Mean-preserving spread

Last updated April 10, 2020

In probability and statistics, a mean-preserving spread (MPS)^[1] is a change from one probability distribution A to another probability distribution B, where B is formed by spreading out one or more portions of A's probability density function or probability mass function while leaving the mean (the expected value) unchanged. As such, the concept of mean-preserving spreads provides a stochastic ordering of equal-mean gambles (probability distributions) according to their degree of risk; this ordering is partial, meaning that of two equal-mean gambles, it is not necessarily true that either is a mean-preserving spread of the other. A is said to be a mean-preserving contraction of B if B is a mean-preserving spread of A.

Ranking gambles by mean-preserving spreads is a special case of ranking gambles by second-order stochastic dominance – namely, the special case of equal means: If B is a mean-preserving spread of A, then A is second-order stochastically dominant over B; and the converse holds if A and B have equal means.

If B is a mean-preserving spread of A, then B has a higher variance than A and the expected values of A and B are identical; but the converse is not in general true, because the variance is a complete ordering while ordering by mean-preserving spreads is only partial.

Example

This example shows that to have a mean-preserving spread does not require that all or most of the probability mass move away from the mean.^[2] Let A have equal probabilities $1/100$ on each outcome $x_{Ai}$ , with $x_{Ai}=198$ for $i=1,\dots ,50$ and $x_{Ai}=202$ for $i=51,\dots ,100$ ; and let B have equal probabilities $1/100$ on each outcome $x_{Bi}$ , with $x_{B1}=100$ , $x_{Bi}=200$ for $i=2,\dots ,99$ , and $x_{B100}=300$ . Here B has been constructed from A by moving one chunk of 1% probability from 198 to 100 and moving 49 probability chunks from 198 to 200, and then moving one probability chunk from 202 to 300 and moving 49 probability chunks from 202 to 200. This sequence of two mean-preserving spreads is itself a mean-preserving spread, despite the fact that 98% of the probability mass has moved to the mean (200).

Mathematical definitions

Let $x_{A}$ and $x_{B}$ be the random variables associated with gambles A and B. Then B is a mean-preserving spread of A if and only if $x_{B}{\overset {d}{=}}(x_{A}+z)$ for some random variable $z$ having $E(z\mid x_{A})=0$ for all values of $x_{A}$ . Here ${\overset {d}{=}}$ means "is equal in distribution to" (that is, "has the same distribution as").

Mean-preserving spreads can also be defined in terms of the cumulative distribution functions $F_{A}$ and $F_{B}$ of A and B. If A and B have equal means, B is a mean-preserving spread of A if and only if the area under $F_{A}$ from minus infinity to $x$ is less than or equal to that under $F_{B}$ from minus infinity to $x$ for all real numbers $x$ , with strict inequality at some $x$ .

Both of these mathematical definitions replicate those of second-order stochastic dominance for the case of equal means.

Relation to expected utility theory

If B is a mean-preserving spread of A then A will be preferred by all expected utility maximizers having concave utility. The converse also holds: if A and B have equal means and A is preferred by all expected utility maximizers having concave utility, then B is a mean-preserving spread of A.

Related Research Articles

In probability theory and statistics, the cumulative distribution function (CDF) of a real-valued random variable $, or just distribution function of, evaluated at, is the probability that will take a value less than or equal to .$

There are several kinds of means in various branches of mathematics.

In probability theory, a normaldistribution is a type of continuous probability distribution for a real-valued random variable. The general form of its probability density function is

In probability theory and statistics, a probability distribution is a mathematical function that provides the probabilities of occurrence of different possible outcomes in an experiment. In more technical terms, the probability distribution is a description of a random phenomenon in terms of the probabilities of events. For instance, if the random variable $X$ is used to denote the outcome of a coin toss, then the probability distribution of $X$ would take the value 0.5 for $X = heads$ , and 0.5 for $X = tails$ . Examples of random phenomena can include the results of an experiment or survey.

This is a fundamental notion in probability theory, as in statistics and the theory of stochastic processes.

In probability theory, the central limit theorem (CLT) establishes that, in some situations, when independent random variables are added, their properly normalized sum tends toward a normal distribution even if the original variables themselves are not normally distributed. The theorem is a key concept in probability theory because it implies that probabilistic and statistical methods that work for normal distributions can be applicable to many problems involving other types of distributions.

In probability theory, there exist several different notions of convergence of random variables. The convergence of sequences of random variables to some limit random variable is an important concept in probability theory, and its applications to statistics and stochastic processes. The same concepts are known in more general mathematics as stochastic convergence and they formalize the idea that a sequence of essentially random or unpredictable events can sometimes be expected to settle down into a behavior that is essentially unchanging when items far enough into the sequence are studied. The different possible notions of convergence relate to how such a behavior can be characterized: two readily understood behaviors are that the sequence eventually takes a constant value, and that values in the sequence continue to change but can be described by an unchanging probability distribution.

A Markov chain is a stochastic model describing a sequence of possible events in which the probability of each event depends only on the state attained in the previous event. In continuous-time, it is known as a Markov process. It is named after the Russian mathematician Andrey Markov.

A random walk is a mathematical object, known as a stochastic or random process, that describes a path that consists of a succession of random steps on some mathematical space such as the integers. An elementary example of a random walk is the random walk on the integer number line, $, which starts at 0 and at each step moves +1 or -1 with equal probability. Other examples include the path traced by a molecule as it travels in a liquid or a gas, the search path of a foraging animal, the price of a fluctuating stock and the financial status of a gambler: all can be approximated by random walk models, even though they may not be truly random in reality. As illustrated by those examples, random walks have applications to engineering and many scientific fields including ecology, psychology, computer science, physics, chemistry, biology as well as economics. Random walks explain the observed behaviors of many processes in these fields, and thus serve as a fundamental model for the recorded stochastic activity. As a more mathematical application, the value of π can be approximated by the use of random walk in an agent-based modeling environment. The term random walk was first introduced by Karl Pearson in 1905.$

In economics, game theory, and decision theory, the expected utility hypothesis—concerning people's preferences with regard to choices that have uncertain outcomes (gambles)⁠—states that the subjective value associated with an individual's gamble is the statistical expectation of that individual's valuations of the outcomes of that gamble, where these valuations may differ from the dollar value of those outcomes. The introduction of St. Petersburg Paradox by Daniel Bernoulli in 1738 is considered the beginnings of the hypothesis. This hypothesis has proven useful to explain some popular choices that seem to contradict the expected value criterion, such as occur in the contexts of gambling and insurance.

In probability theory and statistics, a scale parameter is a special kind of numerical parameter of a parametric family of probability distributions. The larger the scale parameter, the more spread out the distribution.

Stochastic dominance is a partial order between random variables. It is a form of stochastic ordering. The concept arises in decision theory and decision analysis in situations where one gamble can be ranked as superior to another gamble for a broad class of decision-makers. It is based on shared preferences regarding sets of possible outcomes and their associated probabilities. Only limited knowledge of preferences is required for determining dominance. Risk aversion is a factor only in second order stochastic dominance.

Cumulative prospect theory concept in behavioral economics

Cumulative prospect theory (CPT) is a model for descriptive decisions under risk and uncertainty which was introduced by Amos Tversky and Daniel Kahneman in 1992. It is a further development and variant of prospect theory. The difference between this version and the original version of prospect theory is that weighting is applied to the cumulative probability distribution function, as in rank-dependent expected utility theory but not applied to the probabilities of individual outcomes. In 2002, Daniel Kahneman received the Bank of Sweden Prize in Economic Sciences in Memory of Alfred Nobel for his contributions to behavioral economics, in particular the development of Cumulative Prospect Theory (CPT).

In statistics, an exchangeable sequence of random variables is a sequence X₁, X₂, X₃, ... whose joint probability distribution does not change when the positions in the sequence in which finitely many of them appear are altered. Thus, for example the sequences

In statistics, the monotone likelihood ratio property is a property of the ratio of two probability density functions (PDFs). Formally, distributions ƒ(x) and g(x) bear the property if

In probability theory and statistics, a stochastic order quantifies the concept of one random variable being "bigger" than another. These are usually partial orders, so that one random variable $may be neither stochastically greater than, less than nor equal to another random variable . Many different orders exist, which have different applications.$

In probability theory and statistics, the Poisson distribution, named after French mathematician Siméon Denis Poisson, is a discrete probability distribution that expresses the probability of a given number of events occurring in a fixed interval of time or space if these events occur with a known constant mean rate and independently of the time since the last event. The Poisson distribution can also be used for the number of events in other specified intervals such as distance, area or volume.

In probability theory, a Cauchy process is a type of stochastic process. There are symmetric and asymmetric forms of the Cauchy process. The unspecified term "Cauchy process" is often used to refer to the symmetric Cauchy process.

In probability, statistics and related fields, a Poisson point process is a type of random mathematical object that consists of points randomly located on a mathematical space. The Poisson point process is often called simply the Poisson process, but it is also called a Poisson random measure, Poisson random point field or Poisson point field. This point process has convenient mathematical properties, which has led to it being frequently defined in Euclidean space and used as a mathematical model for seemingly random processes in numerous disciplines such as astronomy, biology, ecology, geology, seismology, physics, economics, image processing, and telecommunications.

In the mathematical theory of probability, the Wiener process, named after Norbert Wiener, is a stochastic process used in modeling various phenomena, including Brownian motion and fluctuations in financial markets. A formula for the conditional probability distribution of the extremum of the Wiener process and a sketch of its proof appears in work of H. J. Kusher published in 1964. a detailed constructive proof appears in work of Dario Ballabio in 1978. This result was developed within a research project about Bayesian optimization algorithms.

References

↑ Rothschild, Michael; Stiglitz, Joseph (1970). "Increasing risk I: A definition". Journal of Economic Theory . 2 (3): 225–243. doi:10.1016/0022-0531(70)90038-4.
↑ Landsberger, M.; Meilijson, I. (1993). "Mean-preserving portfolio dominance". Review of Economic Studies . 60 (2): 479–485. doi:10.2307/2298068. JSTOR 2298068.

Mas-Colell, A.; Whinston, M. D.; Green, J. R. (1995). Microeconomic Theory. New York: Oxford University Press. pp. 197–199. ISBN 0-19-510268-1 – via Google Books.

This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.

[1] Rothschild, Michael; Stiglitz, Joseph (1970). "Increasing risk I: A definition". Journal of Economic Theory . 2 (3): 225–243. doi:10.1016/0022-0531(70)90038-4.

[2] Landsberger, M.; Meilijson, I. (1993). "Mean-preserving portfolio dominance". Review of Economic Studies . 60 (2): 479–485. doi:10.2307/2298068. JSTOR 2298068.