Poisson binomial distribution: Difference between revisions
Winterfors (talk | contribs) Tried to simplify plain language definition |
Winterfors (talk | contribs) m →Probability mass function: Corrected index error in formula |
||
Line 46: | Line 46: | ||
</ref> |
</ref> |
||
<math>Pr(K=k) = \sum\limits_{A\in {{F}_{k}}}{\prod\limits_{i\in A}{{{p}_{i}}}\prod\limits_{j\in {{A}^{c}}}{(1-{{p}_{j}})}}</math> |
:<math>Pr(K=k) = \sum\limits_{A\in {{F}_{k}}}{\prod\limits_{i\in A}{{{p}_{i}}}\prod\limits_{j\in {{A}^{c}}}{(1-{{p}_{j}})}}</math> |
||
where <math>F_k</math> is the set of all subsets of ''k'' integers that can be selected from {1,2,3,...,''n''}. For example, if ''n'' = 3, then <math>{{F}_{2}}=\left\{ \{1,2\},\{1,3\},\{2,3\} \right\}</math>. <math>A^c</math> is the complement of <math>A</math>, i.e. <math>A^c =\{1,2,3,\dots,n\}\backslash A</math>. |
where <math>F_k</math> is the set of all subsets of ''k'' integers that can be selected from {1,2,3,...,''n''}. For example, if ''n'' = 3, then <math>{{F}_{2}}=\left\{ \{1,2\},\{1,3\},\{2,3\} \right\}</math>. <math>A^c</math> is the complement of <math>A</math>, i.e. <math>A^c =\{1,2,3,\dots,n\}\backslash A</math>. |
||
Line 68: | Line 68: | ||
</ref> |
</ref> |
||
<math>\Pr (K=k)=\left\{ \begin{align} |
:<math>\Pr (K=k)=\left\{ \begin{align} |
||
& \prod\limits_{i=1}^{n}{(1-{{p}_{i}})} \qquad k=0 \\ |
& \prod\limits_{i=1}^{n}{(1-{{p}_{i}})} \qquad k=0 \\ |
||
& \frac{1}{k}\sum\limits_{i=1}^{k}{{{(-1)}^{i-1}}\Pr (K= |
& \frac{1}{k}\sum\limits_{i=1}^{k}{{{(-1)}^{i-1}}\Pr (K=k-i)T(i)} \qquad k>0 \\ |
||
\end{align} \right.</math> |
\end{align} \right.</math> |
||
Line 92: | Line 92: | ||
</ref> |
</ref> |
||
<math>\Pr (K=k)=\frac{1}{n+1}\sum\limits_{l=0}^{n}{{{C}^{lk}}\prod\limits_{m=1}^{n}{\left( 1+({{C}^{l}}-1){{p}_{m}} \right)}}</math> |
:<math>\Pr (K=k)=\frac{1}{n+1}\sum\limits_{l=0}^{n}{{{C}^{lk}}\prod\limits_{m=1}^{n}{\left( 1+({{C}^{l}}-1){{p}_{m}} \right)}}</math> |
||
where |
where |
Revision as of 14:31, 9 September 2010
Parameters | — success probabilities for each of the n trials | ||
---|---|---|---|
Support | k ∈ { 0, …, n } | ||
PMF | |||
CDF | |||
Mean | |||
Variance | |||
Skewness | |||
Excess kurtosis | |||
MGF | |||
CF |
In probability theory and statistics, the Poisson binomial distribution is the discrete probability distribution of a sum of independent Bernoulli trials.
In other words, it is the probability distribution of the number of successes in a sequence of n independent yes/no experiments with success probabilities . The ordinary binomial distribution is a special case of the Poisson binomial distribution, when all success probabilities are the same, that is .
Mean and variance
Since a Poisson binomial distributed variable is a sum of n independent Bernoulli distributed variables, its mean and variance will simply be sums of the mean and variance of the n Bernoulli distributions:
Probability mass function
The probability of having k successful trials out of a total of n can be written as the sum [1]
where is the set of all subsets of k integers that can be selected from {1,2,3,...,n}. For example, if n = 3, then . is the complement of , i.e. .
will contain elements, the sum over which is infeasible to compute in practice unless the number of trials n is small (e.g. if n=30, contains over 1020 elements). There are luckily more efficient ways to calculate .
As long as none of the success probabilities are equal to one, one can calculate the probability of n successes using the recursive formula [2]
where .
Another possibility is using the discrete Fourier transform
[3]
where
Still other methods are described in [4].
See also
References
- ^ Wang, Y. H. (1993). "On the number of successes in independent trials" (PDF). Statistica Sinica. 3 (2): 295–312.
- ^
Chen, X. H (1994). "Weighted finite population sampling to maximize entropy" (PDF). Biometrika. 81 (3): 457.
{{cite journal}}
: Unknown parameter|coauthors=
ignored (|author=
suggested) (help) - ^
Fernandez, M. (2010). "Closed-Form Expression for the Poisson-Binomial Probability Density Function". IEEE Transactions on Aerospace Electronic Systems. 46: 803–817. doi:10.1109/TAES.2010.5461658.
{{cite journal}}
: Unknown parameter|coauthors=
ignored (|author=
suggested) (help) - ^ Chen, S. X (1997). "Statistical Applications of the Poisson-Binomial and conditional Bernoulli distributions". Statistica Sinica. 7: 875–892.
{{cite journal}}
: Unknown parameter|coauthors=
ignored (|author=
suggested) (help)