Reputation
9,272
Top tag
Next privilege 10,000 Rep.
Access moderator tools
Badges
1 14 48
Newest
 Enlightened
Impact
~235k people reached

16h
comment Is 10 years data enough for forecasting?
If you do causal forecasting, you will need to forecast your causal variables, too. Keep that in mind. In your specific case, I'd recommend building two models, one including prices and two years of history, the other one excluding prices but using ten years of history. Forecast out using both models. Then average the two forecasts within each future time bucket. Averaging forecasts very often improves accuracy.
19h
answered Is 10 years data enough for forecasting?
1d
revised Ensemble time series prediction from two separate models
added 2 characters in body; edited title
1d
answered Ensemble time series prediction from two separate models
1d
comment Zooming in on tail of histogram plot in R
This is about programing in R, not statistics. I suggest you edit your question to include a minimal workable example, then flag it for moderator attention and request migration to StackOverflow.
May
25
comment Where can I find time series data to assess accuracy of forecast?
@forecaster: I don't think so (it would have kind of defeated the entire idea of a forecasting competition to include series from an earlier competition). However, both the M1 and the M3 series are available in the Mcomp package for R that Rob linked to.
May
21
comment Predicting the job switching period of an employee
You may want to google for "churn prediction" and similar, which is the term that mobile phone companies use for customers that cancel their contract, which is similar to your problem.
May
21
revised Is building training data set from unlabeled data considered as a scientific contribution?
added 83 characters in body
May
21
answered Is building training data set from unlabeled data considered as a scientific contribution?
May
19
revised Predictive distributions in Poisson regression
deleted 33 characters in body; edited title
May
18
awarded  Enlightened
May
18
awarded  Nice Answer
May
11
revised Confidence interval of the mean for a beta distribution when alpha and beta are estimated
edited title
May
6
comment Why is this result significant but this other one not significant?
Please carefully read the article I linked to. If you still have questions after that, feel free to open a new question. We are getting sidetracked here.
May
6
revised Why is this result significant but this other one not significant?
added 10 characters in body; edited tags
May
6
comment Why is this result significant but this other one not significant?
I know this is hard to wrap one's head around. See it this way: there is no probability that an underlying relationship exists or not. It either exists or not. What we can assign probabilities to are outcomes of random variables. This article is very good.
May
6
comment Why is this result significant but this other one not significant?
No. That is an extremely common misconception about p-values. It ignores base rates. I very much recommend that you read about criticisms of NHST, starting, e.g., with the Wikipedia articles linked above.
May
6
comment Why is this result significant but this other one not significant?
It just means what I wrote: if the null hypothesis were true, the observed test statistics would be very unlikely. We usually deduce that the null hypothesis is not true, i.e., that there is some correlation in the underlying data generation process. This is related to the mathematical proof by contradiction. Null hypothesis significance testing is not universally accepted, read the "criticism" section in the Wikipedia article.
May
6
answered Why is this result significant but this other one not significant?
May
6
revised Finding the point of maximum probability in a mixture of gaussians
added 434 characters in body