13,757 reputation
42351
bio website
location England
age
visits member for 2 years, 4 months
seen 7 hours ago

21h
comment problems in doing logistic regression with unbalanced sample, give me some references
The problem is the few $Y=1$ rather than the many $Y=0$. See here. If you already have the data, there's no benefit to throwing some of it away.
1d
reviewed Close Mean and Standard deviation
2d
reviewed Close Does THE discordance test for outliers exist?
Mar
23
awarded  Constituent
Mar
23
reviewed Close How does Vowpal Wabbit handle NA's or missing values?
Mar
23
reviewed Reopen Control chart constants
Mar
23
revised Control chart constants
edited tags
Mar
23
comment Getting the optimal age cut off
I should also have mentioned that it's very likely the kind of situation in which it would be extremely inappropriate not to consult a medical statistician before making any final decision.
Mar
23
comment Getting the optimal age cut off
This is the kind of situation where any reasonable meaning that can be given to "optimal" has to take into account the relative costs of false positive & false negative results, as well as the prevalence of the disease.
Mar
22
revised Understanding Chib (1998) Bayesian multiple changepoint model
fixed typo
Mar
22
reviewed Close nonparametric estimation to similar shapes with different mean and variance
Mar
22
reviewed Close How to solve equation by computer package?
Mar
22
comment P-value in a two-tail test with asymmetric null distribution
@Glen_b: Thanks, I look forward to it. I also want to extend mine to show how score tests & generalized likelihood ratio tests give different answers (in general); & the theory of unbiased tests is surely worth mentioning in this context (but I can barely remember it).
Mar
21
wiki
Mar
21
comment how to regress with dummy variables only
@ChauyaRhinoWesley: Sounds sensible, as far as I can guess while knowing nothing about the context. You might well want to consider a curvilinear relationship between the log odds & years of schooling.
Mar
21
comment P-value in a two-tail test with asymmetric null distribution
@AlecosPapadopoulos: That's fine, of course, & you're welcome. (As both Glen_b & I have taken pains to point out, there's not a uniquely correct approach.)
Mar
20
comment Interpretation P value one sample KS test
(3) The considerations here apply to exponentiality testing too.
Mar
20
comment Interpretation P value one sample KS test
(1) When the exponential rate parameter is estimated from the data, that should be taken into account when considering the distribution of the KS test statistic - see here. (2) You seem to have the right idea about p-values & significance levels.
Mar
20
comment Interpretation P value one sample KS test
(-1) The log of an exponentially distributed random variable is not normally distributed.
Mar
19
revised Can you compare different clustering methods on a dataset with no ground truth by cross-validation?
fixed typos