Hyp Testing, Crosstabs, and Chi-square

Hyp Testing, Crosstabs, and Chi-square - Hypothesis Testing...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
Hypothesis Testing Hypothesis Testing Formulate H 0 and H 1 Choose Significance Level Select Appropriate Test Data Collection Determine Critical Value Compare the Probability Reject or FTR
Background image of page 1

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

View Full DocumentRight Arrow Icon
Hypothesis Testing Steps: Hypothesis Testing Steps: The Basics The Basics Null hypothesis (H 0 ) - statement of no difference or no effect it's the status quo Step 1: Formulate H 0 & H 1 ex. Using age to predict bottled water intake Alternative (H 1 ) - some difference or effect is expected opposite of the status quo
Background image of page 2
Null hypothesis (H 0 ) - age has no effect on bottled water intake. H 0 & H & H 1 Alternative (H 1 ) - younger consumers (< 30 years) drink significantly more bottled water than older consumers ( 30 years). Next question: if there is a difference, is it: statistically significant ???
Background image of page 3

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

View Full DocumentRight Arrow Icon
Significance Basics Significance Basics o Significance Level: specifies the probability at which you are willing to risk an incorrect conclusion . α = .05 means that it's acceptable to commit a Type I error 5 times out of 100 i.e., the probability of making a Type I error:
Background image of page 4
Types of Errors: a. Type I ( α )- probability of rejecting a true null "finding an effect when there isn't one" "a false positive" saying age makes a difference in bottled water intake when it really doesn't Significance Basics Significance Basics
Background image of page 5

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

View Full DocumentRight Arrow Icon
Power (1- β ) - rejecting a false null "finding an effect when it exists" b. Type II ( β ) - probability of FTR a false null "missing an effect when it exists" "false negative" saying age doesn't make a difference in bottled water intake when it really does n = (1 - β ) Significance Basics Significance Basics
Background image of page 6
Frequencies Frequencies - using percentages to test a relationship - 79% of those < 30 drink bottled water Cross-Tabs Cross-Tabs Cross Cross - - Tabulation Tabulation - - cross classifies categories of one variable with the categories of one or more others. describes two or more variables Ordinal Data or Less: Ordinal Data or Less:
Background image of page 7

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

View Full DocumentRight Arrow Icon
Cross-Tabs Cross-Tabs row by column analysis of the frequency counts Independent Variables: Column (Banner) Dependent Variable(s): Row (stubs) Sampling: need 5 expected observations per cell Age: < 30 30 total Drink: yes 79 43 122 no 21 57 78 total 100 100 200
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 28

Hyp Testing, Crosstabs, and Chi-square - Hypothesis Testing...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online