the accepted post do you see an answer to your question, that is, if I read you correctly, a function $f$ defining the UMVE of $\beta$? If there is one, I might have entirely misunderstood the question, in which case please explain what your question is, really... Jul18 comment Confusion regarding random walk model That, plus a trivial Jacobian. Jul18 comment Optimal estimation of a mean from non-independent data @cardinal: This comment of yours describes the (structural) reason why the (somewhat tedious, but more elementary) computations in my post indeed yield these coefficients. Well done. Jul18 comment Optimal estimation of a mean from non-independent data @Macro: Why?  Jul18 comment Optimal estimation of a mean from non-independent data May7 comment Pairwise vs. total independence of discrete uniform random deviates Then why refer to Hamming distance? May1 comment Pairwise vs. total independence of discrete uniform random deviates See here for a full solution. May1 comment Pairwise vs. total independence of discrete uniform random deviates I know an answer to the generalization question but I have no idea how your indication may lead to it. Apr26 comment What is the most surprising characterization of the Gaussian (normal) distribution? @Xi'an Here is a preprint by Victor Kleptsyn and Aline Kurtzmann with a counterexample to the Cantelli conjecture. The construction uses a new tool, which the authors call the Brownian mass transport, and yields a discontinuous function $f$. The authors state that they believe that Cantelli conjecture holds if one asks that $f$ is continuous (theirs is a mixture of two continuous functions). Jan12 comment What is the most surprising characterization of the Gaussian (normal) distribution? @Xi'an: I fully agree, of course. (Didn't know you were roaming in these quarters of the web... Good news that you are.)