Rank: 1808 based on 72 downloads (last 30 days) and 7 files submitted
photo

Matthew Nelson

E-mail

Personal Profile:

http://www.its.caltech.edu/~nelsonmj/


 

Watch this Author's files

 

Files Posted by Matthew Nelson View all
Updated   File Tags Downloads
(last 30 days)
Comments Rating
16 Sep 2011 Binomial Test 1 or 2 sided binomial test with arbitrary binomial probabilities Author: Matthew Nelson binomial, statistics, stats, test, binomial test, onesided 32 4
  • 4.5
4.5 | 2 ratings
24 Mar 2010 Non-parametric error/confidence intervals Calc standard error of the mean or non-parametric confidence intervals for samples of a time series Author: Matthew Nelson statistics, nonparametric, chebyshev, vysochanskij–petunin, standard error, confidence intervals 9 0
21 Apr 2009 Huynh-Feldt epsilon general procedure Calc. the Huynh-Feldt epsilon for any arbitrary combination of between and within subject factors Author: Matthew Nelson statistics, anova, repeated measures, repeated, huynhfeldt, huynh 13 10
  • 5.0
5.0 | 4 ratings
25 Mar 2009 SDFConv Given spike times across trials, create smoothed peri-event hist convolved with a PSP or Gaus kernel Author: Matthew Nelson neuroscience, histogram, spike, spike train, convolve, smoothed histogram 2 0
25 Mar 2009 Find Optimal Kernel Find optimal causal filter kernel that convolves with one time series to approximate another Author: Matthew Nelson neuroscience, psychology, filter, kernel, wiener, wienerhopf 7 9
  • 4.0
4.0 | 5 ratings
Comments and Ratings by Matthew Nelson View all
Updated File Comments Rating
20 Jan 2012 Find Optimal Kernel Find optimal causal filter kernel that convolves with one time series to approximate another Author: Matthew Nelson

These are just parameters in creating a sample kernel for testing the performance of the function. You can adjust them however you please to change the test kernel. The purpose of including TestFindOptKern.m was just to demonstrate the use of the function, and is not by itself an important script.

05 Jan 2012 Huynh-Feldt epsilon general procedure Calc. the Huynh-Feldt epsilon for any arbitrary combination of between and within subject factors Author: Matthew Nelson

I suspect that this is a difference between how SPSS defines the Huynh-Feldt epsilon in its different versions of SPSS, but I don’t have the time to investigate this further now. I had checked this earlier with a version that I know was older than SPSS 20, but I don’t recall which. The ‘heart’ of the program is the EpsGG which is used to determine the EpsHF.

16 Sep 2011 Binomial Test 1 or 2 sided binomial test with arbitrary binomial probabilities Author: Matthew Nelson

Thanks for calling attention to that. The problem was that when using the two-sided test in the special case when the expected value was precisely equaled by the number of successes, the code would add the probability at that discrete value twice. That is now fixed in the update. The probability is always 1 in this case anyway, which can be interpreted as the probability that the absolute difference in the outcome from the expected value is greater than or equal to 0. (A certainty) In all other cases the code is and has been accurate.

13 Apr 2010 Huynh-Feldt epsilon general procedure Calc. the Huynh-Feldt epsilon for any arbitrary combination of between and within subject factors Author: Matthew Nelson

Thanks all for the comments and sorry to be slow to respond.

I didn’t add anything like mauchly’s test for sphericity because personally I prefer to account for even small deviations from sphericity rather than use a test like that to decide whether or not to. But thanks just the same to Matt for posting that code for anyone that wants to use it.

With regards to Yoni’s question, there is matlab’s anovan that could be combined with this to allow for a Repeated Measures anovan. I have code for that halfway finished, but stopped as I found a better way around that for the project I was working on at the time. If I come across a project later on where I need that, I will finish that and post it to the matlab file exchange. (Provided someone else hasn’t already done that by then!)

It’s unfortunate that matlab’s statistical toolbox is so lacking for such basic things like a repeated measures anova, among other things, but c’est la vie.

25 Mar 2009 Find Optimal Kernel Find optimal causal filter kernel that convolves with one time series to approximate another Author: Matthew Nelson

xcov is available in matlab's signal processing toolbox. I'm sorry if that wasn't clear before. I've adjusted the online page to reflect that.

Comments and Ratings on Matthew Nelson's Files View all
Updated File Comment by Comments Rating
05 Nov 2014 Huynh-Feldt epsilon general procedure Calc. the Huynh-Feldt epsilon for any arbitrary combination of between and within subject factors Author: Matthew Nelson David Saxby

Hi All,

I'm a PhD candidate at Griffith University, Australia.

I'm experimenting with this function and reading some of the MathWorks commentary. I'm not formatting my input arguments correctly as I'm getting errors, and was hoping to clarify.

I'm testing a single group of individuals (n=54) (no between analysis) across 3 repeated measures. I'm looking at a single factor (a particular loading variable). Sample size is consistent across all repeated measures.

My understanding is:

Y is a single column with the repeated measured variable stacked vertically (first, second, third repeated measurement), length 3*n.
BTFacs is empty.
WInFacs is a column of 1's of length Y.
S is column array 1:length(Y).

Any help would be greatly appreciated.

Best,

16 May 2013 Find Optimal Kernel Find optimal causal filter kernel that convolves with one time series to approximate another Author: Matthew Nelson Luke Gahan

30 Mar 2013 Find Optimal Kernel Find optimal causal filter kernel that convolves with one time series to approximate another Author: Matthew Nelson Luke Gahan

Hi,

Just one small question. For xcov(x,y) you retain Cxy(MaxnLags+2:end). This means that you are discarding the covariance at zero lag and retaining 1:MaxnLags.

While for xcov(x,x) you retain 0:MaxnLags-1.

My understanding of the procedure (which could well be incorrect) is that if the user specifies MaxnLags, then maybe 0:MaxnLags should be retained, meaning MaxnLags+1 filter coefficients will be calculated (zero time plus lags)?

Thanks,

Luke

28 Feb 2012 Binomial Test 1 or 2 sided binomial test with arbitrary binomial probabilities Author: Matthew Nelson Adam

Probably related to the above problem, but it is still possible to get results greater than 1 when the input is a vector:

binotest([11],22,0.5, 'Two')
ans =
1

binotest([11;12],22,0.5, 'Two')
ans =
1.1682
0.8318

04 Feb 2012 Huynh-Feldt epsilon general procedure Calc. the Huynh-Feldt epsilon for any arbitrary combination of between and within subject factors Author: Matthew Nelson Amarelo

Thanks, a very helpful function! Together with Matt Mollison's addition of the Mauchly-Test for sphericity (see above) this completely saves me running the repeated measures ANOVAs on SPSS again to get the corrected p-values. And it seems to agree well with the comparisons I have made.

Contact us