17.8 Examples of the Chi-Square Distribution

The Chi-Square ($\chi^2$) distribution is a fundamental probability distribution widely used in statistical hypothesis testing, variance analysis, and goodness-of-fit tests. It is a special case of the Gamma distribution and its shape is determined by a single parameter: the degrees of freedom ($\nu$).

Chi-Square Probability Density Function (PDF)

The mathematical formula for the Chi-Square probability density function is:

$$ f(x; \nu) = \frac{1}{2^{\nu/2} \Gamma(\nu/2)} x^{(\nu/2) - 1} e^{-x/2} \quad \text{for } x > 0 $$

Where:

• $\nu$: Degrees of freedom. This integer value represents the number of independent pieces of information that go into estimating a statistic.
• $\Gamma(\nu/2)$: The Gamma function evaluated at $\nu/2$. The Gamma function is a generalization of the factorial function to complex and real numbers. For positive integers $n$, $\Gamma(n) = (n-1)!$.
• $x$: The value of the random variable. The Chi-Square distribution is defined for non-negative values ($x > 0$).

Examples of Chi-Square Distribution Applications

The following examples illustrate how to use the Chi-Square distribution to solve practical problems.

Example 1: Probability of Total Age Being Less Than a Certain Value

Problem: A sample of 20 individuals is taken, and their ages are assumed to follow a Chi-Square distribution with 15 degrees of freedom. Calculate the probability that the total age of these individuals is less than 30 years.

Solution: Given:

• Degrees of freedom ($\nu$) = 15
• We need to find the probability $P(X < 30)$.

Using a Chi-Square distribution table or a statistical calculator:

$P(X < 30) = 0.9881$

This means there is approximately a 98.81% chance that the total age of the sampled individuals will be less than 30 years, given the assumed distribution.

Example 2: Probability of the Number of Defects in a Batch

Problem: The number of defects in a batch of products is observed to follow a Chi-Square distribution with 8 degrees of freedom. Determine the probability that the number of defects in a batch is less than 12.

Solution: Given:

• Degrees of freedom ($\nu$) = 8
• We need to find the probability $P(X < 12)$.

From Chi-Square tables or a calculator:

$P(X < 12) = 0.8488$

This indicates an 84.88% probability that a batch will contain fewer than 12 defects.

Key Concepts and Applications

The Gamma distribution, which encompasses the Chi-Square distribution as a special case, is a versatile tool applied in various domains:

• Reliability Testing: Modeling the lifespan of components or systems.
• Risk Modeling: Quantifying potential financial losses or project risks.
• Queueing Theory: Analyzing waiting times in systems like call centers or service desks.
• Time-to-Event Analysis: Studying the duration until a specific event occurs (e.g., patient recovery time).

The Chi-Square distribution itself is particularly critical in:

• Engineering: Variance analysis, quality control.
• Environmental Science: Analyzing environmental data for trends or deviations.
• Finance: Modeling volatility, testing hypotheses about financial markets.
• Biology: Goodness-of-fit tests for genetic data, analyzing experimental results.

Further Reading

• Uniform Distribution
• Probability Distributions
• Binomial Distribution

---

Interview Questions on Chi-Square Distribution

Here are some common interview questions related to the Chi-Square distribution:

1. What is the Chi-Square distribution, and how is it related to the Gamma distribution?
2. Explain the Chi-Square PDF formula and the meaning of its parameters ($\nu$ and $\Gamma$).
3. What is the significance of "degrees of freedom" ($\nu$) in the context of the Chi-Square distribution?
4. How do you typically calculate probabilities like $P(X < x)$ or $P(X > x)$ using the Chi-Square distribution?
5. In which types of statistical problems is the Chi-Square distribution commonly applied?
6. How is the Chi-Square test utilized in hypothesis testing?
7. What are the core assumptions that must be met to correctly apply a Chi-Square test?
8. How is the Chi-Square distribution used for variance estimation and hypothesis testing about population variances?
9. Can you describe scenarios where the Chi-Square distribution is valuable for defect analysis or quality control?
10. What is the difference between a Chi-Square distribution and other common distributions like the Normal or t-distribution?