Impossible to find the quantile of any equation

  • Context: High School 
  • Thread starter Thread starter Addez123
  • Start date Start date
  • Tags Tags
    Impossible
Click For Summary
SUMMARY

The discussion centers on finding the quantile of the probability density function defined by \( f(x) = 2xe^{-x^2} \). The user initially attempted to solve for the .5 quantile by setting \( F(x) = .5 \) but encountered issues due to taking the natural logarithm of a negative number. The resolution involved recognizing the need for a definite integral, specifically \( F(x) = -e^{-x^2} |_0^x \), which correctly leads to the expression \( -e^{-x^2} + 1 = 0.5 \). This clarification emphasizes the importance of defining the limits of integration when working with cumulative distribution functions.

PREREQUISITES
  • Understanding of probability density functions (PDFs)
  • Familiarity with cumulative distribution functions (CDFs)
  • Knowledge of definite integrals in calculus
  • Ability to manipulate exponential functions and logarithms
NEXT STEPS
  • Study the properties of probability density functions and cumulative distribution functions
  • Learn how to compute definite integrals for various functions
  • Explore the concept of quantiles in statistical distributions
  • Investigate the implications of using logarithmic functions with negative values
USEFUL FOR

Mathematicians, statisticians, data scientists, and students studying probability theory and statistics will benefit from this discussion.

Addez123
Messages
199
Reaction score
21
TL;DR
Find the .5 quantile (which is same as median for continuous functions?) given the distribution function:
$$f(x) = 2xe^{-x^2}$$
Given the distribution function
$$f(x) = 2xe^{-x^2}$$
The probability density function would then be
$$F(x) = -e^{-x^2}$$

To find the .5 quantile I set F(x) = .5
$$.5 = -e^{-x^2}$$
$$ln(-.5) = -x^2$$

And already here we have the issue, you can't take ln of a negative number.
 
Physics news on Phys.org
Think I solved it. Issue was I wasn't solving the definitive integral, aka. I wasn't solving the integral with any specific range. Should've solved
$$F(x)= −e^{−x2} |_0^x \Leftrightarrow -e^{-x^2} + 1 = 0.5$$
 
Previous answer deleted. I was confused by your terminology.

##f(x)## is a density, provided you include the restriction that ##x \geq 0##, and ##F(x)## is the cumulative distribution, which is ##\int_0^x f(t) dt##.

Sometimes the term "distribution" is used for the cumulative distribution function F(x), but it is never called a "probability density".

So you are correct, you need to do a definite integral starting at 0, which will give you the correct expression.
 

Similar threads

  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K
  • · Replies 3 ·
Replies
3
Views
1K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 9 ·
Replies
9
Views
2K
  • · Replies 2 ·
Replies
2
Views
2K
  • · Replies 3 ·
Replies
3
Views
3K