Week 3 & 4 Flashcards

1
Q

Parametric

A

assess group means
normal distribution
can deal with unequal variances across groups
generally more powerful

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

non-parametric

A

assesses group medians
don’t require normal distribution
can handle small sample size

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

parametric test assumptions

A

additivity and linearity
normality
homogeneity of variance
independence of observations

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

additivity and linearity

A

outcome is a linear function of the predictors X1 and X2, and the predictors are added together
outcome y is an additive combination of the effects of X1 and X2

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

Assessing linearity

A

observed vs predicted values (symmetrically distributed around diagonal line)
residuals vs predicted values (symmetrically distributed around horizontal line)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

fixing non-linearity

A

apply non linear transformation to variables
add another regressor that is a nonlinear function (polynomial curve)
examine moderators

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

central limit theory

A

as the sample size increases towards infinity, the sample distribution (NOT DATA) approaches normal distribution

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

skewness

A

how symmetrical the data is
positive: scores bunched at low values, tail pointing to high values
negative: scores bunched at high values, tail pointing to low values

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

kurtosis

A

how much the data clusters either at the tails/ends or peak of the distribution

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

leptokurtic

A

heavy tails

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

platykurtic

A

light tails

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

normality checks

A

Q-Q plot compares sample quantiles to quantiles of normal distribution; normal= forms straight line
Shapiro wilkes test: tests if data differs from normal distribution; normal=p>.05, data does not vary significantly from a normal distribution
histogram

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

homogeneity of variance

A

all groups or data points have same or similar variance
equal distribution above and below horizontal line on residual vs predicted plot= homoscedasticity
heteroscedasticity would be cone shapes

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Independence

A

residuals unrelated
if non-independent: downwardly biased SE (too small) and incorrect statistical inference (p values <.05 when they should be >.05)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Univariate outlier

A

outlier when considering only the distribution of the variable it belongs to
bias mean and inflate SD

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Bivariate outlier

A

outlier when considering the joint distribution of two variables

17
Q

Multivariate outlier

A

outliers when simultaneously considering multiple variables, difficult to assess using numbers or graphs
bias relationship between two variables e.g. change strength

18
Q

changing the data= winsorizing

A

next highest value plus some small number
z score of +/- 3.29
mean plus 2 or 3 SDs
percentile of distributions

19
Q

winsorizing

A

a predefined quantum of the smaller and/or largest values are replaced by less extreme values

20
Q

linear transformations

A

adding constant to each value
converting to z score (x-m)/SD
mean centering (x-m)

21
Q

non linear transformations

A

log, log (x) or In (x)
square root of x
reciprocal, 1/x

22
Q

log (x)

A

reduce positive skew and stabilise variance
positive values >0

23
Q

square root of x

A

reduce positive skew and stabilise variance
zero and positive values

24
Q

1/x

A

reduce impact of large scores and stabilise variance
score reversal can be avoided by reversing before transforming: 1/(xhighest-x)

25
variance
average squared distance from mean linked to sum of squares
26
covariance
how much two variables differ from their means linked to sum of cross products
27
correlation coefficient
standardised version of covariance divide covariance by SD of both variables
28
pearsons correlation assumptions
interval/ratio variables normality linearity
29
coefficient of determination
r^2
30
r^2 in spearmans correlation
proportion of variance in the ranks that the two variables share
31
partial correlations
measure the association between two variables, controlling for the effects that a third variable has on them both
32
semi-partial correlations
part correlation measures the relationship between two variables, controlling for the effect that a third variable has on one of the others
33
zero order correlations
measuring correlation between two variables when not controlling for anything
34
excluding cases pairwise
for each correlation, exclude particiapnts who do not have a score for both vairables
35
excluding cases listwise
across all correlations, exclude particiapnts who do not have a score for each variable
36
linear regression looks at
direction (unstandardised B) magnitude (standardised beta) significance (p<.05)
37
Standardised coefficients (beta)
show the expected SD change in DV for a 1SD change in IV