Soc%20005%20-%20Lecture%203_1

# Soc%20005%20-%20Lecture%203_1 - SOCIOLOGY 005 Lecture 3...

This preview shows pages 1–8. Sign up to view the full content.

SOCIOLOGY 005 Lecture 3 Inferential Statistics Often times we are interested in estimating values within the population based upon a sample We usually do this because we do not have a census of a population and because it is more cost effective But in order for us to “infer” a population value, we need to engage in employ some kind of random sample

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Inferential Statistics Before discussing more about inference, we need know how sample statistics correspond to population parameters s Y 2 ! Y 2 Mean Variance Std. Dev. s Y Y Y μ Y Sample Population Inferential Statistics When we are looking at particular observations or outcomes within a population, we can talk about them in terms of what was the probability of a particular observation occurring We refer to the distribution of probabilities of observing an outcome as a probability distribution
Inferential Statistics Continuous probability distributions Since the underlying distribution is continuous, we look at areas between two outcomes when assessing the probability of an a particular outcome We call the probability of observing a score in between these two points (alpha) ! Inferential Statistics p ( a ! Y ! b ) = " Alpha

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Inferential Statistics A normal distribution has several unique characteristics It is unimodal Its mean, median, and mode equal one another We can calculate probabilities of observing a score based upon the symmetric nature of the curve based upon Z-scores The Normal Distribution The Normal Distribution !" + ! 68% ! Z " Z ! 95% ! 2 Z 2 Z 99.7% ! 3 Z 3 Z μ = 0 100% = .68
The Normal Distribution We can also look at the probability that a score is observed μ = 0 1.67 The Normal Distribution ...or the area of a tail of a normal distribution which is cut off by a given z-score (alpha area) = 0 1.67 p ( Z ! Z " ) =

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
The Normal Distribution μ = 0 1.67 What is the probability we’ll observe a score higher than 1.67 from the population mean? Z-Score Area from 0 to Z Area from Z to InFnity 1.66 0.4515 0.0485 1.67 0.4525 0.0475 { For these numbers, we need to consult a table Critical Value: Minimum value to designate an alpha area Central Limit Theorem Now that we know something about normal distributions, we can use this knowledge to infer values of a sample to a population. The central limit theorem states: “If all possible random samples of N observations are drawn from any population with a mean and variance , then as N grows larger, these sample means approach a normal distribution, with mean and variance . ! Y 2 Y Y Y 2 N
Say we have a population of college students. .. And we ask them how many times have they have been intoxicated over the last two months. .. Central Limit Theorem want to take a sample.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 10/23/2011 for the course SOC 10 taught by Professor Dunn during the Spring '10 term at UC Riverside.

### Page1 / 30

Soc%20005%20-%20Lecture%203_1 - SOCIOLOGY 005 Lecture 3...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online