COMM 162 Lecture Notes - Lecture 6: Binomial Distribution, Probability Mass Function, Random Variable

• School: Queen's University
• Department: Commerce
• Course: COMM 162
• Professor: Tatsiana Levina

Document Summary

Review: types of data sampling: non-probabilistic, judgemental, convenience, snowball, self-selection, quota, probabilistic, simple random sampling, systematic, stratified, cluster. Random variable: a rule or function that assigns a numeric value to the outcomes of a random experiment, ex. When tossing a die, we may count the numbers of dots (x: x is particular outcome of random variable x, p(x) is probability of this particular outcome. Continuous random variables: we characterize random variables with probability distributions, discrete random variables are used with countable data, described by tables or probability mass functions, continuous random variables are used with uncountable data, described by probability density functions. Properties of discrete distributions: mean/expected, e(x) = u = sum x*p(x, population variance, v(x) = o^2 = sum (x-u)^2*p(x, shortcut: v(x) = o^2 = sum x^2*p(x) u^2. Types of distribution: countable (discrete, whole items (people, cars, etc. , uncountable (continuous, infinitely divisible (time, water, etc. )