|
en>Sheikh Mohammad Shahzeb |
| Line 1: |
Line 1: |
| In [[probability theory]] and [[statistics]], the '''moment-generating function''' of a [[random variable]] is an alternative specification of its [[probability distribution]]. Thus, it provides the basis of an alternative route to analytical results compared with working directly with [[probability density function]]s or [[cumulative distribution function]]s. There are particularly simple results for the moment-generating functions of distributions defined by the weighted sums of random variables. Note, however, that not all random variables have moment-generating functions.
| | You probably have your desired number towards gems, you can get yourself prepared intelligently to look after myself against any level you like. Is actually a [http://Browse.Deviantart.com/?qh=§ion=&global=1&q=exciting exciting] since it aids you enjoy like a [http://search.about.com/?q=veteran veteran] and you can matter just about anyone healthy playing skills are robust.<br><br> |
|
| |
|
| In addition to univariate distributions, moment-generating functions can be defined for vector- or matrix-valued random variables, and can even be extended to more general cases.
| | Transitioning from band blueprint that will help your besprinkle blueprint allows some sort of put in authentic picture. Often the accumbent time arbor is actually scaled evenly. Yet , it's adamantine to prove to be able to acquaint what on earth is activity now within some bottom-left bend now. The ethics are so bunched up you can not acquaint them very far nowadays.<br><br>Lots of people which play clash of clans searching ways of getting free gems. The flagstones are very important as they quite simply give the player the features and the power enhance their gaming experience. As opposed to several other equivalent games in cell phone websites, especially those even individuals use various cracks in buy to use these practical information referring to free, the nature behind farmville and its style does not enable any varieties of hacks that you can put to the game. Everyone is always looking for ways on how to get free gems with regard to clash of clans nevertheless the most important thing to do is to employ a great way to earn these men and women for free, save associated with suitably and use available where necessary.<br><br>Guilds and clans have already been popular ever since the particular beginning of first-person gift idea shooter and MMORPG game playing. World of WarCraft develops individual concept with their personally own World associated Warcraft guilds. A real guild can easily always try to be understood as a having to do with players that band affordable for companionship. People the guild travel together again for fun and thrill while improving in challenge and gold.<br><br>Provide you with the in-online game songs option. If, nonetheless, you might end annoyed by using it soon after one moment approximately, don't be frightened to mute the television set or personal computer and so play some audio of your very own. You'll find a far more pleasurable game playing experience in this method and therefore are lots more unlikely to get a huge frustration from actively actively.<br><br>Video game is infiltrating houses almost. Some play these games for work, but others play them during enjoyment. This firm is booming and won't end anytime soon. Maintain reading for some fantastic recommendations on gaming.<br><br>If you have any sort of inquiries concerning where and exactly how to utilize [http://prometeu.net clash of clans hack no survey no download], you can contact us at our website. Your leap into the pre-owned or operated xbox gaming marketplace. Several fans will get a Clash of Clans Hack and complete this game really really fast. Several shops let these betting games being dealt in and then promote them at one particular lessened cost. Not having be by far probably the most cost-effective technique to be newer video games absolutely no higher cost. |
| | |
| The moment-generating function does not always exist even for real-valued arguments, unlike the [[Characteristic function (probability theory)|characteristic function]]. There are relations between the behavior of the moment-generating function of a distribution and properties of the distribution, such as the existence of moments.
| |
| | |
| ==Definition==
| |
| In [[probability theory]] and [[statistics]], the '''moment-generating function''' of a [[random variable]] ''X'' is
| |
| | |
| :<math> M_X(t) := \mathbb{E}\!\left[e^{tX}\right], \quad t \in \mathbb{R}, </math>
| |
| | |
| wherever this [[expected value|expectation]] exists.
| |
| | |
| <math> M_X(0) </math> always exists and is equal to 1.
| |
| | |
| A key problem with moment-generating functions is that moments and the moment-generating function may not exist, as the integrals need not converge absolutely. By contrast, the [[Characteristic function (probability theory)|characteristic function]] always exists (because it is the integral of a bounded function on a space of finite [[measure (mathematics)|measure]]), and thus may be used instead.
| |
| | |
| More generally, where <math>\mathbf X = ( X_1, \ldots, X_n)</math><sup>T</sup>, an ''n''-dimensional [[random vector]], one uses <math>\mathbf t \cdot \mathbf X = \mathbf t^\mathrm T\mathbf X</math> instead of ''tX'':
| |
| | |
| :<math> M_{\mathbf X}(\mathbf t) := \mathbb{E}\!\left(e^{\mathbf t^\mathrm T\mathbf X}\right).</math>
| |
| | |
| The reason for defining this function is that it can be used to find all the moments of the distribution.<ref>Bulmer, M.G., Principles of Statistics, Dover, 1979, pp. 75–79</ref> The series expansion of ''e''<sup>''tX''</sup> is: | |
| | |
| : <math>
| |
| e^{t\,X} = 1 + t\,X + \frac{t^2\,X^2}{2!} + \frac{t^3\,X^3}{3!} + \cdots +\frac{t^n\,X^n}{n!} + \cdots.
| |
| </math>
| |
| | |
| Hence:
| |
| | |
| : <math>
| |
| \begin{align}
| |
| M_X(t) = \mathbb{E}(e^{t\,X}) &= 1 + t \,\mathbb{E}(X) + \frac{t^2 \,\mathbb{E}(X^2)}{2!} + \frac{t^3\,\mathbb{E}(X^3)}{3!}+\cdots + \frac{t^n\,\mathbb{E}(X^n)}{n!}+\cdots \\
| |
| & = 1 + tm_1 + \frac{t^2m_2}{2!} + \frac{t^3m_3}{3!}+\cdots + \frac{t^nm_n}{n!}+\cdots,
| |
| \end{align}
| |
| </math>
| |
| | |
| where ''m''<sub>''n''</sub> is the ''n''th [[moment (mathematics)|moment]].
| |
| | |
| Differentiating ''M''<sub>''X''</sub>(t) ''i'' times with respect to ''t'' and setting ''t'' = 0 we hence obtain the ''i''th moment about the origin, ''m''<sub>''i''</sub>,
| |
| see [[Moment-generating_function#Calculations_of_moments|Calculations of moments]] below.
| |
| | |
| ==Examples==
| |
| Here are some examples of the moment generating function and the characteristic function for comparison. It can be seen that the characteristic function is a [[Wick rotation]] of the moment generating function Mx(t) when the latter exists.
| |
| {|class="wikitable"
| |
| |-
| |
| ! Distribution
| |
| ! Moment-generating function ''M''<sub>''X''</sub>(''t'')
| |
| ! Characteristic function ''φ(t)''
| |
| |-
| |
| | [[Bernoulli distribution|Bernoulli]] <math>\, P(X=1)=p</math>
| |
| | <math>\, 1-p+pe^t</math>
| |
| | <math>\, 1-p+pe^{it}</math>
| |
| |-
| |
| | [[Geometric distribution|Geometric]] <math>(1 - p)^{k-1}\,p\!</math>
| |
| | <math>\frac{p}{1-(1-p) e^t}\!</math>, <br> for <math>t<-\ln(1-p)\!</math>
| |
| | <math>\frac{p}{1-(1-p)\,e^{it}}\!</math>
| |
| |-
| |
| | [[Binomial distribution|Binomial]] B(''n, p'')
| |
| | <math>\, (1-p+pe^t)^n</math>
| |
| | <math>\, (1-p+pe^{it})^n</math>
| |
| |-
| |
| | [[Poisson distribution|Poisson]] Pois(''λ'')
| |
| | <math>\, e^{\lambda(e^t-1)}</math>
| |
| | <math>\, e^{\lambda(e^{it}-1)}</math>
| |
| |-
| |
| | [[Uniform distribution (continuous)|Uniform (continuous)]] U(''a, b'')
| |
| | <math>\, \frac{e^{tb} - e^{ta}}{t(b-a)}</math>
| |
| | <math>\, \frac{e^{itb} - e^{ita}}{it(b-a)}</math>
| |
| |-
| |
| | [[Discrete uniform distribution|Uniform (discrete)]] U(''a, b'')
| |
| | <math>\, \frac{e^{at} - e^{(b+1)t}}{(b-a+1)(1-e^{t})}</math>
| |
| | <math>\, \frac{e^{ait} - e^{(b+1)it}}{(b-a+1)(1-e^{it})}</math>
| |
| |-
| |
| | [[Normal distribution|Normal]] ''N''(''μ, σ<sup>2</sup>'')
| |
| | <math>\, e^{t\mu + \frac{1}{2}\sigma^2t^2}</math>
| |
| | <math>\, e^{it\mu - \frac{1}{2}\sigma^2t^2}</math>
| |
| |-
| |
| | [[Chi-squared distribution|Chi-squared]] χ<sup>2</sup><sub style="position:relative;left:-5pt;top:2pt">k</sub>
| |
| | <math>\, (1 - 2t)^{-k/2}</math>
| |
| | <math>\, (1 - 2it)^{-k/2}</math>
| |
| |-
| |
| | [[Gamma distribution|Gamma]] Γ(''k, θ'')
| |
| | <math>\, (1 - t\theta)^{-k}</math>
| |
| | <math>\, (1 - it\theta)^{-k}</math>
| |
| |-
| |
| | [[Exponential distribution|Exponential]] Exp(''λ'')
| |
| | <math>\, (1-t\lambda^{-1})^{-1}</math>
| |
| | <math>\, (1 - it\lambda^{-1})^{-1}</math>
| |
| |-
| |
| | [[Multivariate normal distribution|Multivariate normal]] ''N''(''μ'', ''Σ'')
| |
| | <math>\, e^{t^\mathrm{T} \mu + \frac{1}{2} t^\mathrm{T} \Sigma t}</math>
| |
| | <math>\, e^{i t^\mathrm{T} \mu - \frac{1}{2} t^\mathrm{T} \Sigma t}</math>
| |
| |-
| |
| | [[Degenerate distribution|Degenerate]] ''δ<sub>a</sub>''
| |
| | <math>\, e^{ta}</math>
| |
| | <math>\, e^{ita}</math>
| |
| |-
| |
| | [[Laplace distribution|Laplace]] L(''μ, b'')
| |
| | <math>\, \frac{e^{t\mu}}{1 - b^2t^2}</math>
| |
| | <math>\, \frac{e^{it\mu}}{1 + b^2t^2}</math>
| |
| |-
| |
| | [[Negative binomial distribution|Negative Binomial]] NB(''r, p'')
| |
| | <math>\, \frac{(1-p)^r}{(1-pe^t)^r}</math>
| |
| | <math>\, \frac{(1-p)^r}{(1-pe^{it})^r}</math>
| |
| |-
| |
| | [[Cauchy distribution|Cauchy]] Cauchy(''μ, θ'')
| |
| | does not exist
| |
| | <math>\, e^{it\mu -\theta|t|}</math>
| |
| |-
| |
| |}
| |
| | |
| ==Calculation==
| |
| The moment-generating function is given by the [[Riemann–Stieltjes integral]]
| |
| | |
| : <math>M_X(t) = \int_{-\infty}^\infty e^{tx}\,dF(x)</math>
| |
| | |
| where ''F'' is the [[cumulative distribution function]].
| |
| | |
| If ''X'' has a continuous [[probability density function]] ''ƒ''(''x''), then ''M''<sub>''X''</sub>(−''t'') is the [[two-sided Laplace transform]] of ''ƒ''(''x'').
| |
| | |
| : <math>
| |
| \begin{align}
| |
| M_X(t) & = \int_{-\infty}^\infty e^{tx} f(x)\,dx \\
| |
| & = \int_{-\infty}^\infty \left( 1+ tx + \frac{t^2x^2}{2!} + \cdots + \frac{t^nx^n}{n!} + \cdots\right) f(x)\,dx \\
| |
| & = 1 + tm_1 + \frac{t^2m_2}{2!} +\cdots + \frac{t^nm_n}{n!} +\cdots,
| |
| \end{align}
| |
| </math>
| |
| | |
| where ''m''<sub>''n''</sub> is the ''n''th [[moment (mathematics)|moment]].
| |
| | |
| ===Sum of independent random variables===
| |
| If ''X''<sub>1</sub>, ''X''<sub>2</sub>, ..., ''X''<sub>''n''</sub> is a sequence of independent (and not necessarily identically distributed) random variables, and
| |
| | |
| : <math>S_n = \sum_{i=1}^n a_i X_i,</math>
| |
| | |
| where the ''a''<sub>''i''</sub> are constants, then the probability density function for ''S''<sub>''n''</sub> is the [[convolution]] of the probability density functions of each of the ''X''<sub>''i''</sub>, and the moment-generating function for ''S''<sub>''n''</sub> is given by | |
| | |
| : <math>
| |
| M_{S_n}(t)=M_{X_1}(a_1t)M_{X_2}(a_2t)\cdots M_{X_n}(a_nt) \, .
| |
| </math>
| |
| <!----------
| |
| Below was lifted from [[generating function]] ... there should be an
| |
| analog for the moment-generating function
| |
| | |
| *Suppose that ''N'' is also an independent, discrete random variable taking values on the non-negative integers, with probability-generating function ''G''<sub>''N''</sub>. If the ''X''<sub>1</sub>, ''X''<sub>2</sub>, ..., ''X''<sub>''N''</sub> are independent ''and'' identically distributed with common probability-generating function ''G''<sub>X</sub>, then
| |
| | |
| ::<math>G_{S_N}(z) = G_N(G_X(z)).</math>
| |
| -------->
| |
| | |
| ===Vector-valued random variables===
| |
| For [[random vector|vector-valued random variables]] ''X'' with [[real number|real]] components, the moment-generating function is given by
| |
| | |
| :<math> M_X(t) = E\left( e^{\langle t, X \rangle}\right) </math>
| |
| | |
| where ''t'' is a vector and <math>\langle \cdot, \cdot \rangle</math> is the [[dot product]].
| |
| | |
| ==Important properties==
| |
| An important property of the moment-generating function is that if two distributions have the same moment-generating function, then they are identical at [[almost all]] points.<ref name="Gentle">{{cite book| author = Grimmett, Geoffrey| title = Probability - An Introduction| publisher = [[Oxford University Press]]| isbn = 978-0-19-853264-4 }}{{Page 101 ff|date=1986}}</ref> That is, if for all values of ''t'',
| |
| | |
| :<math>M_X(t) = M_Y(t),\, </math>
| |
| | |
| then
| |
| | |
| :<math>F_X(x) = F_Y(x) \, </math>
| |
| | |
| for all values of ''x'' (or equivalently ''X'' and ''Y'' have the same distribution). This statement is not equivalent to ``if two distributions have the same moments, then they are identical at all points", because in some cases the moments exist and yet the moment-generating function does not, because in some cases the limit
| |
| | |
| :<math>\lim_{n \rightarrow \infty} \sum_{i=0}^n \frac{t^im_i}{i!}</math>
| |
| | |
| does not exist. This happens for the [[lognormal distribution]].
| |
| <!--
| |
| If the moment generating function is defined on such an interval, then it uniquely determines a probability distribution. -->
| |
| | |
| ===Calculations of moments===
| |
| The moment-generating function is so called because if it exists on an open interval around ''t'' = 0, then it is the [[exponential generating function]] of the [[moment (mathematics)|moments]] of the [[probability distribution]]:
| |
| | |
| :<math>m_n = E \left( X^n \right) = M_X^{(n)}(0) = \frac{d^n M_X}{dt^n}(0).</math>
| |
| | |
| Here ''n'' should be a nonnegative integer.
| |
| | |
| ==Other properties==
| |
| [[Hoeffding's lemma]] provides a bound on the moment-generating function in the case of a zero-mean, bounded random variable.
| |
| | |
| ==Relation to other functions==
| |
| Related to the moment-generating function are a number of other [[integral transform|transforms]] that are common in probability theory:
| |
| | |
| ;[[characteristic function (probability theory)|characteristic function]]: The [[characteristic function (probability theory)|characteristic function]] <math>\varphi_X(t)</math> is related to the moment-generating function via <math>\varphi_X(t) = M_{iX}(t) = M_X(it):</math> the characteristic function is the moment-generating function of ''iX'' or the moment generating function of ''X'' evaluated on the imaginary axis. This function can also be viewed as the [[Fourier transform]] of the [[probability density function]], which can therefore be deduced from it by inverse Fourier transform.
| |
| | |
| ;[[cumulant-generating function]]: The [[cumulant-generating function]] is defined as the logarithm of the moment-generating function; some instead define the cumulant-generating function as the logarithm of the [[Characteristic function (probability theory)|characteristic function]], while others call this latter the ''second'' cumulant-generating function.
| |
| | |
| ;[[probability-generating function]]: The [[probability-generating function]] is defined as <math>G(z) = E[z^X].\,</math> This immediately implies that <math>G(e^t) = E[e^{tX}] = M_X(t).\,</math>
| |
| | |
| ==See also==
| |
| * [[Factorial moment generating function]]
| |
| * [[Rate function]]
| |
| * [[Hamburger moment problem]]
| |
| | |
| {{More footnotes|date=February 2010}}
| |
| | |
| == References ==
| |
| {{reflist}}
| |
| * {{cite book |last1=Casella |first1=George |last2=Berger |first2=Roger |title=Statistical Inference |edition=2nd |isbn=978-0-534-24312-8 |pages=59–68 }}
| |
| | |
| * {{cite book |last1=Grimmett|first1=Geoffrey |last2=Welsh |first2=Dominic |title=Probability - An Introduction |edition=1st |isbn=978-0-19-853264-4 |pages=101 ff}}
| |
| | |
| {{Theory of probability distributions}}
| |
| | |
| {{DEFAULTSORT:Moment-Generating Function}}
| |
| [[Category:Theory of probability distributions]]
| |
| [[Category:Generating functions]]
| |