98,074 reputation
8177346
bio website quantdec.com
location Northeastern US
age 14
visits member for 4 years, 5 months
seen 14 hours ago

Consultant (environmental and spatial stats a specialty), expert witness, and teacher. I can be reached through (outdated but still valid) links posted on my web site.

Twitter: @WilliamAHuber // ASA-P website: http://amstatphilly.org/


Why waste time learning, when ignorance is instantaneous?

--T(iger) Hobbes.

For any complex problem there is a simple solution. And it's always wrong.

--[Mis?]attributed to H.L. Mencken by Dava Sobel, Longitude.


1d
reviewed Close comparison behavior of time series
1d
reviewed No Action Needed paired t-test for pairs each having more than one sample
1d
comment trouble plotting ARIMA
I'm voting to close this question as off-topic because it is about an insufficiently documented coding error. (Code problems can be posted on Stack Overflow, but please be sure to follow the guidelines for asking questions there.)
1d
revised Sum of iid random variables
edited body
1d
comment When to use simulations?
@Tim The only thing there is to disagree with in my comment is that our site has over a thousand answers containing simulations, but that is an objective fact whose truth you can verify yourself. I made no claim, explicit or implicit, that this represents a complete or representative list of anything. As a set of actual examples, however, it is far richer and more detailed than any individual answer could ever hope to accomplish and as such is a valuable resource for anyone who might wish to pursue question (2) further.
1d
comment Is this method of arriving at a statistic valid?
The survey seems fatally flawed to me, due to the way in which the original question was phrased: "For your family, is having more boys than girls preferred?" This treats boys and girls asymmetrically, implicitly suggesting boys ought to be preferred over girls. At a minimum half of the surveys should randomly have reversed the question to ask "For your family, is having more girls than boys preferred?" (The question phrasing has other problems, too.) Because the subsequent "list experiment" is described so vaguely, any comments about it would be purely speculative.
1d
awarded  Nice Answer
1d
comment Sum of iid random variables
@Aksakal Please consider posting that as an answer.
1d
comment Sum of iid random variables
@Aksakal Right, you got it. (Although invoking the Radon-Nikodym derivative isn't quite right, since we're talking about random variables rather than distributions. But I understand.) That's exactly the point: you must actually do some calculations. You cannot say that just because a variable is "contained in" a formula means it creates a dependence.
1d
comment Sum of iid random variables
@Aksakal "Contains in it" by itself does not imply correlation. For instance, the random variable $X_2 (\sin^2(X_1) + \cos^2(X_1))$ is explicitly a function of $X_1$, but it is independent of $X_1$.
1d
reviewed Approve machine learning with linear regression algorithm
1d
comment How can I sample multivariate binary variables such that sum of them follows a gamma distribution?
It is impossible for any function of a finite number $0,1$ variables (which would be discrete) to follow a Gamma distribution (which is continuous). This makes your question impossible to understand.
1d
comment Sum of iid random variables
Suppose the $X_i$ were constants (which can be considered a special case of a random variable). Do you think $X_1, X_1+X_2$, and $X_1+X_2+X_3$ must have the same three values? (That is part of what "iid" implies.)
1d
comment Plotting a polynomial regression with its confidence interval of 95% in R
Could you elaborate on why you think the distance must be narrower on the right side (larger independent values) than on the left? And what "three equations" did you substitute the x values into?
1d
comment A Conditional Probability Question
Yes, please edit it to clear up those issues. The "$p$" notation is superfluous and potentially confusing. When $w$ is a random variable, "$w\sim N(0,\Sigma)$" means that $w$ has a $N(0,\Sigma)$ distribution.
1d
comment centering two variables X and Z makes cov (X,XZ) = 0
Yes: as you can see, that is the only assumption needed to show the covariance is zero. Normality was not used. (But I believe it is rare to make such a bivariate symmetry assumption: as soon as the variables are assumed to be non-normal, symmetry of the joint distribution typically becomes implausible.)
1d
answered centering two variables X and Z makes cov (X,XZ) = 0
1d
comment centering two variables X and Z makes cov (X,XZ) = 0
I may have misread part of it. I'll post an answer.
1d
comment What are marginals?
It's a nice answer, but it strikes me that it will appear perfectly circular to anyone who does not already know the definition of "marginal distribution"; and that might be what is at issue here.
1d
comment What are marginals?
The "marginal [distributions]" are what you get when you focus on a single variable and simply ignore the rest.