Determine the the slope and its uncertainty?

40 次查看（过去 30 天）
Lizan
Lizan 2012-11-16
评论： Ankan Biswas 2018-1-28
Hi,
I am trying to linearly fit a set of data points, find the slope and then compute the uncertainty of the slope, +, - uncertainty. How can I do this in MATLAB?
I have tried to look into regression and regress but are getting very confused.
Additional questions:
What is the outputs of Regress? Does it gives the slope of the linear fit? And the 95% confidence intervals? I noticed that b not the same as the polyfit?
Likewise, the polyfit does not give the same slope as regression. And Regression gives me matrix of result.. shouldn't slope just be one value. The inputs are just vectors of x,y data.
Thanks

请先登录，再回答此问题。

采纳的回答

Jos (10584)
Jos (10584) 2012-11-16
Do you also want to fit an offset? Polyfit does that for you, but you have to tell regress explicitly,. Example:
x = 1:10 ; y = 10*x+3 ;
yr = y + rand(size(y))-0.5 ; % add noise
[b, bint] = regress(yr(:), [x(:) ones(numel(x),1)])
  2 个评论
Lizan
Lizan 2012-11-18
What does regress give you? Does it give you,
slope + error; slope - error;
I also find that polyfit does not give the same slope as in regress. Its confusing for me...
Venkatessh
Venkatessh 2013-3-14
编辑：Venkatessh 2013-3-14
regress gives you the 95% confidence interval of the coefficients (slope and y-intercept). I am not sure if you can get the errors by simply subtracting the confidence interval and even if you can bear in mind that it gives you a 95% estimate (~ 2-sigma) and not a 1-sigma uncertainty.
I am assuming by error you mean the uncertainty

请先登录，再进行评论。

更多回答（1 个）

Ganessen Moothooveeren
But still how to find the uncertainty in the slope using the polyfit function??
  2 个评论
Venkatessh
Venkatessh 2013-3-14
In order to estimate the uncertainties of the coefficients obtained from polyfit function, you may follow the following steps:
[b, bint] = polyfit(x,y,1);
b_err = sqrt(diag((bint.R)\inv(bint.R'))./bint.normr.^2./bint.df);
where, b_err contains the uncertainty of the coefficients
Ankan Biswas
Ankan Biswas 2018-1-28
Hi Venkatessh, Can you explain the rationale behind your error calculation? Thanks in advance.

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Support Vector Machine Regression 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by