Weighted Least Squares Fit for Statistical Analysis of Data

  • Thread starter Thread starter Logik
  • Start date Start date
  • Tags Tags
    Fit Square
Logik
Messages
31
Reaction score
0

Homework Statement



I have a project for one of my class and I have been given a sheet to do the statistical analyst of my data. I am not convince this sheet is proper and I need someone to look over it it. I don't understand where my Delta R goes...


Homework Equations


<br /> \chi^2 =-\frac{1}{2} \sum_{i=1}^{N}{\left(\frac{y_i-ax_i}{\sigma_i^2}\right)^2} \\<br /> \frac{\partial \chi^2}{\partial a}
= \sum_{i=1}^{N}{\frac{x_i}{\sigma_i^2}(y_i-ax_i)} = 0 \\<br /> \sum_{i=1}^{N}{\frac{x_i y_i}{\sigma_i^2}}
= a\sum_{i=1}^{N}{\frac{x_i^2}{\sigma_i^2}} \\<br /> a= \sum_{i=1}^{N}{\frac{x_iy_i}{x_i^2}} \\<br /> \sigma_a^2 = \sum_{i=1}^{N}{\frac{x_i^2}{\sigma_i^2}} S^2 \\<br /> S^2

= \frac{1}{N-1}\sum_{i=1}^{N}{\frac{(y_i-ax_i)^2}{\sigma_i^2}} \\<br /> \sigma_a^2 =
\frac{1}{N-1}\left(\sum_{i=1}^{N}{\frac{x_i^2}{\sigma_i^2}}\right)\left(\sum_{i=1}^{N}{\frac{(y_i-ax_i)^2}{\sigma_i^2}}\right) \\<br /> r_n^2 = \left(n-\frac{1}{2}\right)\lambda R \\<br /> a= \sum_{n=1}^{15}{\frac{r_n^2\left(n-\frac{1}{2}\right)}{(r_n^2)^2}} \\<br /> \sigma_a^2
= \frac{1}{14}\left(\sum_{n=1}^{14}{\frac{(r_n^2)^2}{\sigma_r^2}}\right)\left(\sum_{i=1}^{N}{\frac{(r_n^2-a\left(n-\frac{1}{2}\right))^2}{\sigma_r^2}}\right) \\<br /> \Psi(x) = x^2 \\ <br /> \sigma_\Psi^2 = (\frac{\partial}{\partial x}(x^2)\Delta x)^2= 4x^2(\Delta x)^2 \\ <br /> \sigma_{r_n^2} = 4r_n^2(\Delta r)^2 \\<br /> \sigma_a^2 = \frac{1}{14}\left(\sum_{n=1}^{14}{\frac{(r_n^2)^2}{4r_n^2}}\right)/\left(\sum_{i=1}^{N}{\frac{(r_n^2-a\left(n-\frac{1}{2}\right))^2}{4r_n^2}}\right)<br />


The Attempt at a Solution



The error on r comes from the fact it's a measurement and we square it. I think Delta R should be there somewhere even though it is constant...
 
Last edited by a moderator:
Physics news on Phys.org
pdf

PDF of latex file.
 

Attachments

Logik, do not put the spaces in [ tex ] and [ /tex ].

And do NOT write a LONG formula as a single Tex statement.
It will wind up all on one page.
 
Logik - regarding your enclosure, I don't understand the step from equation (3) to equation (4). I also don't know if this is relevant to your question.
 
There are two things I don't understand about this problem. First, when finding the nth root of a number, there should in theory be n solutions. However, the formula produces n+1 roots. Here is how. The first root is simply ##\left(r\right)^{\left(\frac{1}{n}\right)}##. Then you multiply this first root by n additional expressions given by the formula, as you go through k=0,1,...n-1. So you end up with n+1 roots, which cannot be correct. Let me illustrate what I mean. For this...
Back
Top