CMST300 Exam 3 Chapter 12
Home > Flashcards > Print Preview
The flashcards below were created by user
calhounk1
on
FreezingBlue Flashcards. What would you like to do?

Inferential statistics
can show how variables relate to one another, help us to draw conclusions about a population based on a sample.

Standard error
The extent to which the sample estimates will be distributed around the population parameter
how close our findings match what we should find in the population
*error decreases as population increases

Assumptions of standard error
 1. Samples must be drawn from a population
 2. Assumes simple random sampling
 3. Assumes 100% completion rate

H_{1}
Hypothesis, Statement that tells us how we expect variables to be related.

H_{0}
Null hypothesis, statement that says there is no relationship.

Type I Error
When Null is true, but is rejected

Type II Error
When null hypothesis is false, but we mistakenly fail to reject.

How do you prevent a type I error?
set a standard for .05

To prevent a type II error
 have a larger sample
 use interval/ratio data
 use a directional hypothesissay it goes one way instead of saying its different

ChiSquare
1 categorical variable
eg. do political ads attack policy or character more often

TTest
 IV: 1 categorical variable with TWO groups
 DV: 1 continuous variable (amount of disclosure)

ANOVA
**Analysis of variance
 IV: 1 categorical variable with 3+ groups
 DV: 1 continuous variable (number of hours on homework)

Correlation
**Test of association
 IV: A continuous variable (exam grade)
 DV: A continuous variable