Normal Approximation Aa4769
1. **Problem Statement:**
We want to approximate the probability $P(X \geq x)$ for a binomial random variable $X$ using a normal distribution.
2. **Formula:**
The normal approximation to the binomial uses the mean $\mu = np$ and standard deviation $\sigma = \sqrt{np(1-p)}$ where $n$ is the number of trials and $p$ is the probability of success.
3. **Normal Approximation:**
We approximate $P(X \geq x)$ by
$$P\left(Z \geq \frac{x - \mu}{\sigma}\right)$$
where $Z$ is a standard normal variable.
4. **Continuity Correction:**
Since $X$ is discrete and $Z$ is continuous, apply a continuity correction:
$$P(X \geq x) \approx P\left(Z \geq \frac{x - 0.5 - \mu}{\sigma}\right)$$
5. **Steps to Calculate:**
- Calculate $\mu = np$
- Calculate $\sigma = \sqrt{np(1-p)}$
- Compute the z-score with continuity correction: $z = \frac{x - 0.5 - \mu}{\sigma}$
- Find $P(Z \geq z)$ using standard normal tables or software.
This method provides a good approximation when $n$ is large and $p$ is not too close to 0 or 1.
**Final answer:**
$$P(X \geq x) \approx P\left(Z \geq \frac{x - 0.5 - np}{\sqrt{np(1-p)}}\right)$$