\@doendnote{endnote5}{These specific instructions are for the Athena installation of Matlab. Very similar (if not identical) operations will work on Windows platforms as well.}
\@doendnote{endnote6}{Cftool has several fitting algorithms at its disposal. The most powerful fitting technique is the ``Trust-Region'' discussed in \cite {branch} which is the default non-linear method. It permits the use of lower and upper bounds around the initial guesses for the fitting parameters. The second method ``Levenberg-Marquardt'' is the one discussed in \cite {bevington} and originally presented in \cite {levenberg, marquardt}. This method, is only slightly less powerful in that it cannot accept bounds on the fit parameters (though it does require good initial guesses). Try typing: {\protect \bf  help fitoptions} to learn more about other fit options that you can select.}
\@doendnote{endnote7}{Strictly speaking, the confidence bounds for fitted coefficients are given by: $C = b \pm t \protect \sqrt  {S}$ where $b$ are the coefficients of the fit, $t$ is the inverse of the Student's t cumulative distribution function (see Bevington, Appendix C.6 for more details on the origin and significance of the Student t distribution or try {\protect \tt  `help tinv'} from inside Matlab), and $S$ is a vector of the diagonal elements of the covariance matrix of the coefficient estimates, $(X^TX)^{-1}s^2$. Here $s^2 =\chi ^2_{\nu -1}$. Refer to ``Linear Least Squares'' from Matlab's online documentation or Reference\protect \nobreakspace  {}\cite {bevington} for more information about $X$ and $X^T$.}
\@doendnote{endnote8}{The Matlab toolbox returns a goodness-of-fit statistic called SSE (Sum of Squares due to Error). This is simply the $\chi ^2$ statistic used frequently by physicists and in Bevington. The other necessary statistics is DFE (Degrees of Freedom) and is equal to the number of data points minus the number of fitted coefficients. In Junior Lab, we are most often interested in the reduced chi-square $(\chi ^2_{\nu -1})$ which is simply given by the $\chi ^2$ divided by the DFE.}