Planned VS Post-Hoc Contrasts and Exam Details Flashcards

1
Q

RECAP

A
  • ANOVA is used to find if IV effects performance on a DV (ie. finding a needle in a haystack; WHERE specifically is the effect? between who?)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

CONTRAST MEANINGS

A
  • they’re like co-ordinates; here’s a needle (0, -1, 0, 0), while here there is none (0, 0, -2, -1)
  • they enable you to hone in and ask detailed questions about result patterns
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

CONTRAST CLASSES

A
PLANNED/A PRIORI/PLANNED COMPARISONS:
- designed before experimenter sees data
UNPLANNED/POST-HOC/A POSTERIORI: 
- devised after experimenter sees data
- difs must be much larger here than in planned; it is possible to find STATSIG if planned BUT always non-STATSIG if they only thought of looking at effect after
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

CC: PROCEDURES

A
PLANNED:
- calculated via previous work
UNPLANNED:
- Newman/Keul's
- Duncan's Multiple Range
- Tukey's
- Dunnett's
- Bonferroni's
- Scheffe's
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

CC-P: SCHEFFE’S

A

VIRTUES:

  • easy calculations
  • if Scheffe is STATSIG, so are the others, making them unnecessary
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

CC-P-S: PROCEDURE

A
  1. Select contrast weights and do as you would in a planned contrast.
  2. Use Scheffe’s code.
  3. Ignore Sig. column if results.
  4. Calculate Scheffe criterion (ie. 5xF(5, 12)
  5. Find F in ELE table (ie. 5x3.106=15.53)
  6. Calc F-ratio = STATSIG if computed value is >/= of Schaffe’s criterion (ie. 9.600<15.53 = NOT STATSIG! at post-hoc check)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

CC-P-S: SCHEFFE’S CRITERION

A

(k-1) x Tabled value of F(k-1, error df)

  • k = number of levels in examined factor
  • error df = degrees of freedom of denominator of original ANOVA
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

CC-P-S: SCHEFFE’S CODE

A
UNIANOVA
score BY group
/contrast(group)=special(-1, 0, 1, 0, 0, 0)
/METHOD = SSTYPE(3)
/INTERCEPT = INCLUDE
/CRITERIA = ALPHA(.05)
/DESIGN = group
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

CONTRAST PARADOX

A
  • EG contrast (9.600) is STATSIG if planned as comparison in advance (9.600>p.009) BUT not STATSIG if comparison was not planned (9.600<15.53)
  • THIS MAKES SENSE! strange but a result can be both STATSIG/not STATSIG
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

CP: NULL HYPOTHESIS DISTRIBUTION

A

NHD = distribution of outcomes to be expected if there are no genuine differences between the groups
IMAGINE…
- if EG scores were imaginary (but groups the same), SPSS may show (say) F (5, 12) = 1.3
- if this were repeated 18 more times, say now its F (5, 12) = .690; now repeat x10,000
- most of x10,000 will be close to 1; 500 of them all will exceed 3.106; this is NHD

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

CP-NHD: EXPLANATION

A
  • if results of real exp were randomly sampled from outcome pop (aka. no genuine effect) then only 5% chance of f-ratio exceeding 3.106
  • BUT if dif is genuine, results wouldn’t be sampled from this pop but rather from the one skewed right, SO high f-values (>3.106) is much more likely
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

CP-NHD: IMPLICATIONS

A
  • if exp has f-ratio of 4.640, outcome can be either:
    1. no genuine dif between 6 groups; f-ratio = chance of rare outcome (<5% of random selection)
    2. genuine dif between 6 groups; working from wrong start assumption assuming no dif; f-ratio = could easily reappear on bulk of repetitions
  • 1 forces assumption of rarity, so sensible to reject it; this means rejecting NHD and accepting experimental hypothesis (EH)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

STATISTICAL ERRORS

A
- classical testing has inbuilt possibility of two error types in decision process:
TYPE 1: 
- no dif pop sampled
- f-ratio = higher via chance
- reject NHD; accept EH
TYPE 2:
- genuine dif pop sampled
- f-ratio = lower via chance
- accept NHD; reject EH
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

SE: IMPLICATIONS

A
  • T1 risked every time NHD rejected; built into testing procedure (one 5% criterion test = 5% T1 chance; twenty tests = higher T1 chance; at least once conclusion = misleading)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

PLANNED/POST-HOC RELATIONSHIPS

A
- correction for both requires raised bar via using more stringent statistical criterion
PLANNED:
- single test; 5% T1 
- comfortably low
POST-HOC:
- interesting pattern hunt; 5-15 tests
- inflated T1 chance
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

STILL UNCONVINCED BY LOGIC?

A
  • if i wrote down next week’s lottery, you’d be impressed
  • if i borrowed world pop and got a person to write down 1-6, the next 1-7, etc., then found the winner after drawing, you wouldn’t be as impressed
  • same rule applies