** Next:** Approximated solution for non-linear
** Up:** Fits, and especially linear
** Previous:** Probabilistic parametric inference from

#

Linear fit with normal errors on both axes

To apply the general formulas of the previous section
we only need to make explicit
and the error functions, and finally
integrate over .
In the case of linear fit with normal errors
the individual contributions
to the likelihoods become

that, inserted into Eq. (25), finally give

The effect of the error of the -values is to have an effective
standard error on the -values that is the quadratic combination
of and , the latter `propagated'
to the other coordinate via the slope
(this result can be justified heuristically by dimensional analysis).

** Next:** Approximated solution for non-linear
** Up:** Fits, and especially linear
** Previous:** Probabilistic parametric inference from
Giulio D'Agostini
2005-11-21