Conjugate prior

The form of the conjugate prior can generally be determined by inspection of the probability density or probability mass function of a distribution. For example, consider a random variable which consists of the number of successes ${\displaystyle s}$ in ${\displaystyle n}$ Bernoulli trials with unknown probability of success ${\displaystyle q}$ in [0,1]. This random variable will follow the binomial distribution, with a probability mass function of the form

${\displaystyle p(s)={n \choose s}q^{s}(1-q)^{n-s}}$

The usual conjugate prior is the beta distribution with parameters (${\displaystyle \alpha }$, ${\displaystyle \beta }$):

${\displaystyle p(q)={q^{\alpha -1}(1-q)^{\beta -1} \over \mathrm {B} (\alpha ,\beta )}}$

where ${\displaystyle \alpha }$ and ${\displaystyle \beta }$ are chosen to reflect any existing belief or information (${\displaystyle \alpha }$ = 1 and ${\displaystyle \beta }$ = 1 would give a uniform distribution) and Β(${\displaystyle \alpha }$, ${\displaystyle \beta }$) is the Beta function acting as a normalising constant.

In this context, ${\displaystyle \alpha }$ and ${\displaystyle \beta }$ are called hyperparameters (parameters of the prior), to distinguish them from parameters of the underlying model (here q). It is a typical characteristic of conjugate priors that the dimensionality of the hyperparameters is one greater than that of the parameters of the original distribution. If all parameters are scalar values, then this means that there will be one more hyperparameter than parameter; but this also applies to vector-valued and matrix-valued parameters. (See the general article on the exponential family, and consider also the Wishart distribution, conjugate prior of the covariance matrix of a multivariate normal distribution, for an example where a large dimensionality is involved.)

If we then sample this random variable and get s successes and f failures, we have

${\displaystyle {\begin{aligned}P(s,f\mid q=x)&={s+f \choose s}x^{s}(1-x)^{f},\\P(q=x)&={x^{\alpha -1}(1-x)^{\beta -1} \over \mathrm {B} (\alpha ,\beta )},\\P(q=x\mid s,f)&={\frac {P(s,f\mid x)P(x)}{\int P(s,f\mid y)P(y)dy}}\\&={{{s+f \choose s}x^{s+\alpha -1}(1-x)^{f+\beta -1}/\mathrm {B} (\alpha ,\beta )} \over \int _{y=0}^{1}\left({s+f \choose s}y^{s+\alpha -1}(1-y)^{f+\beta -1}/\mathrm {B} (\alpha ,\beta )\right)dy}\\&={x^{s+\alpha -1}(1-x)^{f+\beta -1} \over \mathrm {B} (s+\alpha ,f+\beta )},\end{aligned}}}$

which is another Beta distribution with parameters (${\displaystyle \alpha }$ + s, ${\displaystyle \beta }$ + f). This posterior distribution could then be used as the prior for more samples, with the hyperparameters simply adding each extra piece of information as it comes.

It is often useful to think of the hyperparameters of a conjugate prior distribution as corresponding to having observed a certain number of pseudo-observations with properties specified by the parameters. For example, the values ${\displaystyle \alpha }$ and ${\displaystyle \beta }$ of a beta distribution can be thought of as corresponding to ${\displaystyle \alpha -1}$ successes and ${\displaystyle \beta -1}$ failures if the posterior mode is used to choose an optimal parameter setting, or ${\displaystyle \alpha }$ successes and ${\displaystyle \beta }$ failures if the posterior mean is used to choose an optimal parameter setting. In general, for nearly all conjugate prior distributions, the hyperparameters can be interpreted in terms of pseudo-observations. This can help both in providing an intuition behind the often messy update equations, as well as to help choose reasonable hyperparameters for a prior.

Suppose a rental car service operates in your city. Drivers can drop off and pick up cars anywhere inside the city limits. You can find and rent cars using an app.

Suppose you wish to find the probability that you can find a rental car within a short distance of your home address at any given time of day.

Over three days you look at the app at random times of the day and find the following number of cars within a short distance of your home address: ${\displaystyle \mathbf {x} =[3,4,1]}$

If we assume the data comes from a Poisson distribution, we can compute the maximum likelihood estimate of the parameters of the model which is ${\textstyle \lambda ={\frac {3+4+1}{3}}\approx 2.67.}$ Using this maximum likelihood estimate we can compute the probability that there will be at least one car available: ${\textstyle p(x>0)=1-p(x=0)=1-{\frac {2.67^{0}e^{-2.67}}{0!}}\approx 0.93}$

This is the Poisson distribution that is the most likely to have generated the observed data ${\displaystyle \mathbf {x} }$. But the data could also have come from another Poisson distribution, e.g. one with ${\displaystyle \lambda =3}$, or ${\displaystyle \lambda =2}$, etc. In fact there is an infinite number of poisson distributions that could have generated the observed data and with relatively few data points we should be quite uncertain about which exact poisson distribution generated this data. Intuitively we should instead take a weighted average of the probability of ${\displaystyle p(x>0)}$ for each of those Poisson distributions, weighted by how likely they each are, given the data we've observed ${\displaystyle \mathbf {x} }$.

Generally, this quantity is known as the posterior predictive distribution ${\displaystyle p(x|\mathbf {x} )=\int _{\theta }p(x|\theta )p(\theta |\mathbf {x} )d\theta \,,}$ where ${\displaystyle x}$ is a new data point, ${\displaystyle \mathbf {x} }$ is the observed data and ${\displaystyle \theta }$ are the parameters of the model. Using Bayes' theorem we can expand ${\displaystyle p(\theta |\mathbf {x} )={\frac {p(\mathbf {x} |\theta )p(\theta )}{p(\mathbf {x} )}}\,,}$ such that ${\displaystyle p(x|\mathbf {x} )=\int _{\theta }p(x|\theta ){\frac {p(\mathbf {x} |\theta )p(\theta )}{p(\mathbf {x} )}}d\theta \,.}$ Generally, this integral is hard to compute. However, if you choose a conjugate prior distribution ${\displaystyle p(\theta )}$, a closed form expression can be derived. This is the posterior predictive column in the tables below.

Returning to our example, if we pick the Gamma distribution as our prior distribution over the rate of the poisson distributions, then the posterior predictive is the negative binomial distribution as can be seen from the last column in the table below. The Gamma distribution is parameterized by two hyperparameters ${\displaystyle \alpha ,\beta }$ which we have to choose. By looking at plots of the gamma distribution we pick ${\displaystyle \alpha =\beta =2}$, which seems to be a reasonable prior for the average number of cars. The choice of prior hyperparameters is inherently subjective and based on prior knowledge.

Given the prior hyperparameters ${\displaystyle \alpha }$ and ${\displaystyle \beta }$ we can compute the posterior hyperparameters ${\textstyle \alpha '=\alpha +\sum _{i}x_{i}=2+3+4+1=10}$ and ${\textstyle \beta '=\beta +n=2+3=5}$

Given the posterior hyperparameters we can finally compute the posterior predictive of ${\textstyle p(x>0|\mathbf {x} )=1-p(x=0|\mathbf {x} )=1-NB\left(0\,|\,10,{\frac {1}{1+5}}\right)\approx 0.84}$

This much more conservative estimate reflect the uncertainty in the model parameters, which the posterior predictive takes into account.

Let n denote the number of observations. In all cases below, the data is assumed to consist of n points ${\displaystyle x_{1},\ldots ,x_{n}}$ (which will be random vectors in the multivariate cases).

If the likelihood function belongs to the exponential family, then a conjugate prior exists, often also in the exponential family; see Exponential family: Conjugate distributions.

When likelihood function is a discrete distribution

Likelihood	Model parameters	Conjugate prior distribution	Prior hyperparameters	Posterior hyperparameters[note 1]	Interpretation of hyperparameters	Posterior predictive[note 2]
Bernoulli	p (probability)	Beta	${\displaystyle \alpha ,\,\beta \in \mathbb {R} \!}$	${\displaystyle \alpha +\sum _{i=1}^{n}x_{i},\,\beta +n-\sum _{i=1}^{n}x_{i}\!}$	${\displaystyle \alpha }$ successes, ${\displaystyle \beta }$ failures[note 3]	${\displaystyle p({\tilde {x}}=1)={\frac {\alpha '}{\alpha '+\beta '}}}$
Binomial	p (probability)	Beta	${\displaystyle \alpha ,\,\beta \in \mathbb {R} \!}$	${\displaystyle \alpha +\sum _{i=1}^{n}x_{i},\,\beta +\sum _{i=1}^{n}N_{i}-\sum _{i=1}^{n}x_{i}\!}$	${\displaystyle \alpha }$ successes, ${\displaystyle \beta }$ failures[note 3]	${\displaystyle \operatorname {BetaBin} ({\tilde {x}}|\alpha ',\beta ')}$ (beta-binomial)
Negative binomial with known failure number, r	p (probability)	Beta	${\displaystyle \alpha ,\,\beta \in \mathbb {R} \!}$	${\displaystyle \alpha +\sum _{i=1}^{n}x_{i},\,\beta +rn\!}$	${\displaystyle \alpha }$ total successes, ${\displaystyle \beta }$ failures[note 3] (i.e., ${\displaystyle {\frac {\beta }{r}}}$ experiments, assuming ${\displaystyle r}$ stays fixed)	${\displaystyle \operatorname {BetaNegBin} ({\tilde {x}}|\alpha ',\beta ')}$ (beta-negative binomial)
Poisson	λ (rate)	Gamma	${\displaystyle k,\,\theta \in \mathbb {R} \!}$	${\displaystyle k+\sum _{i=1}^{n}x_{i},\ {\frac {\theta }{n\theta +1}}\!}$	${\displaystyle k}$ total occurrences in ${\displaystyle {\frac {1}{\theta }}}$ intervals	${\displaystyle \operatorname {NB} \left({\tilde {x}}\mid k',{\frac {\theta '}{\theta '+1}}\right)}$ (negative binomial)
			${\displaystyle \alpha ,\,\beta \!}$ [note 4]	${\displaystyle \alpha +\sum _{i=1}^{n}x_{i},\ \beta +n\!}$	${\displaystyle \alpha }$ total occurrences in ${\displaystyle \beta }$ intervals	${\displaystyle \operatorname {NB} \left({\tilde {x}}\mid \alpha ',{\frac {1}{1+\beta '}}\right)}$ (negative binomial)
Categorical	p (probability vector), k (number of categories; i.e., size of p)	Dirichlet	${\displaystyle {\boldsymbol {\alpha }}\in \mathbb {R} ^{k}\!}$	${\displaystyle {\boldsymbol {\alpha }}+(c_{1},\ldots ,c_{k}),}$ where ${\displaystyle c_{i}}$ is the number of observations in category i	${\displaystyle \alpha _{i}}$ occurrences of category ${\displaystyle i}$[note 3]	${\displaystyle {\begin{aligned}p({\tilde {x}}=i)&={\frac {{\alpha _{i}}'}{\sum _{i}{\alpha _{i}}'}}\\&={\frac {\alpha _{i}+c_{i}}{\sum _{i}\alpha _{i}+n}}\end{aligned}}}$
Multinomial	p (probability vector), k (number of categories; i.e., size of p)	Dirichlet	${\displaystyle {\boldsymbol {\alpha }}\in \mathbb {R} ^{k}\!}$	${\displaystyle {\boldsymbol {\alpha }}+\sum _{i=1}^{n}\mathbf {x} _{i}\!}$	${\displaystyle \alpha _{i}}$ occurrences of category ${\displaystyle i}$[note 3]	${\displaystyle \operatorname {DirMult} ({\tilde {\mathbf {x} }}\mid {\boldsymbol {\alpha }}')}$ (Dirichlet-multinomial)
Hypergeometric with known total population size, N	M (number of target members)	Beta-binomial[4]	${\displaystyle n=N,\alpha ,\,\beta \!}$	${\displaystyle \alpha +\sum _{i=1}^{n}x_{i},\,\beta +\sum _{i=1}^{n}N_{i}-\sum _{i=1}^{n}x_{i}\!}$	${\displaystyle \alpha }$ successes, ${\displaystyle \beta }$ failures[note 3]
Geometric	p0 (probability)	Beta	${\displaystyle \alpha ,\,\beta \in \mathbb {R} \!}$	${\displaystyle \alpha +n,\,\beta +\sum _{i=1}^{n}x_{i}\!}$	${\displaystyle \alpha }$ experiments, ${\displaystyle \beta }$ total failures[note 3]

When likelihood function is a continuous distribution

Likelihood	Model parameters	Conjugate prior distribution	Prior hyperparameters	Posterior hyperparameters[note 1]	Interpretation of hyperparameters	Posterior predictive[note 5]
Normal with known variance σ2	μ (mean)	Normal	${\displaystyle \mu _{0},\,\sigma _{0}^{2}\!}$	${\displaystyle {\frac {1}{{\frac {1}{\sigma _{0}^{2}}}+{\frac {n}{\sigma ^{2}}}}}\left({\frac {\mu _{0}}{\sigma _{0}^{2}}}+{\frac {\sum _{i=1}^{n}x_{i}}{\sigma ^{2}}}\right),\left({\frac {1}{\sigma _{0}^{2}}}+{\frac {n}{\sigma ^{2}}}\right)^{-1}}$	mean was estimated from observations with total precision (sum of all individual precisions)${\displaystyle 1/\sigma _{0}^{2}}$ and with sample mean ${\displaystyle \mu _{0}}$	${\displaystyle {\mathcal {N}}({\tilde {x}}|\mu _{0}',{\sigma _{0}^{2}}'+\sigma ^{2})}$[5]
Normal with known precision τ	μ (mean)	Normal	${\displaystyle \mu _{0},\,\tau _{0}\!}$	${\displaystyle {\frac {\tau _{0}\mu _{0}+\tau \sum _{i=1}^{n}x_{i}}{\tau _{0}+n\tau }},\,\tau _{0}+n\tau }$	mean was estimated from observations with total precision (sum of all individual precisions)${\displaystyle \tau _{0}}$ and with sample mean ${\displaystyle \mu _{0}}$	${\displaystyle {\mathcal {N}}\left({\tilde {x}}\mid \mu _{0}',{\frac {1}{\tau _{0}'}}+{\frac {1}{\tau }}\right)}$[5]
Normal with known mean μ	σ2 (variance)	Inverse gamma	${\displaystyle \mathbf {\alpha ,\,\beta } }$ [note 6]	${\displaystyle \mathbf {\alpha } +{\frac {n}{2}},\,\mathbf {\beta } +{\frac {\sum _{i=1}^{n}{(x_{i}-\mu )^{2}}}{2}}}$	variance was estimated from ${\displaystyle 2\alpha }$ observations with sample variance ${\displaystyle \beta /\alpha }$ (i.e. with sum of squared deviations ${\displaystyle 2\beta }$, where deviations are from known mean ${\displaystyle \mu }$)	${\displaystyle t_{2\alpha '}({\tilde {x}}|\mu ,\sigma ^{2}=\beta '/\alpha ')}$[5]
Normal with known mean μ	σ2 (variance)	Scaled inverse chi-squared	${\displaystyle \nu ,\,\sigma _{0}^{2}\!}$	${\displaystyle \nu +n,\,{\frac {\nu \sigma _{0}^{2}+\sum _{i=1}^{n}(x_{i}-\mu )^{2}}{\nu +n}}\!}$	variance was estimated from ${\displaystyle \nu }$ observations with sample variance ${\displaystyle \sigma _{0}^{2}}$	${\displaystyle t_{\nu '}({\tilde {x}}|\mu ,{\sigma _{0}^{2}}')}$[5]
Normal with known mean μ	τ (precision)	Gamma	${\displaystyle \alpha ,\,\beta \!}$[note 4]	${\displaystyle \alpha +{\frac {n}{2}},\,\beta +{\frac {\sum _{i=1}^{n}(x_{i}-\mu )^{2}}{2}}\!}$	precision was estimated from ${\displaystyle 2\alpha }$ observations with sample variance ${\displaystyle \beta /\alpha }$ (i.e. with sum of squared deviations ${\displaystyle 2\beta }$, where deviations are from known mean ${\displaystyle \mu }$)	${\displaystyle t_{2\alpha '}({\tilde {x}}\mid \mu ,\sigma ^{2}=\beta '/\alpha ')}$[5]
Normal[note 7]	μ and σ2 Assuming exchangeability	Normal-inverse gamma	${\displaystyle \mu _{0},\,\nu ,\,\alpha ,\,\beta }$	${\displaystyle {\frac {\nu \mu _{0}+n{\bar {x}}}{\nu +n}},\,\nu +n,\,\alpha +{\frac {n}{2}},\,}$ ${\displaystyle \beta +{\tfrac {1}{2}}\sum _{i=1}^{n}(x_{i}-{\bar {x}})^{2}+{\frac {n\nu }{\nu +n}}{\frac {({\bar {x}}-\mu _{0})^{2}}{2}}}$ ${\displaystyle {\bar {x}}}$ is the sample mean	mean was estimated from ${\displaystyle \nu }$ observations with sample mean ${\displaystyle \mu _{0}}$; variance was estimated from ${\displaystyle 2\alpha }$ observations with sample mean ${\displaystyle \mu _{0}}$ and sum of squared deviations ${\displaystyle 2\beta }$	${\displaystyle t_{2\alpha '}\left({\tilde {x}}\mid \mu ',{\frac {\beta '(\nu '+1)}{\nu '\alpha '}}\right)}$[5]
Normal	μ and τ Assuming exchangeability	Normal-gamma	${\displaystyle \mu _{0},\,\nu ,\,\alpha ,\,\beta }$	${\displaystyle {\frac {\nu \mu _{0}+n{\bar {x}}}{\nu +n}},\,\nu +n,\,\alpha +{\frac {n}{2}},\,}$ ${\displaystyle \beta +{\tfrac {1}{2}}\sum _{i=1}^{n}(x_{i}-{\bar {x}})^{2}+{\frac {n\nu }{\nu +n}}{\frac {({\bar {x}}-\mu _{0})^{2}}{2}}}$ ${\displaystyle {\bar {x}}}$ is the sample mean	mean was estimated from ${\displaystyle \nu }$ observations with sample mean ${\displaystyle \mu _{0}}$, and precision was estimated from ${\displaystyle 2\alpha }$ observations with sample mean ${\displaystyle \mu _{0}}$ and sum of squared deviations ${\displaystyle 2\beta }$	${\displaystyle t_{2\alpha '}\left({\tilde {x}}\mid \mu ',{\frac {\beta '(\nu '+1)}{\alpha '\nu '}}\right)}$[5]
Multivariate normal with known covariance matrix Σ	μ (mean vector)	Multivariate normal	${\displaystyle {\boldsymbol {\boldsymbol {\mu }}}_{0},\,{\boldsymbol {\Sigma }}_{0}}$	${\displaystyle \left({\boldsymbol {\Sigma }}_{0}^{-1}+n{\boldsymbol {\Sigma }}^{-1}\right)^{-1}\left({\boldsymbol {\Sigma }}_{0}^{-1}{\boldsymbol {\mu }}_{0}+n{\boldsymbol {\Sigma }}^{-1}\mathbf {\bar {x}} \right),}$ ${\displaystyle \left({\boldsymbol {\Sigma }}_{0}^{-1}+n{\boldsymbol {\Sigma }}^{-1}\right)^{-1}}$ ${\displaystyle \mathbf {\bar {x}} }$ is the sample mean	mean was estimated from observations with total precision (sum of all individual precisions)${\displaystyle {\boldsymbol {\Sigma }}_{0}^{-1}}$ and with sample mean ${\displaystyle {\boldsymbol {\mu }}_{0}}$	${\displaystyle {\mathcal {N}}({\tilde {\mathbf {x} }}\mid {{\boldsymbol {\mu }}_{0}}',{{\boldsymbol {\Sigma }}_{0}}'+{\boldsymbol {\Sigma }})}$[5]
Multivariate normal with known precision matrix Λ	μ (mean vector)	Multivariate normal	${\displaystyle \mathbf {\boldsymbol {\mu }} _{0},\,{\boldsymbol {\Lambda }}_{0}}$	${\displaystyle \left({\boldsymbol {\Lambda }}_{0}+n{\boldsymbol {\Lambda }}\right)^{-1}\left({\boldsymbol {\Lambda }}_{0}{\boldsymbol {\mu }}_{0}+n{\boldsymbol {\Lambda }}\mathbf {\bar {x}} \right),\,\left({\boldsymbol {\Lambda }}_{0}+n{\boldsymbol {\Lambda }}\right)}$ ${\displaystyle \mathbf {\bar {x}} }$ is the sample mean	mean was estimated from observations with total precision (sum of all individual precisions)${\displaystyle {\boldsymbol {\Lambda }}_{0}}$ and with sample mean ${\displaystyle {\boldsymbol {\mu }}_{0}}$	${\displaystyle {\mathcal {N}}\left({\tilde {\mathbf {x} }}\mid {{\boldsymbol {\mu }}_{0}}',({{{\boldsymbol {\Lambda }}_{0}}'}^{-1}+{\boldsymbol {\Lambda }}^{-1})^{-1}\right)}$[5]
Multivariate normal with known mean μ	Σ (covariance matrix)	Inverse-Wishart	${\displaystyle \nu ,\,{\boldsymbol {\Psi }}}$	${\displaystyle n+\nu ,\,{\boldsymbol {\Psi }}+\sum _{i=1}^{n}(\mathbf {x_{i}} -{\boldsymbol {\mu }})(\mathbf {x_{i}} -{\boldsymbol {\mu }})^{T}}$	covariance matrix was estimated from ${\displaystyle \nu }$ observations with sum of pairwise deviation products ${\displaystyle {\boldsymbol {\Psi }}}$	${\displaystyle t_{\nu '-p+1}\left({\tilde {\mathbf {x} }}|{\boldsymbol {\mu }},{\frac {1}{\nu '-p+1}}{\boldsymbol {\Psi }}'\right)}$[5]
Multivariate normal with known mean μ	Λ (precision matrix)	Wishart	${\displaystyle \nu ,\,\mathbf {V} }$	${\displaystyle n+\nu ,\,\left(\mathbf {V} ^{-1}+\sum _{i=1}^{n}(\mathbf {x_{i}} -{\boldsymbol {\mu }})(\mathbf {x_{i}} -{\boldsymbol {\mu }})^{T}\right)^{-1}}$	covariance matrix was estimated from ${\displaystyle \nu }$ observations with sum of pairwise deviation products ${\displaystyle \mathbf {V} ^{-1}}$	${\displaystyle t_{\nu '-p+1}\left({\tilde {\mathbf {x} }}\mid {\boldsymbol {\mu }},{\frac {1}{\nu '-p+1}}{\mathbf {V} '}^{-1}\right)}$[5]
Multivariate normal	μ (mean vector) and Σ (covariance matrix)	normal-inverse-Wishart	${\displaystyle {\boldsymbol {\mu }}_{0},\,\kappa _{0},\,\nu _{0},\,{\boldsymbol {\Psi }}}$	${\displaystyle {\frac {\kappa _{0}{\boldsymbol {\mu }}_{0}+n\mathbf {\bar {x}} }{\kappa _{0}+n}},\,\kappa _{0}+n,\,\nu _{0}+n,\,}$ ${\displaystyle {\boldsymbol {\Psi }}+\mathbf {C} +{\frac {\kappa _{0}n}{\kappa _{0}+n}}(\mathbf {\bar {x}} -{\boldsymbol {\mu }}_{0})(\mathbf {\bar {x}} -{\boldsymbol {\mu }}_{0})^{T}}$ ${\displaystyle \mathbf {\bar {x}} }$ is the sample mean ${\displaystyle \mathbf {C} =\sum _{i=1}^{n}(\mathbf {x_{i}} -\mathbf {\bar {x}} )(\mathbf {x_{i}} -\mathbf {\bar {x}} )^{T}}$	mean was estimated from ${\displaystyle \kappa _{0}}$ observations with sample mean ${\displaystyle {\boldsymbol {\mu }}_{0}}$; covariance matrix was estimated from ${\displaystyle \nu _{0}}$ observations with sample mean ${\displaystyle {\boldsymbol {\mu }}_{0}}$ and with sum of pairwise deviation products ${\displaystyle {\boldsymbol {\Psi }}=\nu _{0}{\boldsymbol {\Sigma }}_{0}}$	${\displaystyle t_{{\nu _{0}}'-p+1}\left({\tilde {\mathbf {x} }}|{{\boldsymbol {\mu }}_{0}}',{\frac {{\kappa _{0}}'+1}{{\kappa _{0}}'({\nu _{0}}'-p+1)}}{\boldsymbol {\Psi }}'\right)}$[5]
Multivariate normal	μ (mean vector) and Λ (precision matrix)	normal-Wishart	${\displaystyle {\boldsymbol {\mu }}_{0},\,\kappa _{0},\,\nu _{0},\,\mathbf {V} }$	${\displaystyle {\frac {\kappa _{0}{\boldsymbol {\mu }}_{0}+n\mathbf {\bar {x}} }{\kappa _{0}+n}},\,\kappa _{0}+n,\,\nu _{0}+n,\,}$ ${\displaystyle \left(\mathbf {V} ^{-1}+\mathbf {C} +{\frac {\kappa _{0}n}{\kappa _{0}+n}}(\mathbf {\bar {x}} -{\boldsymbol {\mu }}_{0})(\mathbf {\bar {x}} -{\boldsymbol {\mu }}_{0})^{T}\right)^{-1}}$ ${\displaystyle \mathbf {\bar {x}} }$ is the sample mean ${\displaystyle \mathbf {C} =\sum _{i=1}^{n}(\mathbf {x_{i}} -\mathbf {\bar {x}} )(\mathbf {x_{i}} -\mathbf {\bar {x}} )^{T}}$	mean was estimated from ${\displaystyle \kappa _{0}}$ observations with sample mean ${\displaystyle {\boldsymbol {\mu }}_{0}}$; covariance matrix was estimated from ${\displaystyle \nu _{0}}$ observations with sample mean ${\displaystyle {\boldsymbol {\mu }}_{0}}$ and with sum of pairwise deviation products ${\displaystyle \mathbf {V} ^{-1}}$	${\displaystyle t_{{\nu _{0}}'-p+1}\left({\tilde {\mathbf {x} }}\mid {{\boldsymbol {\mu }}_{0}}',{\frac {{\kappa _{0}}'+1}{{\kappa _{0}}'({\nu _{0}}'-p+1)}}{\mathbf {V} '}^{-1}\right)}$[5]
Uniform	${\displaystyle U(0,\theta )\!}$	Pareto	${\displaystyle x_{m},\,k\!}$	${\displaystyle \max\{\,x_{1},\ldots ,x_{n},x_{\mathrm {m} }\},\,k+n\!}$	${\displaystyle k}$ observations with maximum value ${\displaystyle x_{m}}$
Pareto with known minimum xm	k (shape)	Gamma	${\displaystyle \alpha ,\,\beta \!}$	${\displaystyle \alpha +n,\,\beta +\sum _{i=1}^{n}\ln {\frac {x_{i}}{x_{\mathrm {m} }}}\!}$	${\displaystyle \alpha }$ observations with sum ${\displaystyle \beta }$ of the order of magnitude of each observation (i.e. the logarithm of the ratio of each observation to the minimum ${\displaystyle x_{m}}$)
Weibull with known shape β	θ (scale)	Inverse gamma[4]	${\displaystyle a,b\!}$	${\displaystyle a+n,\,b+\sum _{i=1}^{n}x_{i}^{\beta }\!}$	${\displaystyle a}$ observations with sum ${\displaystyle b}$ of the β'th power of each observation
Log-normal	Same as for the normal distribution after exponentiating the data
Exponential	λ (rate)	Gamma	${\displaystyle \alpha ,\,\beta \!}$ [note 4]	${\displaystyle \alpha +n,\,\beta +\sum _{i=1}^{n}x_{i}\!}$	${\displaystyle \alpha -1}$ observations that sum to ${\displaystyle \beta }$ [6]	${\displaystyle \operatorname {Lomax} ({\tilde {x}}\mid \beta ',\alpha ')}$ (Lomax distribution)
Gamma with known shape α	β (rate)	Gamma	${\displaystyle \alpha _{0},\,\beta _{0}\!}$	${\displaystyle \alpha _{0}+n\alpha ,\,\beta _{0}+\sum _{i=1}^{n}x_{i}\!}$	${\displaystyle \alpha _{0}/\alpha }$ observations with sum ${\displaystyle \beta _{0}}$	${\displaystyle \operatorname {CG} ({\tilde {\mathbf {x} }}\mid \alpha ,{\alpha _{0}}',{\beta _{0}}')=\operatorname {\beta '} ({\tilde {\mathbf {x} }}|\alpha ,{\alpha _{0}}',1,{\beta _{0}}')}$ [note 8]
Inverse Gamma with known shape α	β (inverse scale)	Gamma	${\displaystyle \alpha _{0},\,\beta _{0}\!}$	${\displaystyle \alpha _{0}+n\alpha ,\,\beta _{0}+\sum _{i=1}^{n}{\frac {1}{x_{i}}}\!}$	${\displaystyle \alpha _{0}/\alpha }$ observations with sum ${\displaystyle \beta _{0}}$
Gamma with known rate β	α (shape)	${\displaystyle \propto {\frac {a^{\alpha -1}\beta ^{\alpha c}}{\Gamma (\alpha )^{b}}}}$	${\displaystyle a,\,b,\,c\!}$	${\displaystyle a\prod _{i=1}^{n}x_{i},\,b+n,\,c+n\!}$	${\displaystyle b}$ or ${\displaystyle c}$ observations (${\displaystyle b}$ for estimating ${\displaystyle \alpha }$, ${\displaystyle c}$ for estimating ${\displaystyle \beta }$) with product ${\displaystyle a}$
Gamma [4]	α (shape), β (inverse scale)	${\displaystyle \propto {\frac {p^{\alpha -1}e^{-\beta q}}{\Gamma (\alpha )^{r}\beta ^{-\alpha s}}}}$	${\displaystyle p,\,q,\,r,\,s\!}$	${\displaystyle p\prod _{i=1}^{n}x_{i},\,q+\sum _{i=1}^{n}x_{i},\,r+n,\,s+n\!}$	${\displaystyle \alpha }$ was estimated from ${\displaystyle r}$ observations with product ${\displaystyle p}$; ${\displaystyle \beta }$ was estimated from ${\displaystyle s}$ observations with sum ${\displaystyle q}$

• Beta-binomial distribution