# stats

Mind Map by gatalina95, updated more than 1 year ago
 Created by gatalina95 almost 5 years ago
4
0

anova for stats

## Resource summary

stats
1 one anova
1.1 compares within and between variance
1.1.1 f-ratio
1.2 to report
1.2.1 f(b,w)=...MSE=.... P<.05
1.2.1.1 use smallest p value possible
1.3 compares 2 or more means
1.4 to compute
1.4.1 factor=IV
1.4.1.1 stats >Descriptive and homogeneity
1.4.1.1.1 explore histograms
2 Post-Hoc
2.1 BONFERRONI
2.1.1 0.05/n
2.1.1.1 Family wise error rate 1-(1-0.05)xn
2.2 Tukeys
2.2.1 it tests all conditions
2.2.1.1 click post hoc
2.3 priori
2.3.1 contrast
2.3.1.1 for one way anova
2.3.1.1.1 eg: 2 -1 -1 to opposite signs to compare
2.3.1.1.1.1 or 0. 1 -1
2.3.1.1.1.1.1 not interested in 0
3 REPEATED MEASURES ANOVA
3.1.1 if significant then paired T tests using Bonferroni adjustments
3.1.1.1 if it is one way
3.1.1.1.1 1 Dv ,within participants
3.2 if it is two way
3.2.1 Analyse >GLM>
3.2.1.1 This is to get interaction plus main effect
3.2.1.1.1 Repeated measures again choose one factor > define > choose that you are interested on for the other level
3.2.1.1.1.1 FOR SIMPLE MAIN EFFECT
3.2.1.1.2 Check sphericity if Maunch is significant use Hyung feldt
4 Two way ANOVA
4.1 interaction
4.1.1 The effect one iv varies according to the other iv
4.1.1.1 compares all cell meas
4.2 simple main
4.2.1 one iv has an effect on the dv in one particular conditin of the dv
4.2.1.1 compares all cell means in one condition
4.2.1.1.1 to compute
4.2.1.1.1.1 analyze
4.2.1.1.1.1.1 GLM
4.2.1.1.1.1.1.1 univairate
4.2.1.1.1.1.1.1.1 option descriptives = Marginal means
4.2.1.1.1.1.1.1.1.1 paste syntax
4.2.1.1.1.1.2 for simple main effect
4.2.1.1.1.1.2.1.1 /EE: eg compare (sex)
4.2.1.1.1.1.2.1.1.1 look at univariate test
4.3 main effect
4.3.1 an IV has some effect of the Dv
4.3.1.1 compares marginal means for each condition
5 t test
5.1 uses do compare two means
5.1.1 independent
5.1.1.1 compares two unrelated samples
5.1.1.1.1 between participants
5.1.2 paired sample
5.1.2.1 related
5.1.2.1.1 within participants
5.1.3 one sample
5.1.3.1 compare one sample to pop mean
5.2 assumptions
5.2.1 normally distribution
5.2.1.1 Homogeneity
5.2.1.1.1 if Levene's is significant = not homogenous..
5.3 t (DF)=2.56 , p , . 05
5.3.1 if not significant use actual figure
5.4 To compute
5.4.1 Analyze
5.4.1.1 Descriptives
5.4.1.1.1 explore
5.4.2 compare means
5.4.2.1 paired sample meand
5.4.2.1.1 within
5.4.3 compare means
5.4.3.1 independent t test
5.4.3.1.1 Between
5.4.3.1.1.1 test variable = DV
5.4.4 if you want one level only eg specidic role
5.4.4.1 split file
5.4.4.1.1 organize by group > role
5.4.4.2 select cases
5.4.4.2.1 if role =1
6 3 WAY INTERACTION
6.1 GLM> univariate add 3 factors
6.1.1 if significant look for interaction effects
6.2 L-matrix
6.2.1 remember the order
6.2.2 test results
6.2.3 look at custom Hypothesis test
7 MIXED MODEL
7.1 Analyze-GLM>repeated measures
7.1.1 Within factors add numbers of levels
7.1.1.1 Define
7.1.1.1.1.1 see test of within and test of between ? look at each separate error
7.2.1 test interaction between 2 at a level of third factor
7.2.2 simple main effect
7.2.2.1 when you want to compare two levels from diff iv eg male patients select cases if gender = 1 if patients = 1
7.2.2.1.1 if I want to compare eg male patients and female patients
7.2.2.1.1.1 split file compare groups and select if role = 1

### Similar

Most Influential People Under 25
ECO 351 - Business Statistics II - Problem Set 2
ANOVA
STATISTICS 1
S2 - Chapter 1 to 5
Statistics Overview
WEEK 4: Path Analysis
Stats
Evaluate Statistical Reports
Research Methods: Multiple Regression
AQA Statistics 1 (GCE)