Introduction to the normal distribution | Probability and Statistics | Khan Academy

The normal distribution is a fundamental concept in statistics, crucial for inferential statistics and making data-based inferences. This video aims to provide a deep understanding of the normal distribution, equipping viewers with the knowledge to understand its formula and use it effectively. The accompanying spreadsheet is available for download on Khan Academy.

The normal distribution's formula, which appears complex with Greek letters, represents its probability density function. Sigma (σ) denotes the standard deviation. Unlike discrete distributions, continuous probability distributions require ranges to calculate probabilities, which are represented by the area under the curve. For those familiar with calculus, this involves integrating the probability density function over a specific range.

The Central Limit Theorem states that the sum of many independent trials, even if individual trials aren't normally distributed, tends towards a normal distribution as the number of trials increases. This explains why the normal distribution is observed so frequently in nature and is a good assumption for complex phenomena that are a sum of many independent events.

The normal distribution formula can be rewritten to reveal its components more clearly. It shows how the height of the curve is determined by the mean (μ) and standard deviation (σ). The term 'x minus mu over sigma' represents the z-score, indicating how many standard deviations a point is from the mean. This detailed breakdown helps in understanding how changes in these parameters affect the distribution's shape.

Using a spreadsheet, the video demonstrates how changing the mean shifts the entire bell curve horizontally. Altering the standard deviation affects the spread of the curve; a smaller standard deviation results in a narrower, taller curve (data points are closer to the mean), while a larger one creates a flatter, wider curve (data points are more spread out). The normal distribution, unlike binomial, is defined over the entire real number line, meaning any value has some probability, however small.

For continuous distributions, the probability of an exact value is zero; probabilities are calculated over a range, representing the area under the curve. The cumulative distribution function (CDF) is a tool that provides the area under the curve up to a given x-value (the probability of getting a value less than or equal to x). By subtracting CDF values at two points, one can find the probability of a value falling within that specific range.

The video reinforces the concept of calculating probabilities using the CDF and highlights that approximately 68.3% of data in a normal distribution falls within one standard deviation of the mean. It encourages viewers to interact with the provided spreadsheet to gain intuitive understanding. The integral of the entire normal distribution curve always equals 1, representing 100% of all possible outcomes. The video concludes by encouraging future exploration of how normal distribution applies to various models, including financial ones.