Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Thread Subject:
Probit regression threshold value?

Subject: Probit regression threshold value?

From: Robert

Date: 26 Jul, 2013 12:03:16

Message: 1 of 2

I frequently use glmfit for fitting probit regression models, in much the same way as shown in the help section for the glmfit function:

% Example: Fit a probit regression model for y on x. Each y(i) is the
% number of successes in n(i) trials.
         x = [2100 2300 2500 2700 2900 3100 3300 3500 3700 3900 4100 4300]';
         n = [48 42 31 34 31 21 23 23 21 16 17 21]';
         y = [1 2 0 3 8 8 14 17 19 15 17 21]';
         b = glmfit(x, [y n], 'binomial', 'link', 'probit');
         yfit = glmval(b, x, 'probit', 'size', n);
         plot(x, y./n, 'o', x, yfit./n, '-')

However, I would also like to know how to derive the estimated value of x associated with a given threshold 'success' probability (and associated confidence limits if possible). For example, this threshold value is commonly the 50% point, where half of responses are 'successes' and half are not.

Any advice would be much appreciated!

Many thanks,
Robert

Subject: Probit regression threshold value?

From: Alan_Weiss

Date: 26 Jul, 2013 13:30:32

Message: 2 of 2

On 7/26/2013 8:03 AM, Robert wrote:
> I frequently use glmfit for fitting probit regression models, in much
> the same way as shown in the help section for the glmfit function:
>
> % Example: Fit a probit regression model for y on x. Each y(i) is the
> % number of successes in n(i) trials.
> x = [2100 2300 2500 2700 2900 3100 3300 3500 3700 3900 4100
> 4300]';
> n = [48 42 31 34 31 21 23 23 21 16 17 21]';
> y = [1 2 0 3 8 8 14 17 19 15 17 21]';
> b = glmfit(x, [y n], 'binomial', 'link', 'probit');
> yfit = glmval(b, x, 'probit', 'size', n);
> plot(x, y./n, 'o', x, yfit./n, '-')
>
> However, I would also like to know how to derive the estimated value
> of x associated with a given threshold 'success' probability (and
> associated confidence limits if possible). For example, this threshold
> value is commonly the 50% point, where half of responses are
> 'successes' and half are not.
>
> Any advice would be much appreciated!
>
> Many thanks,
> Robert

I don't know how to calculate confidence limits, but you can calculate
the 50% point pretty easily:

r = @(x)glmval(b,x,'probit')-.5;
ranswer = fzero(r,[2500,3500])

ranswer =

    3.1958e+03

Alan Weiss
MATLAB mathematical toolbox documentation

Tags for this Thread

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Contact us