Description Usage Arguments Details Value References Examples
View source: R/percent2probit.R
These functions transform data between percentage, probit and Normal Equivalent Deviate (NED) \insertCitebliss_method_1934,finney_probit_1952viabilitymetrics. \loadmathjax
1 2 3 4 5 6 7 8 9 10 11 12 13 | PercentAdjust(percentage, n)
Percent2NED(percentage)
Percent2Probit(percentage)
Probit2NED(probit)
NED2Probit(NED)
NED2Percent(NED)
Probit2Percent(probit)
|
percentage |
The percentage value. |
n |
Sample size for estimation of percentage. |
probit |
The probit value |
NED |
The NED value. |
Probit transformation can be used to transform a sigmoid curve of percentage data to a linear one. The probit transformation is defined as \mjseqn\textrmNED + 5. However the two terms probit and NED are used interchangeably in literature.
NED function (\mjseqn\Phi^-1) is is the inverse of the cumulative distribution function (\mjseqn\Phi) of the standard normal distribution (\mjseqnz\sim N(0,1)) or the quantile function associated with the standard normal distribution.
For percentage \mjseqnp,
\mjsdeqn\textrmNED(p)=\Phi^-1(p)= \sqrt2~\textrmerf^-1(2p-1)
and
\mjsdeqn\textrmprobit(p)=\textrmNED(p)+5
The PercentAdjust
function adjusts the percentage values of 0 and 100
to \mjseqn100\times \dfrac0.25n and \mjseqn100\times
\dfracn-0.25n respectively, according to the sample size \mjseqnn to
avoid infinity values during probit transformation
\insertCitemiller_estimation_1944viabilitymetrics.
The transformed value.
bliss_method_1934viabilitymetrics
\insertRefmiller_estimation_1944viabilitymetrics
\insertReffinney_probit_1952viabilitymetrics
1 2 3 4 5 6 7 8 9 10 11 12 13 14 | Percent2NED(0:100)
Percent2Probit(0:100)
Percent2NED(25)
Percent2Probit(25)
Percent2NED(25) +5
NED2Probit(-0.6744898)
# Percentage adjustment for 0 and 100
Percent2Probit(100)
Percent2Probit(0)
n = 50
Percent2Probit(PercentAdjust(100, n))
Percent2Probit(PercentAdjust(0, n))
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.