Home > Preview
The flashcards below were created by user
camturnbull
on FreezingBlue Flashcards.

What does a significant result on the Omnibus test imply?
 The null is false
 The degree to which it is false is not implied

What are omnibus tests?
Types of stats tests that tell us whether or not the explained variance in data is more significantly than the unexplained variance

What is the error rate per comparison (PC)?
The probability of making a type 1 error at any given comparison

What is the familywise error rate (FW)?
 The set of comparisons that are made is called a family according to Tukey
 This is the probability that at least one comparison from a family will contain a type 1 error

What is the error rate for FW?
1(1 the error rate per comparison) x the number of comparisons

How can we control the FW rates?
 Use a more stringent error rate per comparison (such as.025)
 Divide the desired overall significance level by the number of comparisons you plan to make
 Assess the probability associated with each comparison with more stringent value
 This is known as the Bonferroni Method

What is the alternate way of performing the Bonferroni method?
 Multiply the associated probabilities by the number of comparisons
 Compare this to the .05 significance level

For FW, what is the significance rate?
.05

For factorial analysis of variance what are the IV known as?
Factors

For factorial analysis of variance what are the experimental conditions known as?
The levels of the factor

How are factor levels compared?
 Each factor level is compared with every level of the other factors
 This ensures that the design contains every combination of the factorial levels

What is a 3x2x2 design?
There are three factors, one with three levels and two with two

What is the main effect?
The effect of an independent variable on a dependent variable averaging across the levels of any other independent variables

What else do factorials allow us to analyse?
The interaction between variables

