Portal:Physics/Selected article/Week 17, 2007

Template:Probability distribution In probability theory and statistics, the normal-gamma distribution (or Gaussian-gamma distribution) is a bivariate four-parameter family of continuous probability distributions. It is the conjugate prior of a normal distribution with unknown mean and precision.

Definition

For a pair of random variable, (X,T), suppose that the conditional distribution of X given T is given by

$X|T\sim N(\mu ,1/(\lambda T)),$

meaning that the condition distribution is a normal distribution with mean $\mu$ and precision $\lambda T$ — equivalently, with variance $1/(\lambda T).$

Suppose also that the marginal distribution of T is given by

$T|\alpha ,\beta \sim \mathrm{G}\mathrm{a}\mathrm{m}\mathrm{m}\mathrm{a}(\alpha ,\beta ),$

where this means that T has a gamma distribution. Here λ, α and β are parameters of the joint distribution.

Then (X,T) has a normal-gamma distribution, and this is denoted by

$(X,T)\sim \mathrm{N}\mathrm{o}\mathrm{r}\mathrm{m}\mathrm{a}\mathrm{l}\mathrm{G}\mathrm{a}\mathrm{m}\mathrm{m}\mathrm{a}(\mu ,\lambda ,\alpha ,\beta ).$

Properties

Probability density function

The joint probability density function of (X,T) isTemplate:Cn

$f(x,\tau |\mu ,\lambda ,\alpha ,\beta )=\frac{{\beta }^{\alpha }\sqrt{\lambda }}{\Gamma (\alpha )\sqrt{2\pi }}{\tau }^{\alpha -\frac{1}{2}}{e}^{-\beta \tau }{e}^{-\frac{\lambda \tau (x-\mu {)}^2}{2}}$

Marginal distributions

By construction, the marginal distribution over $\tau$ is a gamma distribution, and the conditional distribution over $x$ given $\tau$ is a Gaussian distribution. The marginal distribution over $x$ is a three-parameter non-standardized Student's t-distribution with parameters $(\nu ,\mu ,{\sigma }^2)=(2\alpha ,\mu ,\beta /(\lambda \alpha ))$.Template:Cn

Exponential family

The normal-gamma distribution is a four-parameter exponential family with natural parameters $\alpha -1/2,-\beta -\lambda {\mu }^2/2,\lambda \mu ,-\lambda /2$ and natural statistics $\ln \tau ,\tau ,\tau x,\tau x^2$.Template:Cn

Moments of the natural statistics

The following moments can be easily computed using the moment generating function of the sufficient statistic:Template:Cn

$\mathrm{E}(\ln T)=\psi \left(\alpha \right)-\ln \beta$, where $\psi \left(\alpha \right)$ is the digamma function,

$\mathrm{E}(T)=\frac{\alpha }{\beta }$,

$\mathrm{E}(TX)=\mu \frac{\alpha }{\beta }$,

$\mathrm{E}(T{X}^2)=\frac{1}{\lambda }+{\mu }^2\frac{\alpha }{\beta }$.

Scaling

If $(X,T)\sim \mathrm{N}\mathrm{o}\mathrm{r}\mathrm{m}\mathrm{a}\mathrm{l}\mathrm{G}\mathrm{a}\mathrm{m}\mathrm{m}\mathrm{a}(\mu ,\lambda ,\alpha ,\beta ),$ then for any b > 0, (bX,bT) is distributed asTemplate:Cn $\mathrm{N}\mathrm{o}\mathrm{r}\mathrm{m}\mathrm{a}\mathrm{l}\mathrm{G}\mathrm{a}\mathrm{m}\mathrm{m}\mathrm{a}(b\mu ,\lambda ,\alpha ,b^2\beta ).$To succeed in selling a home, it is advisable be competent in real estate advertising and marketing, authorized, monetary, operational aspects, and other information and skills. This is essential as a result of you want to negotiate with more and more sophisticated buyers. You could outperform rivals, use latest technologies, and stay ahead of the fast altering market.

Home is where the center is, and choosing the right house is a part of guaranteeing a contented expertise in Singapore. Most expats sign up for a two-year lease with the option to resume, so it is value taking the time to choose a neighbourhood that has the services you want. The experts at Expat Realtor have compiled the next data that will help you negotiate your means by way of the property minefield. Some government state properties for rent. Over 2000 units available for lease however occupancy is often excessive. Some properties come under a bidding system. Their property brokers embody DTZ and United Premas. Up to date serviced residences located just off Orchard Highway. one hundred sixty Orchard Highway, #06-01 Orchard Level, Singapore 238842. Institute Of Property Agents

There is no such thing as a deal too small. Property agents who're willing to find time for any deal even when the commission is small are those you want in your side. They also show humbleness and might relate with the average Singaporean higher. Relentlessly pursuing any deal, calling prospects even without being prompted. Even when they get rejected a hundred times, they still come back for more. These are the property brokers who will find consumers what they want finally, and who would be the most profitable in what they do. four. Honesty and Integrity

As a realtor, you're our own business. Due to this fact, it is imperative that you handle yours prices and spend money correctly in order to market your property successfully. Also, beware of mentors who always ask you to pay for pointless costs. Such mentors typically are recruiting to develop a staff and see you as a option to defray advertising and marketing prices. For foreigners who want to register with CEA as salespersons, they might want to have a valid Employment Cross (EP) issued by the Ministry of Manpower (MOM). They should consult an property agent that is ready to assist their future registration software, who would then examine with CEA. Thereafter, after they register for the RES Course, they might want to produce a letter of assist from the property agent."

Main Real Property Brokers with in depth local knowledge, Carole Ann, Elizabeth and their group of extremely skilled property consultants provide a personalised service, for those looking to buy, lease or promote in Singapore. Relocation companies out there. Properties for the aesthete. Boutique real property agency for architecturally distinguished, unique properties for rent and on the market. Caters to the niche market of design-savvy people. Sale, letting and property management and taxation services. three Shenton Means, #10-08 Shenton Home, Singapore 068805. Buy property, promote or leasing estate company. 430 Lorong 6 Toa Payoh, #08-01 OrangeTee Constructing, Singapore 319402. HIGH Date / Age of property Estate Agents and Home Search Services Property Information Highlights Prime Achievers

From the above info, you may see that saving on agent's commission will not cover the expenses wanted to market your home efficiently. As well as, it's essential make investments a whole lot of time, vitality and effort. By taking yourself away from your work and other endeavors, additionally, you will incur unnecessary opportunity prices. There may be additionally no assurance you could beat the market and get the outcomes you need. That is why you want an agent - not simply an ordinary agent - you want knowledgeable and competent specialist, geared up with the best instruments and knowledge to serve you and lead you to success! Within the midst of this ‘uniquely Singapore' Property GSS, our most needed foreign customers are nowhere to be seen. Different types of Public Residential properties

Based on Kelvin, other agents may also make use of your agent's listings. "If your pricing is on the excessive aspect, these brokers may use your house to persuade their patrons why Http://Trafficstooges.Com/Singapore-Property-Condominium they should purchase another residence." To counter this, Kelvin says it is crucial for your agent to supply a current market analysis before putting up your private home for sale. "This helps you worth your property appropriately and realistically." When property is made accessible (HIGH is issued) to the client. Becoming a successful property agent is a distinct story altogether! Hi, I would like to ask how I might be a property agent and whether there are courses I might take. And if I need to be at a certain age. www. Property BUYER com.sg (your impartial Mortgage Advisor) In private properties in

Posterior distribution of the parameters

Assume that x is distributed according to a normal distribution with unknown mean $\mu$ and precision $\tau$.

$x\sim 𝒩(\mu ,{\tau }^{-1})$

and that the prior distribution on $\mu$ and $\tau$, $(\mu ,\tau )$, has a normal-gamma distribution

$(\mu ,\tau )\sim \text{NormalGamma}({\mu }_0,{\lambda }_0,{\alpha }_0,{\beta }_0),$

for which the density π satisfies

$\pi (\mu ,\tau )\propto {\tau }^{{\alpha }_0-\frac{1}{2}}\exp [-{\beta }_0\tau ]\exp [-\frac{{\lambda }_0\tau (\mu -{\mu }_0{)}^2}{2}].$

Given a dataset $𝐗$, consisting of $n$ independent and identically distributed random_variables (i.i.d), $\{x_1,\mathrm{...},x_n\}$, the posterior distribution of $\mu$ and $\tau$ given this dataset can be analytically determined by Bayes' theorem. Explicitly,Template:Cn

$𝐏(\tau ,\mu |𝐗)\propto 𝐋(𝐗|\tau ,\mu )\pi (\tau ,\mu )$,

where $𝐋$ is the likelihood of the data given the parameters.

Since the data are i.i.d, the likelihood of the entire dataset is equal to the product of the likelihoods of the individual data samples:

$𝐋(𝐗|\tau ,\mu )=\prod _{i=1}^n𝐋(x_i|\tau ,\mu ).$

This expression can be simplified as follows:

$\begin{array}{cc}𝐋(𝐗|\tau ,\mu )& \propto \prod _{i=1}^n{\tau }^{1/2}\exp [\frac{-\tau }{2}(x_i-\mu {)}^2]\\ & \propto {\tau }^{n/2}\exp [\frac{-\tau }{2}\sum _{i=1}^n(x_i-\mu {)}^2]\\ & \propto {\tau }^{n/2}\exp [\frac{-\tau }{2}\sum _{i=1}^n(x_i-\overline{x}+\overline{x}-\mu {)}^2]\\ & \propto {\tau }^{n/2}\exp [\frac{-\tau }{2}\sum _{i=1}^n((x_i-\overline{x}{)}^2+(\overline{x}-\mu {)}^2)]\\ & \propto {\tau }^{n/2}\exp [\frac{-\tau }{2}(ns+n(\overline{x}-\mu {)}^2)],\end{array}$

where $\overline{x}=\frac{1}{n}\sum _{i=1}^n{x}_i$, the mean of the data samples, and $s=\frac{1}{n}\sum _{i=1}^n(x_i-\overline{x}{)}^2$, the sample variance.

The posterior distribution of the parameters is proportional to the prior times the likelihood.

$\begin{array}{cc}𝐏(\tau ,\mu |𝐗)& \propto 𝐋(𝐗|\tau ,\mu )\pi (\tau ,\mu )\\ & \propto {\tau }^{n/2}\exp [\frac{-\tau }{2}(ns+n(\overline{x}-\mu {)}^2)]{\tau }^{{\alpha }_0-\frac{1}{2}}\exp [-{\beta }_0\tau ]\exp [-\frac{{\lambda }_0\tau (\mu -{\mu }_0{)}^2}{2}]\\ & \propto {\tau }^{\frac{n}{2}+{\alpha }_0-\frac{1}{2}}\exp [-\tau (\frac{1}{2}ns+{\beta }_0)]\exp [-\frac{\tau }{2}({\lambda }_0(\mu -{\mu }_0{)}^2+n(\overline{x}-\mu {)}^2)]\\ \end{array}$

The final exponential term is simplified by completing the square.

$\begin{array}{cc}{\lambda }_0(\mu -{\mu }_0{)}^2+n(\overline{x}-\mu {)}^2& ={\lambda }_0{\mu }^2-2{\lambda }_0\mu {\mu }_0+{\lambda }_0{\mu }_0^2+n{\mu }^2-2n\overline{x}\mu +n{\overline{x}}^2\\ & =({\lambda }_0+n){\mu }^2-2({\lambda }_0{\mu }_0+n\overline{x})\mu +{\lambda }_0{\mu }_0^2+n{\overline{x}}^2\\ & =({\lambda }_0+n)({\mu }^2-2\frac{{\lambda }_0{\mu }_0+n\overline{x}}{{\lambda }_0+n}\mu )+{\lambda }_0{\mu }_0^2+n{\overline{x}}^2\\ & =({\lambda }_0+n){(\mu -\frac{{\lambda }_0{\mu }_0+n\overline{x}}{{\lambda }_0+n})}^2+{\lambda }_0{\mu }_0^2+n{\overline{x}}^2-\frac{{({\lambda }_0{\mu }_0+n\overline{x})}^2}{{\lambda }_0+n}\\ & =({\lambda }_0+n){(\mu -\frac{{\lambda }_0{\mu }_0+n\overline{x}}{{\lambda }_0+n})}^2+\frac{{\lambda }_{0}n(\overline{x}-{\mu }_0{)}^2}{{\lambda }_0+n}\end{array}$

On inserting this back into the expression above,

$\begin{array}{cc}𝐏(\tau ,\mu |𝐗)& \propto {\tau }^{\frac{n}{2}+{\alpha }_0-\frac{1}{2}}\exp [-\tau (\frac{1}{2}ns+{\beta }_0)]\exp [-\frac{\tau }{2}(({\lambda }_0+n){(\mu -\frac{{\lambda }_0{\mu }_0+n\overline{x}}{{\lambda }_0+n})}^2+\frac{{\lambda }_{0}n(\overline{x}-{\mu }_0{)}^2}{{\lambda }_0+n})]\\ & \propto {\tau }^{\frac{n}{2}+{\alpha }_0-\frac{1}{2}}\exp [-\tau (\frac{1}{2}ns+{\beta }_0+\frac{{\lambda }_{0}n(x-{\mu }_0{)}^2}{2({\lambda }_0+n)})]\exp [-\frac{\tau }{2}({\lambda }_0+n){(\mu -\frac{{\lambda }_0{\mu }_0+n\overline{x}}{{\lambda }_0+n})}^2]\end{array}$

This final expression is in exactly the same form as a Normal-Gamma distribution, i.e.,

$𝐏(\tau ,\mu |𝐗)=\text{NormalGamma}(\frac{{\lambda }_0{\mu }_0+n\overline{x}}{{\lambda }_0+n},{\lambda }_0+n,{\alpha }_0+\frac{n}{2},{\beta }_0+\frac{1}{2}(ns+\frac{{\lambda }_{0}n(\overline{x}-{\mu }_0{)}^2}{{\lambda }_0+n}))$

Interpretation of parameters

The interpretation of parameters in terms of pseudo-observations is as follows:

• The new mean takes a weighted average of the old pseudo-mean and the observed mean, weighted by the number of associated (pseudo-)observations.
• The precision was estimated from $2\alpha$ pseudo-observations (i.e. possibly a different number of pseudo-observations, to allow the variance of the mean and precision to be controlled separately) with sample mean $\mu$ and sample variance $\frac{\beta }{\alpha }$ (i.e. with sum of squared deviations $2\beta$).
• The posterior updates the number of pseudo-observations (${\lambda }_0$) simply by adding up the corresponding number of new observations ($n$).
• The new sum of squared deviations is computed by adding the previous respective sums of squared deviations. However, a third "interaction term" is needed because the two sets of squared deviations were computed with respect to different means, and hence the sum of the two underestimates the actual total squared deviation.

As a consequence, if one has a prior mean of ${\mu }_0$ from $n_{\mu }$ samples and a prior precision of ${\tau }_0$ from $n_{\tau }$ samples, the prior distribution over $\mu$ and $\tau$ is

$𝐏(\tau ,\mu |𝐗)=\text{NormalGamma}({\mu }_0,n_{\mu },\frac{n_{\tau }}{2},\frac{n_{\tau }}{2{\tau }_0})$

and after observing $n$ samples with mean $\mu$ and variance $s$, the posterior probability is

$𝐏(\tau ,\mu |𝐗)=\text{NormalGamma}(\frac{n_{\mu }{\mu }_0+n\mu }{n_{\mu }+n},n_{\mu }+n,\frac{1}{2}(n_{\tau }+n),\frac{1}{2}(\frac{n_{\tau }}{{\tau }_0}+ns+\frac{n_{\mu }n(\mu -{\mu }_0{)}^2}{n_{\mu }+n}))$

Note that in some programming languages, such as Matlab, the gamma distribution is implemented with the inverse definition of $\beta$, so the fourth argument of the Normal-Gamma distribution is $2{\tau }_0/n_{\tau }$.

Generating normal-gamma random variates

Generation of random variates is straightforward:

1. Sample $\tau$ from a gamma distribution with parameters $\alpha$ and $\beta$
2. Sample $x$ from a normal distribution with mean $\mu$ and variance $1/(\lambda \tau )$

Related distributions

• The normal-inverse-gamma distribution is essentially the same distribution parameterized by variance rather than precision
• The normal-exponential-gamma distribution

Notes

43 year old Petroleum Engineer Harry from Deep River, usually spends time with hobbies and interests like renting movies, property developers in singapore new condominium and vehicle racing. Constantly enjoys going to destinations like Camino Real de Tierra Adentro.

References

• Bernardo, J.M.; Smith, A.F.M. (1993) Bayesian Theory, Wiley. ISBN 0-471-49464-X
• Dearden et al. "Bayesian Q-learning", Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98), July 26–30, 1998, Madison, Wisconsin, USA.

55 yrs old Metal Polisher Records from Gypsumville, has interests which include owning an antique car, summoners war hack and spelunkering. Gets immense motivation from life by going to places such as Villa Adriana (Tivoli).

my web site - summoners war hack no survey ios