Approximations

Summary and Exam Tips for Approximations

Approximations is a subtopic of Statistics 2, which falls under the subject Mathematics in the Edexcel International A Levels curriculum. This chapter focuses on using different statistical distributions to approximate others, providing a practical approach to solving real-life problems.

• Poisson Approximation to Binomial: When a binomial distribution $X \sim B(n, p)$ has a large number of trials ($n \geq 50$) and a small probability of success ($np \leq 5$), it can be approximated by a Poisson distribution $X \sim Po(np)$. This is useful when dealing with rare events over a large number of trials.

• Normal Approximation to Binomial: A binomial distribution can be approximated by a normal distribution $X \sim N(\mu, \sigma^2)$ when both $np > 5$ and $np(1-p) > 5$. This requires a continuity correction, where discrete values are adjusted to continuous intervals.

• Normal Approximation to Poisson: For a Poisson distribution with a mean $\lambda > 15$, it can be approximated by a normal distribution $X \sim N(\lambda, \lambda)$. This approximation improves as $\lambda$ increases and also requires a continuity correction.

• Choosing the Appropriate Approximation: Understanding when to use each approximation is crucial. The choice depends on the parameters of the original distribution and the conditions for approximation.

Exam Tips

• Understand Conditions: Memorize the conditions under which each approximation is valid. For example, remember $n \geq 50$ and $np \leq 5$ for Poisson approximation to binomial.

• Continuity Correction: Always apply a continuity correction when approximating a discrete distribution with a continuous one. This involves adjusting the discrete value to a range.

• Practice with Examples: Work through examples to solidify your understanding of when and how to apply these approximations. This will help you quickly identify the correct method during exams.

• Use Diagrams: Visual aids can help in understanding the relationships between different distributions and their approximations.

• Check Assumptions: Before applying any approximation, ensure that all necessary conditions are met to avoid errors in your calculations.