Derivative of cumulative function

  • Context: Undergrad 
  • Thread starter Thread starter toltol
  • Start date Start date
  • Tags Tags
    Derivative Function
Join the discussion
Registration is free. Ask a follow-up in this thread, or start your own.
4 replies · 4K views
toltol
Messages
3
Reaction score
0
Hi everybody,

Can someone tell me the formula to I should use to find the derivative of the following function, with respect to x:

F(x)=Probability[Y<=g(x)]

dF(x)/dx = ??

Thank you for your help.

Toltol
 
Last edited:
Physics news on Phys.org
Well, first step, let h(y) be the density function for Y, and let H(y) be the cumulative distribution function for Y. Now we have
F(x)=P(Y<=g(x))
=[tex]\int_{-\infty}^{g(x)} h(y) dy[/tex]
=H(g(x))
Now, can you differentiate that?
 
Thank you mXSCNT.

If F(x)=P[Y<=g(x)]=H[g(x)]

Thus, the derivative is:

F'(x)=dH[g(x)]/dg(x) . dg(x)/x

The term dH[g(x)]/dg(x) is >0; Thus, the sign of F'(x) is the sign of dg(x)/x.

Am I ok?

Thank you,
Toltol
 
H'(g(x)) g'(x) = h(g(x)) g'(x)
 
Thank you mXSCNT.

It's OK.