91Ó°ÊÓ

The Cumulative Distribution Function (CDF) is a crucial concept in probability theory, providing a way to describe the probability that a random variable takes on a value less than or equal to a specific point. For a given distribution, the CDF is essentially the area under the probability density function (PDF) up to a point, reflecting the cumulative probability of the variable being less than or equal to that point. This makes it a powerful tool for calculating probabilities and understanding the behavior of random variables over an interval.
To derive the CDF from the probability density function provided, which is \( f(x; \theta, \tau) = \frac{\theta}{\tau} (1 - x/\tau)^{\theta - 1} \), we integrate this PDF from 0 to \(x\). This gives us the expression:

• \( \int_0^x \frac{\theta}{\tau} (1 - u/\tau)^{\theta - 1} \, du = 1 - (1 - x/\tau)^{\theta} \)

This resulting equation represents the CDF, \( F(x; \theta, \tau) = 1 - (1 - x/\tau)^{\theta} \), showing the probability that the waiting time \(X\) is less than or equal to \(x\).
Understanding the CDF is vital as it lets you find probabilities without directly integrating the PDF every time. The CDF grows from 0 to 1 as \(x\) moves from the lower bound to the upper bound of the distribution, offering a complete view of the distribution's pattern.

Skewness is a measure that describes the asymmetry, or lack thereof, of a probability distribution. It's a key characteristic that helps in understanding how different distributions can behave in relation to their mean.
In the context of the provided probability density function \( f(x; \theta, \tau) = \frac{\theta}{\tau} (1 - x/\tau)^{\theta - 1} \), the skewness is primarily influenced by the parameter \(\theta\).

• When \(\theta = 4\), the distribution is considered left-skewed or negatively skewed, indicating that the tail is longer on the left side of the distribution.
• For \(\theta = 1\), the distribution becomes uniform, meaning it shows perfect symmetry with no skewness, as each outcome in the distribution is equally likely.
• Conversely, when \(\theta = 0.5\), the distribution is right-skewed or positively skewed, where the tail is longer on the right side.

These variations illustrate how skewness impacts the shape and spread of the distribution. Understanding skewness helps in predicting probabilities and making informed statistical decisions based on how data might be distributed around its central value.

The median is a statisticians' favorite measure of central tendency, as it represents the value separating the higher half from the lower half of a probability distribution. Unlike the mean, the median is not affected by outliers and skewed distributions.
For the distribution defined by our problem, the median can be found by solving the equation where the cumulative distribution function equals 0.5. This is expressed as \( F(m; \theta, \tau) = 0.5 \). By simplifying the equation:

• \( 1 - (1 - m/\tau)^\theta = 0.5 \)

We find:

• \( m = \tau(1 - (0.5)^{1/\theta}) \)

This formula tells us that median depends both on \(\tau\) and \(\theta\).

• For higher \(\theta\) values, the median tends to move closer to the distribution's maximum bound, indicating a skew towards longer times.
• Conversely, with smaller \(\theta\) values, the median drops, showing that most waiting times may be concentrated towards shorter times.

Understanding the median and how it changes with distribution parameters is essential for interpreting the center of a probability distribution effectively, especially in skewed distributions.