Unit 3 - ANOVAs

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/53

encourage image

There's no tags or description

Looks like no tags are added yet.

54 Terms

1
New cards

Ways to estimate population variance

  • Sample variances by taking variance of each sample then averaging it

  • Sample mean variances by multiplying vairance of means with n (o2 = nox2)


2
New cards

F distribution

Probability curve of variance ratios assuming samples are from the same population

3
New cards

What does the F score mean?

F = explained/unexplained = MSgroup/MSerror

4
New cards

If F = 1

owithin and obetween are similar and they’re both samples from the same population

5
New cards

What happens when groups are from different populations?

obetween will be very difference, creating a large ratio

6
New cards

ANOVAs

Partitions variation into group and error variances to evalulate H0

7
New cards

Other terms for within group variances

Error, residuals

8
New cards

Other terms for between group variances

Groups, conditions

9
New cards

SStotal

Measures total variation/total squared spread of raw data

10
New cards

SStotal Steps

  1. Calculate grand mean

  2. Subtract grand mean from each score

  3. Square

  4. Sum


11
New cards

Differences of scores

Measures variation as it represents how far each number is far from grand mean

12
New cards

Grand Mean

Represents best guess at summarizing data

13
New cards

What is SStotal kinda equivalent to

Stnadard error of a sum, it will continusouly increase as N increase because it’s not averaged

14
New cards

Variance

Average square distance from mean

15
New cards

SSerror

Measures variation with groupos, the unexplained variation

16
New cards

SSerror Steps

  1. Calculates group mean

  2. Subtract the group mean from each score

  3. Sum the square deviations


17
New cards

SS group

Number of variation that’s from difference between the mean/variation that researcher can explain from manipulation

18
New cards

SSgroup Steps

  1. Replace each score within a group with its group mean (gets rid of all within var)

  2. Subtract grand mean from each score

  3. Sum the squares deviation


19
New cards

Mean Squares

SS/df = variance(mean) x n = mean(varerror) => variance

20
New cards

MSerror

Variances of deviations from group means regardless of position

21
New cards

MSgroup

Variances amongst group means with respect to position

22
New cards

Contrast

Specific way to compare group means by giving each group a number to indicate how much each group counts in a substraction problem to compare just the groups you care about

23
New cards

Linear Contrast

Breaks up SSgroup into smaller, specific pieces to look for speicific patterns of difference between groups to evaluate a specific hypothesis to focus statistical power on a particular group

24
New cards

Orthogonal Contrasts

Contrasts are mutually exclusive so that all weights and prod of coeff are 0

25
New cards

Why do the error values remain contrast in linear contrasts?

All data used to calculate regardless of which group because assumes groups are from the same population

26
New cards

k

Number of groups

27
New cards

N

Number of people

28
New cards

n

Number of people per group

29
New cards

t2

F

30
New cards

Why are linear contrasts used?

Focuses statistical power on a particular group because MS tends to be larger from less df so F test is more sensitive

31
New cards

Pairwise Tests

Compares each level of group variables with special t test

32
New cards

Tukey HSD

Evaluates all pairwise (variation of groups) differences between groups and gives CI, difference, p value

33
New cards

As # of tests increases,

Chances of getting a type I error compounds (1 - 0.95#)

34
New cards

How does Tukey HSD accounts for compounding type I errors?

Adjusts individual alpha level and t value so that overall/familywise alpha rate is 0.05

35
New cards

Planned Comparisons

Tests decided before research looks at data

36
New cards

Post-Hoc Comparisons

Tests decided after researcher looks at data and increases type I error because multiple informal tests have already been done

37
New cards

Scheffé Method

Increases Fcritical to control for type I error rate in post-hoc tests

38
New cards

Factorial ANOVAs

Tests the effect of 2+ conditions and how they interact by partitioning IV on DV (SSA,SSB), both IVs on DV (SSA + B) and error (SSerror)

39
New cards

Factorial

Going across the variables

40
New cards

Balanced Factorial Design

Equal n per cell/group

41
New cards

Marginal Mean

Mean of a level/category (condition mean)

42
New cards

SSA and SSB

Variation by factor A and B, equivalent to SSgroup

43
New cards

SSA or B Calculation

  1. Calculate marginal mean

  2. Replace each score with marginal mean for each group for that factor

  3. Sub grand mean and sum squares


44
New cards

Degres of freedome for SSA or B

k - 1

45
New cards

SSinteraction

Variability of factor A and B combined that isn’t explained by either factors alones

46
New cards

SSinteraction Calculation

  1. Calculate each specific cell mean

  2. Replace every entry with its cell mean

  3. Subtract grand mean

  4. Square and sum

  5. Subtract from SStotal or SScells


47
New cards

SSinteraction Degrees of freedom

dfA * dfB

48
New cards

SStotal =

SSA + SSB + SSinteraction + SSerror

49
New cards

SScells =

SSA + SSB + SSinteraction

50
New cards

dferror

N - k

51
New cards

When there are 0 effects

Each MS value is an estimate of o2error and should be similar to MSerror

52
New cards

If an interaction is significant

Effect of A and B goes both ways

53
New cards

Interaction

Effects changes outcomes and makes outcome not consistent across conditions

54
New cards

Crossover Effect

Interaction produces results that swap between conditions