Reputation
13,482
Top tag
Next privilege 15,000 Rep.
Protect questions
Badges
1 33 75
Impact
~140k people reached

May
2
comment Second derivative of SmoothKernelDistribution PDF?
You might try KernelMixtureDistribution to avoid the piecewise linear limitation
Apr
19
comment Why do EstimatedDistribution and DistributionFitTest work this way
I recommend reading the following en.m.wikipedia.org/wiki/Lilliefors_test
Apr
19
comment Why do EstimatedDistribution and DistributionFitTest work this way
In one case the parameters are estimated internally. The null distribution for the tests assume the parameters are known apriori and so a correction to the p-value must be applied to account for the estimation. If you provide a fitted distribution the test assumes known parameters and makes no correction.
Mar
16
comment Generate a sample from a multivariate Cauchy distribution
Why not use MultivariateTDistribution with v = 1?
Feb
24
comment Creating Identification/Classification trees
mathematica.stackexchange.com/questions/19285/… may help
Feb
5
comment Is there a convenient way to sum TimeSeries objects in Mathematica?
You can also set the missing data method on the TimeSeries objects to None. Not sure if that will work, I don't have M in front of me to try it.
Feb
4
comment Is there a convenient way to sum TimeSeries objects in Mathematica?
TimeSeriesThread is what you want I think
Jan
17
comment What is the purpose of Internal`LocalizedBlock?
@Mr.Wizard just a little tidbit, if I recall correctly this was added for the purpose of fitted models being able to work with subscripted variables so I think Dan is right on here.
Jan
16
comment Why does TimeSeriesShift is just adding a fixed number of days?
That's probably why TimeSeriesShift does what it does. Both TimeSeries and TemporalData require unique time stamps. Also many algorithms are particular About uniform vs irregular spacing which is only preserved by a uniform shift.
Jan
15
comment Why does TimeSeriesShift is just adding a fixed number of days?
What should it do for January 29th?
Jan
14
comment Periodogram for irregularly spaced data
@Verbeia you should definitely file a suggestion with WRI for Periodogram to take TemporalData (and TimeSeries). This was on my todo list before I left I just didn't get to it.
Jan
9
comment Why is my data 10 times slower than random data when doing matrix multiplication
Computing the following Tally[ByteCount /@ Flatten[tb]] shows that some of your numbers have different byte counts due to large exponents. I doubt the data can be packed.
Jan
4
comment Rapid density estimation and rendering of decision regions
I'm glad to help.
Dec
25
comment Generate nonoverlapping random circles
Related mathematica.stackexchange.com/questions/2594/…
Dec
24
comment Fitting higher order ARIMA models hangs, never completes
@TomHayden you don't want to resample but want to assume regularity then just extract the values and fit with those.
Dec
24
comment What are the differences between these functions when used for NMaximize?
I seriously doubt repeated calls to NumericQ is the problem. It is likely that without NumericQ NMaximize is able to come up with an optimized expression for your function symbolically which it caches. With NumericQ it can't optimize/evaluate the expression symbolically.
Dec
23
comment Interpretation of CopulaDistribution
The reason for my down vote is that I don't feel this addresses the question at hand and would be more fitting as a comment or in chat.
Dec
22
comment Fitting higher order ARIMA models hangs, never completes
I think this might be considered a bug then. By setting TemporalRegularity to true it should completely ignore the actual time stamps in the fitting.
Dec
21
comment Why is Likelihood / LogLikelihood not working?
After addressing @Sjoerd C. de Vries point you need to add another set of list braces around {x1,x2,x3,x4} it is expecting a dataset not a single point and multinomial distributions are multivariate.
Dec
21
comment Time Series Analysis - How does it Difference?
Yes, it uses the orders of the model to do the differencing. I will say that R still has its place, where it lacks in automation and sometimes ease of use it makes up in completeness. Mathematica's time series functionality is great but still immature so there will be things you can't easily do that may cause you to turn to R. If you go there I recommend starting with auto.arima which is the closest I've seen to TimeSeriesModelFit. Incidentally you can get the best of both worlds by getting familiar with RLink.