Lecture 14: Location, Scale, and LOTUS | Statistics 110 | Summary and Q&A

TL;DR

This content discusses different probability distributions, including the normal, Poisson, binomial, geometric, and hypergeometric distributions, and explains the concept of the linearity of expectation.

Key Insights

• 🛟 The standard normal distribution serves as a foundation for understanding and calculating properties of other normal distributions.
• 🟰 The mean and variance of the Poisson distribution are equal, which is a unique property among probability distributions.
• ❓ The variance of the binomial distribution can be calculated using different methods, including the principle of linearity of variance.

Transcript

So last time we were talking about standard normal, right? Normal zero one. So just a few quick facts that we proved last time. So our notation is, traditionally it's often called Z, but I'm not saying Z has to be standard normal. Or you have to call standard normal Z, just we often use letter Z for that. If Z is standard normal, then first of all,... Read More

Questions & Answers

Q: What are the properties of the standard normal distribution?

The standard normal distribution has a mean of 0 and a variance of 1. Its PDF is the bell curve, and its CDF is denoted as "Phi."

Q: How can any normal distribution be obtained from the standard normal distribution?

By adding a constant "mu" to the standard normal distribution and multiplying it by a positive constant "sigma," any normal distribution with mean "mu" and variance "sigma squared" can be obtained.

Q: What is the variance of the Poisson distribution?

The variance of the Poisson distribution is equal to its mean value, lambda. Thus, the variance of a Poisson distribution is lambda.

Q: How can the variance of the binomial distribution be calculated?

The variance of a binomial distribution can be calculated as the product of n, the number of trials, p, the probability of success on each trial, and q, the probability of failure on each trial, where q = 1 - p.

Q: What is LOTUS?

LOTUS, or the Law of the Unconscious Statistician, states that the expected value of a function of a random variable X can be obtained by summing the function values multiplied by the probabilities of all possible values of X.

Summary

This video discusses the standard normal distribution and introduces the general normal distribution, which is a shift and scale of the standard normal. It explains the notation and properties of standard normal distribution, including the mean, variance, and moments. It also introduces LOTUS (Law of the Unconscious Statistician) and uses it to compute the variance of the Poisson and binomial distributions. Finally, it discusses the 68-95-99.7% rule for the standard normal distribution and provides an overview of LOTUS.

Questions & Answers

Q: What is the mean and variance of a standard normal distribution?

The mean of a standard normal distribution is 0, and the variance is 1.

Q: What is the notation used for the cumulative distribution function (CDF) of a standard normal distribution?

The standard notation for the CDF of a standard normal distribution is capital Phi.

Q: How is the mean of a standard normal distribution computed?

The mean of a standard normal distribution is computed by symmetry. Since the distribution is symmetric about 0, the mean is 0.

Q: What is the third moment of a standard normal distribution?

The third moment of a standard normal distribution, E(Z^3), is 0 due to the symmetry.

Q: What is the formula for standardizing a random variable X that follows a normal distribution with mean mu and variance sigma^2?

The formula for standardizing X is (X - mu) / sigma, where mu is the mean and sigma is the standard deviation.

Q: How is the PDF of a general normal distribution obtained from the PDF of a standard normal distribution?

The PDF of a general normal distribution can be obtained by multiplying the PDF of a standard normal distribution by the standard deviation and adding the mean.

Q: What is the 68-95-99.7% rule for the standard normal distribution?

The 68-95-99.7% rule states that in a standard normal distribution, approximately 68% of the values fall within 1 standard deviation of the mean, approximately 95% fall within 2 standard deviations, and approximately 99.7% fall within 3 standard deviations.

Q: How can the variance of a binomial distribution be calculated using LOTUS?

The variance of a binomial distribution can be calculated by first finding the second moment (E(X^2)) using LOTUS, then subtracting the square of the mean. The formula for the variance of a binomial distribution is np(1-p), where n is the number of trials and p is the probability of success on each trial.

Q: What is the proof for LOTUS in the case of a discrete sample space?

LOTUS can be proven for a discrete sample space by considering the two different ways to write the expected value of g(X). One way is to sum g(X)P(X=x) over all possible values x, and the other way is to first group together all pebbles with the same x value and then sum g(X)P(x).

Summary & Key Takeaways

• The content begins by discussing the properties and notation of the standard normal distribution, including its probability density function (PDF), cumulative density function (CDF), mean, and variance.

• It then introduces the general normal distribution and explains how any normal distribution can be obtained by adding or multiplying constants to the standard normal distribution.

• The content proceeds to derive the mean and variance of the Poisson distribution, which is lambda, and explains that the mean equals the variance in the case of the Poisson distribution.

• Next, the variance of the binomial distribution is calculated using different methods, including the principle of linearity of variance.

• The content mentions that the variance of the hypergeometric distribution will be covered in future sessions.

• Finally, the concept of linearity of expectation is explained through examples of the sum of indicator random variables, and the proof of LOTUS (Law of the Unconscious Statistician) is discussed.