Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

I am using a four parameter logistic function $y = a + \dfrac{b-a}{1+e^{c(d-x)}}$. I would like to know how one finds the value $x$ that corresponds to $5\%$ (or $n\%$) cumulative density.

My intuition would be that I find the value between the lower and upper asymptotes that corresponds to an increase of $n\%$. Substituting this value for $y$ and solving the equation for x would give me the value $x$ at which there was a cumulative increase of $n\%$ from the lower asymptote. Is this correct?

share|improve this question
1  
There's no such thing as a cumulative density. The word "cumulative" contradicts the word "density". See en.wikipedia.org/wiki/Cumulative_density_function –  Michael Hardy Jun 7 '13 at 16:09

1 Answer 1

Yes, the procedure you described is correct (except for the misuse of the word "density", pointed out by Michael Hardy). As $x\to-\infty$, $y\to a$ (assuming $c>0$), and as $x\to+\infty$, $y\to b$. Therefore, you want to solve the equation $y=a+0.05(b-a)$, or $y=a+(n/100)(b-a)$ in general. This amounts to $$\frac{1}{1+e^{c(d-x)}} = \frac{n}{100}$$ $$ e^{c(d-x)} = \frac{100}{n}-1$$ $$ c(d-x) = \ln\left(\frac{100}{n}-1\right)$$ and you can take it from there.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.