Reputation
8,480
Top tag
Next privilege 10,000 Rep.
Access moderator tools
Badges
21 44
Newest
 time-series
Impact
~449k people reached

Jul
28
awarded  time-series
Jun
26
comment Avoiding a spline dip
What is your basis for saying "it doesn't represent the data"? You don't have any data between 14 and 21, so how do you know it doesn't go down there? If you have theoretical information that it should not, perhaps you should be using your knowledge to define the curve directly? Which raises the issue of why you are using splines in the first place? Is it just to make a pretty picture? You can get an answer to your question, but are you asking the right question?
Jun
18
comment What is the problem with statistical outlier detection approaches if we have distribution of attributes?
+1 Very clear answer and illustration. In this case, a Mahalanobis distance might be helpful. (en.wikipedia.org/wiki/Mahalanobis_distance)
May
31
answered How a statistical package like SAS analyses market risk without any calculus support
May
26
awarded  Revival
May
18
awarded  Nice Answer
May
15
revised Outlier Detection in Time-Series: How to reduce false positives?
added 596 characters in body
May
15
answered Outlier Detection in Time-Series: How to reduce false positives?
May
7
revised Why is it claimed that a sample is often more accurate than a census?
edited body
Apr
30
comment MCMC converging to a single value?
Do you mean for(j in 1:max(speaker)) or for(j in 1:length(speaker))?
Apr
23
revised Markov chains vs. HMM
edited body
Apr
23
answered Markov chains vs. HMM
Apr
21
comment Using the Weibull curve to model responses from a direct mail campaign. Model isn't fitting the data very well
@tristan: I wouldn't ignore your comment. A gamma curve fits well, including the height and a longer tail. And a plot of the density of the log looks normalish. (I'm not sure where curve-fitting and modeling part ways, though.)
Apr
15
revised Z-score in the analysis of data
added 3 characters in body
Apr
14
answered Z-score in the analysis of data
Apr
9
answered What are the options when statisticians who only know R need more computing speed
Apr
9
reviewed Edit Probability of a consecutive pair of values
Apr
9
revised Probability of a consecutive pair of values
format equations
Apr
7
comment Basic stats question - How to tell if my data distribution is symmetric
@user72943 If you're totally satisfied with it, don't forget to come back and select Glen_b's answer. You might want to wait a little while to see if someone submits a better answer, but Glen_b will receive more credit if you accept the answer.
Apr
6
comment How to best analyze several time series of speed data? Comparing regression analysis?
You need to clarify a bit more what you mean "through a journey". You could use something like "distance in a straight line from the destination", "distance along the (final) path from the destination", or "percentage of the way along the final path", and they have very different meanings when you think of short hops down the coast versus trips across the Pacific. Do you care about things like currents, areas the ship passes through, etc? Should you? (Depends on the conclusions you want to draw and how strong you want them to be.)