 Maximum spacing estimation

In statistics, maximum spacing estimation (MSE or MSP), or maximum product of spacing estimation (MPS), is a method for estimating the parameters of a univariate statistical model.^{[1]} The method requires maximization of the geometric mean of spacings in the data, which are the differences between the values of the cumulative distribution function at neighbouring data points.
The concept underlying the method is based on the probability integral transform, in that a set of independent random samples derived from any random variable should on average be uniformly distributed with respect to the cumulative distribution function of the random variable. The MPS method chooses the parameter values that make the observed data as uniform as possible, according to a specific quantitative measure of uniformity.
One of the most common methods for estimating the parameters of a distribution from data, the method of maximum likelihood (MLE), can break down in various cases, such as involving certain mixtures of continuous distributions.^{[2]} In these cases the method of maximum spacing estimation may be successful.
Apart from its use in pure mathematics and statistics, the trial applications of the method have been reported using data from fields such as hydrology,^{[3]} econometrics,^{[4]} and others.^{[5]}
Contents
History and usage
The MSE method was derived independently by Russel Cheng and Nik Amin at the University of Wales Institute of Science and Technology, and Bo Ranneby at the Swedish University of Agricultural Sciences.^{[2]} The authors explained that due to the probability integral transform at the true parameter, the “spacing” between each observation should be uniformly distributed. This would imply that the difference between the values of the cumulative distribution function at consecutive observations should be equal. This is the case that maximizes the geometric mean of such spacings, so solving for the parameters that maximize the geometric mean would achieve the “best” fit as defined this way. Ranneby (1984) justified the method by demonstrating that it is an estimator of the Kullback–Leibler divergence, similar to maximum likelihood estimation, but with more robust properties for various classes of problems.
There are certain distributions, especially those with three or more parameters, whose likelihoods may become infinite along certain paths in the parameter space. Using maximum likelihood to estimate these parameters often breaks down, with one parameter tending to the specific value that causes the likelihood to be infinite, rendering the other parameters inconsistent. The method of maximum spacings, however, being dependent on the difference between points on the cumulative distribution function and not individual likelihood points, does not have this issue, and will return valid results over a much wider array of distributions.^{[1]}
The distributions that tend to have likelihood issues are often those used to model physical phenomena. Hall & al. (2004) seek to analyze flood alleviation methods, which requires accurate models of river flood effects. The distributions that better model these effects are all threeparameter models, which suffer from the infinite likelihood issue described above, leading to Hall’s investigation of the maximum spacing procedure. Wong & Li (2006), when comparing the method to maximum likelihood, use various data sets ranging from a set on the oldest ages at death in Sweden between 1905 and 1958 to a set containing annual maximum wind speeds.
Definition
Given an iid random sample {x_{1}, …, x_{n}} of size n from a univariate distribution with cdf F(x;θ_{0}), where θ_{0} ∈ Θ is an unknown parameter to be estimated, let {x_{(1)}, …, x_{(n)}} be the corresponding ordered sample, that is the result of sorting of all observations from smallest to largest. For convenience also denote x_{(0)} = −∞ and x_{(n+1)} = +∞.
Define the spacings as the “gaps” between the values of the distribution function at adjacent ordered points: ^{[note 1]}
Then the maximum spacing estimator of θ_{0} is defined as a value that maximizes the logarithm of the geometric mean of sample spacings:
By the inequality of arithmetic and geometric means, function S_{n}(θ) is bounded from above by −ln(n+1), and thus the maximum has to exist at least in the supremum sense.
Note that some authors define the function S_{n}(θ) somewhat differently. In particular, Ranneby (1984) multiplies each D_{i} by a factor of (n+1), whereas Cheng & Stephens (1989) omit the ^{1}⁄_{n+1} factor in front of the sum and add the “−” sign in order to turn the maximization into minimization. As these are constants with respect to θ, the modifications do not alter the location of the maximum of the function S_{n}.
Examples
This section presents two examples of calculating the maximum spacing estimator.
Example 1
Suppose two values x_{(1)} = 2, x_{(2)} = 4 were sampled from the exponential distribution F(x;λ) = 1 − e^{−xλ}, x ≥ 0 with unknown parameter λ > 0. In order to construct the MSE we have to first find the spacings:
i F(x_{(i)}) F(x_{(i−1)}) D_{i} = F(x_{(i)}) − F(x_{(i−1)}) 1 1 − e^{−2λ} 0 1 − e^{−2λ} 2 1 − e^{−4λ} 1 − e^{−2λ} e^{−2λ} − e^{−4λ} 3 1 1 − e^{−4λ} e^{−4λ} The process continues by finding the λ that maximizes the geometric mean of the “difference” column. Using the convention that ignores taking the (n+1)^{st} root, this turns into the maximization of the following product: (1 − e^{−2λ}) · (e^{−2λ} − e^{−4λ}) · (e^{−4λ}). Letting μ = e^{−2λ}, the problem becomes finding the maximum of μ^{5}−2μ^{4}+μ^{3}. Differentiating, the μ has to satisfy 5μ^{4}−8μ^{3}+3μ^{2} = 0. This equation has roots 0, 0.6, and 1. As μ is actually e^{−2λ}, it has to be greater than zero but less than one. Therefore, the only acceptable solution is
which corresponds to an exponential distribution with a mean of ^{1}⁄_{λ} ≈ 3.915. For comparison, the maximum likelihood estimate of λ is the inverse of the sample mean, 3, so λ_{MLE} = ⅓ ≈ 0.333.
Example 2
Suppose {x_{(1)}, …, x_{(n)}} is the ordered sample from a uniform distribution U(a,b) with unknown endpoints a and b. The cumulative distribution function is F(x;a,b) = (x−a)÷(b−a) when x∈[a,b]. Therefore individual spacings are given by
Calculating the geometric mean and then taking the logarithm, statistic S_{n} will be equal to
Here only the first three terms depend on the parameters a and b. Differentiating with respect to those parameters and solving the resulting linear system, the maximum spacing estimates will be
These are known to be the uniformly minimum variance unbiased (UMVU) estimators for the continuous uniform distribution. In comparison, the maximum likelihood estimates for this problem and are biased and have higher meansquared error.
Properties
Consistency and efficiency
The maximum spacing estimator is a consistent estimator in that it converges in probability to the true value of the parameter, θ_{0}, as the sample size increases to infinity.^{[2]} The consistency of maximum spacing estimation holds under much more general conditions than for maximum likelihood estimators. In particular, in cases where the underlying distribution is Jshaped, maximum likelihood will fail where MSE succeeds.^{[1]} An example of a Jshaped density is the Weibull distribution, specifically a shifted Weibull, with a shape parameter less than 1. The density will tend to infinity as x approaches the location parameter rendering estimates of the other parameters inconsistent.
Maximum spacing estimators are also at least as asymptotically efficient as maximum likelihood estimators, where the latter exist. However, MSEs may exist in cases where MLEs do not.^{[1]}
Sensitivity
Maximum spacing estimators are sensitive to closely spaced observations, and especially ties.^{[6]} Given
we get
When the ties are due to multiple observations, the repeated spacings (those that would otherwise be zero) should be replaced by the corresponding likelihood.^{[1]} That is, one should substitute f_{i}(θ) for D_{i}(θ), as
since x_{i} = x_{i − 1}.
When ties are due to rounding error, Cheng & Stephens (1989) suggest another method to remove the effects. ^{[note 2]} Given r tied observations from x_{i} to x_{i+r−1}, let δ represent the roundoff error. All of the true values should then fall in the range . The corresponding points on the distribution should now fall between and . Cheng and Stephens suggest assuming that the rounded values are uniformly spaced in this interval, by defining
The MSE method is also sensitive to secondary clustering.^{[6]} One example of this phenomenon is when a set of observations is thought to come from a single normal distribution, but in fact comes from a mixture normals with different means. A second example is when the data is thought to come from an exponential distribution, but actually comes from a gamma distribution. In the latter case, smaller spacings may occur in the lower tail. A high value of M(θ) would indicate this secondary clustering effect, and suggesting a closer look at the data is required.^{[6]}
Goodness of fit
The statistic S_{n}(θ) is also a form of Moran or MoranDarling statistic, M(θ), which can be used to test goodness of fit. ^{[note 3]} It has been shown that the statistic, when defined as
is asymptotically normal, and that a chisquared approximation exists for small samples.^{[6]} In the case where we know the true parameter θ^{0}, Cheng & Stephens (1989) show that the statistic has a normal distribution with
where γ is the Euler–Mascheroni constant which is approximately 0.57722.^{[note 4]}
The distribution can also be approximated by that of A, where
 ,
in which
and where follows a chisquare distribution with n degrees of freedom. Therefore, to test the hypothesis H_{0} that a random sample of n values comes from the distribution F(x,θ), the statistic can be calculated. Then H_{0} should be rejected with significance α if the value is greater than the critical value of the appropriate chisquare distribution.^{[6]}
Where θ_{0} is being estimated by , Cheng & Stephens (1989) showed that has the same asymptotic mean and variance as in the known case. However, the test statistic to be used requires the addition of a bias correction term and is:
where k is the number of parameters in the estimate.
Generalized maximum spacing
Alternate measures and spacings
Ranneby & Ekström (1997) generalized the MSE method to approximate other measures besides the Kullback–Leibler measure. Ekström (1997) further expanded the method to investigate properties of estimators using higher order spacings, where an morder spacing would be defined as F(X_{j + m}) − F(X_{j}).
Multivariate distributions
Ranneby & al. (2005) discuss extended maximum spacing methods to the multivariate case. As there is no natural order for , they discuss two alternative approaches: a geometric approach based on Dirichlet cells and a probabilistic approach based on a “nearest neighbor ball” metric.
See also
Notes
 ^ The actual definition is sourced to Pyke (1965), but without direct access to that paper, sourcing is given to Pyke (1972) which defines the spacings in passing. — Editor.
Pyke (1965) starts with “review of previous results known about spacings”, which implies that he hasn't invented them. In fact the first work about the spacings he mentions is “Whitworth (1887)”, although no actual reference was given.  ^ There appear to be some minor typographical errors in the paper. For example, in section 4.2, equation (4.1), the rounding replacement for D_{j}, should not have the log term. In section 1, equation (1.2), D_{j} is defined to be the spacing itself, and M(θ) is the negative sum of the logs of D_{j}. If D_{j} is logged at this step, the result is always =<0, as the difference between two adjacent points on a cumulative distribution is always ≤ 1, and strictly <1 unless there are only two points at the bookends. Also, in section 4.3, on page 392, calculation shows that it is the variance which has MPS estimate of 6.87, not the standard deviation .  Editor
 ^ The literature refers to related statistics as Moran or MoranDarling statistics. For example, Cheng & Stephens (1989) analyze the form where is defined as above. Wong & Li (2006) use the same form as well. However, Beirlant & al. (2001) uses the form , with the additional factor of (n + 1) inside the logged summation. The extra factors will make a difference in terms of the expected mean and variance of the statistic. For consistency, this article will continue to use the Cheng & Amin/Wong & Li form.  Editor
 ^ Wong & Li (2006) leave out the Euler–Mascheroni constant from their description.  Editor
References
Works Cited
 Anatolyev, Stanislav; Kosenok, Kosenok (2005). "An alternative to maximum likelihood based on spacings". Econometric Theory 21 (2): 472–476. doi:10.1017/S0266466605050255. http://fir.nes.ru/~gkosenok/MPS.pdf. Retrieved 20090121.
 Beirlant, J.; Dudewicz, E.J.; Györfi, L.; van der Meulen, E.C. (1997). "Nonparametric entropy estimation: an overview". International Journal of Mathematical and Statistical Sciences 6 (1): 17–40. ISSN 10557490. Archived from the original on May 5, 2005. http://web.archive.org/web/20050505044534/http://www.menem.com/ilya/digital_library/entropy/beirlant_etal_97.pdf. Retrieved 20081231. Note: linked paper is an updated 2001 version.
 Cheng, R.C.H.; Amin, N.A.K. (1983). "Estimating parameters in continuous univariate distributions with a shifted origin". Journal of the Royal Statistical Society, Series B 45 (3): 394–403. ISSN 00359246. JSTOR 2345411.
 Cheng, R.C.H; Stephens, M. A. (1989). "A goodnessoffit test using Moran’s statistic with estimated parameters". Biometrika 76 (2): 386–392. doi:10.1093/biomet/76.2.385.
 Ekström, Magnus (1997). "Generalized maximum spacing estimates". University of Umeå, Department of Mathematics 6. ISSN 03453928. Archived from the original on February 14, 2007. http://web.archive.org/web/20070214143052/http://www.matstat.umu.se/varia/reports/rep9706.ps.gz. Retrieved 20081230.
 Hall, M.J.; van den Boogaard, H.F.P.; Fernando, R.C.; Mynett, A.E. (2004). "The construction of confidence intervals for frequency analysis using resampling techniques". Hydrology and Earth System Sciences 8 (2): 235–246. ISSN 10275606. http://www.hydrolearthsystsci.net/8/235/2004/hess82352004.pdf. Retrieved 20090121.
 Pyke, Ronald (1965). "Spacings". Journal of the Royal Statistical Society, Series B 27 (3): 395–449. ISSN 00359246. JSTOR 2345793.
 Pyke, Ronald (1972). "Spacings revisited". Proceedings of the sixth Berkeley symposium on mathematical statistics and probability (University of California Press) 1: 417–427. ISSN 00970433. MR0405709. Zbl 0234.62008. http://projecteuclid.org/DPubS/Repository/1.0/Disseminate?view=body&id=pdf_1&handle=euclid.bsmsp/1200514103. Retrieved 20100318.
 Ranneby, Bo (1984). "The maximum spacing method. An estimation method related to the maximum likelihood method". Scandinavian Journal of Statistics 11 (2): 93–112. ISSN 03036898. JSTOR 4615946.
 Ranneby, Bo; Ekström, Magnus (1997). "Maximum spacing estimates based on different metrics". University of Umeå, Department of Mathematics 5. ISSN 03453928. Archived from the original on February 14, 2007. http://web.archive.org/web/20070214143042/http://www.matstat.umu.se/varia/reports/rep9705.ps.gz. Retrieved 20081230.
 Ranneby, Bo; Jammalamadakab, S. Rao; Teterukovskiy, Alex (2005). "The maximum spacing estimation for multivariate observations". Journal of Statistical Planning and Inference 129 (1–2): 427–446. doi:10.1016/j.jspi.2004.06.059. http://www.pstat.ucsb.edu/faculty/jammalam/html/research%20publication_files/MSP2.pdf. Retrieved 20081231.
 Wong, T.S.T; Li, W.K. (2006). "A note on the estimation of extreme value distributions using maximum product of spacings". Time series and related topics: in memory of ChingZong Wei. Beachwood, Ohio: Institute of Mathematical Statistic. pp. 272–283. arXiv:math/0702830v1. doi:10.1214/074921706000001102.
Categories: Estimation theory
 Mathematical modeling
Wikimedia Foundation. 2010.
Look at other dictionaries:
Maximum likelihood — In statistics, maximum likelihood estimation (MLE) is a method of estimating the parameters of a statistical model. When applied to a data set and given a statistical model, maximum likelihood estimation provides estimates for the model s… … Wikipedia
Minimum distance estimation — (MDE) is a statistical method for fitting a mathematical model to data, usually the empirical distribution. Contents 1 Definition 2 Statistics used in estimation 2.1 Chi square criterion … Wikipedia
Entropy estimation — Estimating the differential entropy of a system or process, given some observations, is useful in various science/engineering applications, such as Independent Component Analysis [Dinh Tuan Pham (2004) Fast algorithms for mutual information based … Wikipedia
German tank problem — During World War II, production of German tanks such as the Panther was accurately estimated by Allied intelligence using statistical methods. In the statistical theory of estimation, estimating the maximum of a uniform distribution is a common… … Wikipedia
Uniform distribution (continuous) — Uniform Probability density function Using maximum convention Cumulative distribution function … Wikipedia
Uniform distribution (discrete) — discrete uniform Probability mass function n = 5 where n = b − a + 1 Cumulative distribution function … Wikipedia
Portal:Statistics — Wikipedia portals: Culture Geography Health History Mathematics Natural sciences People Philosophy Religion Society Technology … Wikipedia
MSE — is a three letter acronym which may refer to: Computing and technology Microsoft Excel, a spreadsheet application Mobile Subscriber Equipment, used for tactical communications Message Stream Encryption, a BitTorrent protocol encryption Microsoft… … Wikipedia
Orthogonal frequencydivision multiplexing — Passband modulation v · d · e Analog modulation AM · … Wikipedia
Heat capacity — Thermodynamics … Wikipedia