Reputation
10,628
Top tag
Next privilege 15,000 Rep.
Protect questions
Badges
1 14 51
Newest
 Nice Answer
Impact
~279k people reached

Aug
21
answered Example of distribution whose support is strictly positive
Aug
18
revised Fisher's test with large data
edited tags
Aug
18
answered Fisher's test with large data
Aug
17
comment Confidence Intervals
Typically, the CI will get larger if you increase the confidence level. Perhaps you could edit your question to clarify what specifically you don't understand about confidence intervals.
Aug
7
comment Prediction intervals for forecasts using spectral analysis
I think I don't understand, starting with the undetrend function. You fit a linear slope to your data, and then you add the forecast from this simple model to your forecast. So you take both your spectral forecast and a linear trend model and add them together. Do you really want to do this?
Aug
6
comment find if two vectors are correlated
Can you include a scatterplot of your data?
Aug
5
comment Prediction intervals for forecasts using spectral analysis
Can you upload your picture elsewhere and link to it from here? Or even better, provide a minimal reproducible example, ideally in R?
Aug
4
comment Prediction intervals for forecasts using spectral analysis
Could you elaborate on what you mean by "wobbly" PIs?
Aug
4
comment Prediction intervals for forecasts using spectral analysis
I took the liberty of changing your tags from confidence-interval (which refers to an interval for an unobservable quantity) to prediction-interval (which refers to an interval for a not yet observed future realization). It's a small but not completely irrelevant difference.
Aug
4
revised Prediction intervals for forecasts using spectral analysis
edited tags
Aug
3
comment Outliers detection for clustering methods
Have you looked at clustering using DBSCAN? It explicitly identifies outliers during clustering.
Jul
31
revised How does the R function arima() calculate its residuals?
edited title
Jul
30
awarded  Nice Answer
Jul
30
comment Why would parametric statistics ever be preferred over nonparametric?
... and @StasK expressed it all much better than I did.
Jul
30
comment Why would parametric statistics ever be preferred over nonparametric?
The null hypotheses are different between a parametric test and its nonparametric counterpart. Specifically, the null hypothesis for a parametric test contains a specific parametric assumption on the distribution of the test statistic (which will usually also be calculated in different ways for the two tests) - that's why it's called "parametric", after all! So the two p values have the same name, but are calculated based on different test statistics, which have different distributions under different null hypotheses.
Jul
30
answered Why would parametric statistics ever be preferred over nonparametric?
Jul
29
answered Forecasting methods for monthly sales
Jul
28
comment Should parsimony really still be the gold standard?
+1. I suggest reading The Elements of Statistical Learning (freely available on the web), which discusses this problem in depth.
Jul
28
answered Nonlinear forecasting
Jul
27
comment Why don't log-likelihoods lead to log(0)?
@marcman: of course pixels can have the value zero. But the probability model you use (and from which you calculate the likelihood) should not assign a zero probability for a pixel to have the value zero.