Precision (statistics)

In <a href="/facts/Statistics/DNPsKGYU">statistics</a>, the precision matrix or concentration matrix is the <a href="/facts/Matrix_inverse/fPqXk3V8">matrix inverse</a> of the <a href="/facts/Covariance_matrix/kLhgjHC6">covariance matrix</a> or dispersion matrix, 
 
 
 
 P
 =
 
 Σ
 
 −
 1
 
 
 
 
 {\displaystyle P=\Sigma ^{-1}}
 
.
For <a href="/facts/Univariate_distribution/YjaPqYfq">univariate distributions</a>, the precision matrix degenerates into a <a href="/facts/Scalar_(mathematics)/MkDbA4Eo">scalar</a> precision, defined as the <a href="/facts/Multiplicative_inverse/yczdYyCw">reciprocal</a> of the <a href="/facts/Variance/ULBJKXD1">variance</a>, 
 
 
 
 p
 =
 
 
 1
 
 σ
 
 2
 
 
 
 
 
 
 {\displaystyle p={\frac {1}{\sigma ^{2}}}}
 
.
Other <a href="/facts/Summary_statistic/o213eGso">summary statistics</a> of <a href="/facts/Statistical_dispersion/xqevRHmz">statistical dispersion</a> also called precision (or imprecision)
include the reciprocal of the <a href="/facts/Standard_deviation/qSug9BRl">standard deviation</a>, 
 
 
 
 p
 =
 
 
 1
 σ
 
 
 
 
 {\displaystyle p={\frac {1}{\sigma }}}
 
; 
the standard deviation itself and the <a href="/facts/Relative_standard_deviation/V8ddKkz4">relative standard deviation</a>;
as well as the <a href="/facts/Standard_error/Iv96AyCD">standard error</a> and the <a href="/facts/Confidence_interval/NS8mG5UE">confidence interval</a> (or its half-width, the <a href="/facts/Margin_of_error/BtnDQ0Iu">margin of error</a>).

Precision (statistics) open-in-new

Precision (statistics)