Let w be (an estimate of) the probability that any selected datapoint is within the error tolerance of the model.
According to current text it is compute as probability of opposite event - probability that datapoint is outside of tolerance of the model (i.e. outlier)
Correct w is thereof is 9/11.
The next is to fix derivation. It says we need 91 iterations, but we actually need only 3.
log(0.05)/log(1 - 0.82^2) = 2.684
May I be wrong?
Let w be (an estimate of) the probability that any selected datapoint is within the error tolerance of the model.
According to current text it is compute as probability of opposite event - probability that datapoint is outside of tolerance of the model (i.e. outlier)
Correct w is thereof is 9/11.
The next is to fix derivation. It says we need 91 iterations, but we actually need only 3.
log(0.05)/log(1 - 0.82^2) = 2.684
May I be wrong?