89,662 reputation
8150312
bio website quantdec.com
location Northeastern US
age 14
visits member for 4 years, 2 months
seen 44 mins 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 I can be reached through (outdated but still valid) links posted on my web site.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.


4h
reviewed No Action Needed attenuation percentage and confidence interval
4h
reviewed Reviewed Distribution of large set of fold changes
4h
comment Distribution of large set of fold changes
Your Q-Q plot does a great job of answering your question. It detects a heavy right tail out beyond the 98th percentile or so and shows you how that tail varies from (log)normal. This is more than you would obtain from any formal statistical test, which will provide only a test statistic (a single number) and a p-value.
4h
reviewed Leave Open Linear model / models analysis
4h
comment Linear model / models analysis
I see the mixture, too. It might or might not be real ("significant"), but one approach you can take is detailed at stats.stackexchange.com/questions/60394/…. A closely related approach is called switching regression.
4h
revised What intuitive explanation is there for the central limit theorem?
Various minor clarifications and improvements
5h
comment What exactly are censored data?
Censoring applies to much more than time-dependent observations. For instance, chemical concentrations measurements that are below the limit of detection are censored, too.
5h
comment What exactly are censored data?
Two aspects of this answer confuse me. First, purely missing values do not necessarily reflect truncation. Second, the manner of censoring ("random" vs. "informative") is often as important as the fact of censoring, indicating that there is more to censoring than the mere recording of interval-valued data.
7h
comment What exactly are censored data?
The more relevant Wikipedia article is at en.wikipedia.org/wiki/Censoring_%28statistics%29. Although not comprehensive, it at least describes Type I and Type II censoring and acknowledges interval censoring along with left and right censoring.
8h
revised Data point that minimizes all four parameters
edited tags
8h
comment Data point that minimizes all four parameters
It is rare that one can simultaneously achieve four objectives optimally. You have to stipulate how to trade off improvements in some objectives against weakening of others. This is not a question of optimization, because it comes beforehand: it is a matter of your values and as such cannot be answered here. We can provide some guidance for how to discover and quantify your values: see inter alia stats.stackexchange.com/questions/9137 and stats.stackexchange.com/questions/9358.
8h
comment Example of two *correlated* normal variables whose sum is not normal
From the picture alone it is obvious that the density of the sum at zero is zero (because the line $x+y=0$ intersects the plot in a single point, which has measure zero), while the sum itself is just as obviously symmetric about zero, showing that zero is the center of the distribution of the sum. Such a distribution cannot be Normal because Normal distributions have nonzero densities at their centers.
8h
comment Systematic Review (maybe)
What exactly are you trying to "conclude according to these [studies]"? Something seems to be missing from the English.
8h
comment Gaussian mixture vs. Gaussian process
"Better" for what purpose and context? You might as well ask "which is better--digging with a spade or digging with a fork--and why?" Please, then, edit this question to provide this information that is essential for getting objective, useful answers.
9h
comment lotto simulation with R
Because knowledge of how games are played is not considered a part of statistics or data analysis, please edit this question to include a clear, pithy description of the process that you want to simulate.
9h
comment $L_p$ norms for vector valued function in econometrics
And what do you mean by "$f_y$" and "$S_Y$"?
9h
revised $L_p$ norms for vector valued function in econometrics
edited tags
9h
comment Compare 2D maps
This question really isn't objectively answerable without some information about what the images represent and why you are comparing them. Would you care to edit it to include such information?
9h
comment How to analyze relationship between data pairs
You may be overinterpreting the overlapping areas: after all, overlapping 95% CIs can occur even among highly significant differences. But why are you recommending these plots? How does this set of plots answer the stated question?
9h
comment How to test a claim about a confidence interval (real case)
As a matter of terminology, this claim is a statement about a proportion of a population. It can be thought of as a confidence limit for the 95th percentile of a population (usually known as a tolerance limit). It is a matter of conjecture whether the company intends it as a lower tolerance limit--in which case it is not confident that 95% of all cases truly are processed in 40 minutes or less, but this is possible--or an upper tolerance limit, in which case the company is quite confident of its claim. This has a strong bearing on how large a sample is needed to test the claim.