Estimate false positive and false negative error probabilities by method moments.

1 | ```
estErrProbMethodOfMoments(nint, nrec, nunr, ntot)
``` |

`nint` |
Integer vector. True number of interactions. Typically, the function is called for a range of these, returning all possible solutions for that range. |

`nrec` |
Integer scalar. Observed number of reciprocated edges. |

`nunr` |
Integer scalar. Observed number of unreciprocated edges. |

`ntot` |
Integer scalar. Number of proteins which were tested twice (e.g. both as viable bait and as viable prey). |

The model is described in the vignette
*Stochastic and systematic errors in PPI data, by looking
at unreciprocated in- or out-edges*
by W. Huber, T. Chiang and R. Gentleman.

Matrix with 5 columns `nint`

(a copy of the input argument),
`pfp1`

, `pfn1`

, `pfp2`

and `pfn2`

, and as many
rows as the length of `nint`

.

Wolfgang Huber http://www.ebi.ac.uk/huber

1 2 3 4 5 6 | ```
est = estErrProbMethodOfMoments(nint=seq(8000, 40000, by=100), nrec=9722, nunr=15856, ntot=2000)
if(interactive()) {
plot(est[, c("pfp2", "pfn2")], type="l", col="blue", lwd=2,
xlab=expression(p[FP]), ylab=expression(p[FN]))
abline(h=0, v=0, lty=2)
}
``` |

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.