372 reputation
9
bio website stas.kolenikov.name
location Columbia, MO
age 41
visits member for 11 months
seen Aug 27 at 17:22

Applied statistician


Jun
21
comment Joseph Kitchen's Calculus (reference)
Thanks, Dave. I think the best evidence of performance of a given book is what kind of classes a student can take if they (i) had this as a required textbook in a calculus class, but did not put any effort, to (ii) put in an honest effort and learned everything this given book can teach, while being limited to but this book being the only one in their disposal.
May
7
answered Evaluating the reception of (epsilon, delta) definitions
Apr
26
comment Power Function for the uniform distribution
See updated. Note that there are better, superefficient estimators of $\theta$ that beat MLE in this situation.
Apr
26
revised Power Function for the uniform distribution
defined power
Apr
25
answered Manipulating inequalities and probabilities
Apr
25
answered Power Function for the uniform distribution
Apr
25
revised Power Function for the uniform distribution
LaTeX formatting; homework tag
Apr
25
suggested suggested edit on Power Function for the uniform distribution
Apr
25
comment Power Function for the uniform distribution
Welcome to the site, and please learn some LaTeX -- this is impossible to read.
Apr
25
comment If $X \sim N(0,1)$, why is $E(X^2)=1$?
Hint to the hint: integrals like $\int x^2 \exp(-x^2/2) dx$ are addressed via integration by parts or differentiation by an artificial parameter: introduce $a$ into the exponent as $\exp( -a x^2/2)$, evaluate the integral, and take derivatives with respect to $a$. Oh, and statisticians hate the erf() function, it is on a wrong scale as it is does not correspond to the standard normal distribution.
Apr
23
awarded  Revival
Apr
23
answered Joseph Kitchen's Calculus (reference)
Apr
22
comment What should the high school math curriculum consist of?
it throws error 404 -- can you please update the link?
Apr
22
answered How to get a top-notch Math education (high school level) online?
Apr
22
awarded  Student
Apr
22
comment Why doesn't this work? — The V.I. Arnold Primary School Problem (Two women started at sunrise…)
You might need to consider geometric average rather than the arithmetic one here. That's what the speeds do when being averaged. While distances are the same, you have either time = distance / speed, so the speed goes to the denominator; or speed = distance / time, so the time goes to the denominator. By Jensen's inequality, you will be off with your arithmetic mean.
Feb
13
awarded  Commentator
Feb
13
comment How to manipulate logit confidence interval into one of the parameter?
Your CI does not have $\pm$ in it, so what? It is still has the (large sample) 95% coverage, because the underlying one for the logit parameter does. It is asymmetric, and a lot of people find that appealing for a parameter that has a restricted range.
Feb
12
comment Computing standard deviation of discrete normal distribution
@ClementC., this is an algorithmic fix, and the OP would be better off figuring out why it happened that they did not get the total mass equal to 1. There may be weird situations with heavy tailed distributions when any discrete version would have all the moments, yet the continuous version (say Cauchy) won't even have the mean. So one has to be careful with discretized distributions.
Feb
12
revised Computing standard deviation of discrete normal distribution
deleted 4 characters in body