Rank: 196 based on 468 downloads (last 30 days) and 5 files submitted
photo

Zdravko Botev

E-mail
Company/University
University of New South Wales

Personal Profile:
Professional Interests:
Monte Carlo methods: generalized splitting

 

Watch this Author's files

 

Files Posted by Zdravko View all
Updated   File Tags Downloads
(last 30 days)
Comments Rating
07 Nov 2012 Screenshot Fractional Brownian field or surface generator Generates fractional Brownian field or surface with a given Hurst parameter using Stein's method. Author: Zdravko Botev circulant matrix, fractional brownian s..., wiener sheet, stationary gaussian p..., circulant embedding 37 2
06 Nov 2012 Screenshot Fractional Brownian motion generator Generates fractional Brownian motion with a given Hurst parameter using the FFT. Author: Zdravko Botev fractional brownian m..., circulant matrix, spectral method, stationary gaussian p... 46 0
02 Nov 2012 Screenshot Circulant Embedding method for generating stationary Gaussian field Implements Dietrich and Newsam's circulant embedding method for fast generation of Gaussian fields. Author: Zdravko Botev random field, stationary gaussian p..., fractional brownian m..., wiener sheet, spatial process 24 1
  • 5.0
5.0 | 1 rating
13 Jan 2011 Screenshot Kernel Density Estimator Reliable and extremely fast kernel density estimator for one-dimensional data Author: Zdravko Botev statistics, probability, kernel smoothing, automatic hitech band..., tdsubha2010, kernel density estima... 191 35
  • 4.75
4.8 | 29 ratings
26 May 2009 Screenshot kernel density estimation fast and accurate state-of-the-art bivariate kernel density estimator Author: Zdravko Botev statistics, probability, kernel density estima..., optimal bandwidth sel... 170 33
  • 4.08
4.1 | 28 ratings
Comments and Ratings by Zdravko View all
Updated File Comments Rating
21 Jan 2011 Kernel Density Estimator Reliable and extremely fast kernel density estimator for one-dimensional data Author: Zdravko Botev

Due to numerical round-off error from the fft.m function, it is possible to get density values of -1.38e-018 (instead of 0) and cdf values slightly larger than 1.
If this is a problem, one can correct the output from kde by overwriting:

density=max(density,0); cdf=min(1,cdf);

15 Oct 2010 Kernel Density Estimator Reliable and extremely fast kernel density estimator for one-dimensional data Author: Zdravko Botev

Dear George, the kde function works as it should. There is no problem with the kde. What you call a problem is actually one of the main strengths of the routine.

By typing data = [d1;d1;d1;d1;d1;d2;d3];
you are creating DISCRETE data, because you create ties (the same values appear multiple times). For a truly continuous data, there can be no ties or repeated values!!!
If you have ties, then the data CANNOT be continuous be definition.

The kde.m CORRECTLY recognizes that the data you have provided is perfectly discrete and since discrete data does not need smoothing, the selected bandwidth should be zero. kde.m is the only routine I am aware of that does this correctly, every other routine fails this BASIC theoretical test.

Comments and Ratings on Zdravko's Files View all
Updated File Comment by Comments Rating
22 Oct 2014 kernel density estimation fast and accurate state-of-the-art bivariate kernel density estimator Author: Zdravko Botev Uribe, Felipe

17 Aug 2014 Kernel Density Estimator Reliable and extremely fast kernel density estimator for one-dimensional data Author: Zdravko Botev Lalancette, Marc

Thanks, very useful. Strangely I get very different results on Matlab 2011b and 2013b with the same data. On the recent version, the density distribution is more smooth and has a stronger tendency to not go to 0 at the ends of the distribution. I'm guessing this is due to changes in a Matlab function. Any ideas?

16 Aug 2014 kernel density estimation fast and accurate state-of-the-art bivariate kernel density estimator Author: Zdravko Botev Jakob Nikolas

If you need to use a fixed bandwidth, just overwrite t_x and t_y in the main function. Thanks to Zdravko for this hint.

16 Aug 2014 kernel density estimation fast and accurate state-of-the-art bivariate kernel density estimator Author: Zdravko Botev Jakob Nikolas

I ran into the same error as described by Oliver and fixed it by replacing

t_star=fzero( @(t)(t-evolve(t)),[0,0.1]);

with

options = optimset('FunValCheck','off')
try
t_star=fzero( @(t)(t-evolve(t)),[0,0.1],options);
catch
defaultError('override error, be cautious!');
t_star=0
end

11 Aug 2014 Kernel Density Estimator Reliable and extremely fast kernel density estimator for one-dimensional data Author: Zdravko Botev Genevieve

Contact us