Back

ⓘ Normal variance-mean mixture. In probability theory and statistics, a normal variance-mean mixture with mixing probability density g {\displaystyle g} is the co ..




                                     

ⓘ Normal variance-mean mixture

In probability theory and statistics, a normal variance-mean mixture with mixing probability density g {\displaystyle g} is the continuous probability distribution of a random variable Y {\displaystyle Y} of the form

Y = α + β V + σ V X, {\displaystyle Y=\alpha +\beta V+\sigma {\sqrt {V}}X,}

where α {\displaystyle \alpha }, β {\displaystyle \beta } and σ > 0 {\displaystyle \sigma > 0} are real numbers, and random variables X {\displaystyle X} and V {\displaystyle V} are independent, X {\displaystyle X} is normally distributed with mean zero and variance one, and V {\displaystyle V} is continuously distributed on the positive half-axis with probability density function g {\displaystyle g}. The conditional distribution of Y {\displaystyle Y} given V {\displaystyle V} is thus a normal distribution with mean α + β V {\displaystyle \alpha +\beta V} and variance σ 2 V {\displaystyle \sigma ^{2}V}. A normal variance-mean mixture can be thought of as the distribution of a certain quantity in an inhomogeneous population consisting of many different normal distributed subpopulations. It is the distribution of the position of a Wiener process Brownian motion with drift β {\displaystyle \beta } and infinitesimal variance σ 2 {\displaystyle \sigma ^{2}} observed at a random time point independent of the Wiener process and with probability density function g {\displaystyle g}. An important example of normal variance-mean mixtures is the generalised hyperbolic distribution in which the mixing distribution is the generalized inverse Gaussian distribution.

The probability density function of a normal variance-mean mixture with mixing probability density g {\displaystyle g} is

f x = ∫ 0 ∞ 1 2 π σ 2 v exp ⁡ − x − α − β v 2 σ 2 v) g v d v {\displaystyle fx=\int _{0}^{\infty }{\frac {1}{\sqrt {2\pi \sigma ^{2}v}}}\exp \left{\frac {-x-\alpha -\beta v^{2}}{2\sigma ^{2}v}}\right)gv\,dv}

and its moment generating function is

M s = exp ⁡ α s M g β s + 1 2 σ 2 s 2, {\displaystyle Ms=\exp\alpha s\,M_{g}\left\beta s+{\frac {1}{2}}\sigma ^{2}s^{2}\right,}

where M g {\displaystyle M_{g}} is the moment generating function of the probability distribution with density function g {\displaystyle g}, i.e.

M g s = E exp ⁡ s V) = ∫ 0 ∞ exp ⁡ s v g v d v. {\displaystyle M_{g}s=E\left\expsV\right)=\int _{0}^{\infty }\expsvgv\,dv.}
                                     
  • distribution is conjugate to the normal distribution when serving as the mixing distribution in a normal variance - mean mixture Let the prior distribution
  • mean distributed according to another Gaussian distribution yields again a Gaussian distribution. Compounding a normal distribution with variance distributed
  • root of the variance is useful because for a wrapped normal distribution, it is an estimator of the standard deviation of the underlying normal distribution
  • population mean The assumptions underlying a t - test in its simplest form are that X follows a normal distribution with mean μ and variance σ2 n s2 follows
  • Josephson et al. limited themselves to considering two normal mixtures with the same component variances and mixing proportions. As a consequence, their proposal
  • the mean When estimating a scale parameter, using a trimmed estimator as a robust measures of scale, such as to estimate the population variance or population
  • finite - variance assumptions, an extension of Cochran s theorem on the distribution of quadratic forms holds. An elliptical distribution with a zero mean and
  • minimum - variance mean for large normal samples which is to say the variance of the median will be 50 greater than the variance of the mean - see asymptotic
  • of the variance This transformation may result in better estimates particularly when the distribution of the variance itself may be non normal For many
  • outliers and not the configuration of data near the mean The kurtosis of any univariate normal distribution is 3. It is common to compare the kurtosis

Users also searched:

...
...
...