Logistic function: Difference between revisions
No edit summary |
|||
Line 72: | Line 72: | ||
| [[horizontal asymptote]]s || asymptote at <math>y = 0</math> corresponding to the limit for <math>x \to -\infty</math><br>asymptote at <math>y = 1</math> corresponding to the limit for <math>x \to \infty</math> | | [[horizontal asymptote]]s || asymptote at <math>y = 0</math> corresponding to the limit for <math>x \to -\infty</math><br>asymptote at <math>y = 1</math> corresponding to the limit for <math>x \to \infty</math> | ||
|- | |- | ||
| [[inverse function]] || [[inverse logistic function]] given by <math>x \mapsto \ln \left(\frac{x}{1 - x} \right)</math> | | [[inverse function]] || [[inverse logistic function]] or [[log-odds function]] given by <math>x \mapsto \ln \left(\frac{x}{1 - x} \right)</math> | ||
|} | |} |
Revision as of 15:50, 31 May 2014
Definition
The logistic function is a function with domain and range the open interval , defined as:
Equivalently, it can be written as:
For this page, we will denote the function by the letter .
We may extend the logistic function to a function , where and .
Probabilistic interpretation
The logistic function transforms the logarithm of the odds to the actual probability. Explicitly, given a probability (strictly between 0 and 1)of an event occurring, the odds in favor of are given as:
This could take any value in
The logarithm of odds is the expression:
If equals the above expression, then the function describing in terms of is the logistic function.
Functional equations
Symmetry equation
The logistic function has the property that its graph has symmetry about the point . Explicitly, it satisfies the functional equation:
Differential equation
The logistic function satisfies the condition:
Therefore, is a solution to the autonomous differential equation:
The general solution to that equation is the function where . The initial condition at pinpoints the logistic function uniquely.
Key data
Item | Value |
---|---|
default domain | all of , i.e., all reals |
range | the open interval , i.e., the set |
derivative | the derivative is . If we denote the logistic function by the letter , then we can also write the derivative as |
second derivative | If we denote the logistic function by the letter , then we can also write the derivative as |
logarithmic derivative | the logarithmic derivative is If we denote the logistic function by , the logarithmic derivative is |
critical points | none |
critical points for the derivative (correspond to points of inflection for the function) | ; the corresponding point on the graph of the function is . |
local maximal values and points of attainment | none |
local minimum values and points of attainment | none |
intervals of interest | increasing and concave up on increasing and concave down on |
horizontal asymptotes | asymptote at corresponding to the limit for asymptote at corresponding to the limit for |
inverse function | inverse logistic function or log-odds function given by |