Lecture 5 Flashcards

1
Q

What does the null hypothesis basically say?

A

There is no difference

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

What does the alternative hypothesis say?

A

There is a difference

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

What is a Type 1 error?

A

False Positive: rejecting the null hypothesis when it’s true

IOW: There’s no difference but you wrongly say that there is.

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

What is a Type 2 error?

A

False Negative: failing to reject the null hypothesis when it’s false

IOW: There’s a difference but you wrongly say there isn’t

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

What data do parametric statistics analyze?

A

Quantitative

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

What are examples of parametric statistics?

A

t-test, ANOVA, Pearson correlation, linear regression

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

When do we use parametric statistics?

A
  • Data must meet assumptions for the model to be correct
  • Based on one of the distributions so the data needs to be normalized
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What data is non-parametric statistics used to analyze?

A

Qualitative data

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

What are examples of non-parametric statistics?

A

Spearman rho, Mann Whitney U, Friedman’s ANOVA, Wilcoxon-signed ranks

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

When do we use non-parametric statistics?

A
  • When we have violated assumptions
  • When we have nominal or ordinal data
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is a linear regression?

A

One predictor variable and one outcome variable

  • significant relationship if the slope does not equal 0
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What are the 5 parametric assumptions for t-test or one-way ANOVA?

A
  1. I/R Data
  2. Normality
  3. Homogeneity of Variance (HOV)
  4. Free of Extreme outliers
  5. Independence of observations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are 3 ways to test for normality?

A
  1. Histograms
  2. Skewness/kurtosis
  3. Shapiro-Wilk Test
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

When does skewness/kurtosis tell you normality is NOT met?

A

if skewness/kurtosis is >2 or <-2

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

When does Shapiro-Wilk tell you normality is met?

A

If the significance is >.05

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

When is HOV not an issue?

A

In repeated measures test

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What does HOV mean?

A

In designs looking for differences, the variances of the outcome variable should be about the same in each group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

How do you test for HOV?

A

Levene’s Test

MET = >.05

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Why must your data be free of influential outliers?

A
  • For t-test or ANOVA: it will pull the mean toward the outlier
  • For regression: it will pull the best-fit line towards the outlier
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What are 4 ways to test for influential outliers?

A
  1. Histogram
  2. Skewness/kurtosis
  3. Boxplots
  4. Regression: Cook’s Distance
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

When will Cook’s Distance tell you that “Free of Influential Outliers” assumption is NOT MET?

A

if > 1

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What does independence of observations mean?

A

Data has to be independent & can’t follow a pattern over time

Scores from one participant can’t influence another participant’s scores

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What are 3 regression assumptions?

A
  1. Linearity
  2. Homoscedasticity
  3. Outlier testing in regression
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

HOV for ___ stats
Homoscedasticity for ____ stats

A

HOV: difference stats
Homoscedasticity: relationship stats

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

If the variance is not evenly distributed, this is called?

A

Heteroscedasticity

26
Q

Based on linearity: the model is a linear model, so the data must be ____

A

Linear

27
Q

What is the easiest way to check for linearity?

A

Scatterplot

Tells you if the data points are mostly in a straight line

28
Q

What is a residual?

A

The difference between the observed score and the predicted score (the line)

29
Q

If you have curvilinear data, can you use a linear model?

A

No, lots of error

30
Q

What type of graph is also used to check for homoscedasticity and outliers?

A

Scatterplots

31
Q

An outlier will have a ____residual

A

Large

32
Q

After we determine every data point’s residual scare, we have to determine the ________

A

Standardized residual

similar to z-score AKA distance from the line in terms of standard deviations

33
Q

UH OH! You violated an assumption. What are some possible solutions?

A
  1. Trim the data
  2. Windsorizing
  3. Transform the data
  4. Analyze with Bootstrapping in SPSS
  5. Use non-parametric stats
34
Q

Which of these are good and bad?

  1. Trim the data
  2. Windsorizing
  3. Transform the data
  4. Analyze with Bootstrapping in SPSS
  5. Use non-parametric stats
A

1-3 BAD

4-5 GOOD

35
Q

What is it called when I delete a certain number of percentage of scores from the extremes?

A

Trim the data

36
Q

What is it called when I substitute outliers with the highest value that isn’t an outlier?

A

Windsorizing

37
Q

What is it called when I apply a log transformation to the scores in hopes of improving normality but then I’m not actually studying the data?

A

Transform the data

38
Q

What is a hypothesis test?

A

Statistical method that uses sample data to evaluate a hypothesis about a population

39
Q

What is the goal of a hypothesis test?

A

To rule out change (sampling error) as plausible explanation for the results from a research study

40
Q

The alpha level determines the risk of a Type ____ error

A

Type 1 Error

41
Q

The critical region consists of the outcomes that are very unlikely to occur if ____ hypothesis is true.

A

Null

because Null says no difference so it doesn’t want effect to be in the critical region

42
Q

The middle 95% is if Ho is _____ AKA ______ change

A

Ho is true
No change

43
Q

If the t-statistic is in the critical region, do we reject the null hypothesis?

A

Yes

44
Q

alpha level vs. p value

A

alpha: set in advance/pre-set significance

p-value: actual probability that the results occurred just because of sampling error

45
Q

The hypothesis test is influenced not only by the _____ and the _____ of the sample but also the _____ of the sample

A

The hypothesis test is influenced not only by the size of the treatment effect and the Variability of the sample but also the size of the sample

46
Q

Cohen’s d is a measure of _____

A

Effect size

47
Q

What are 2 ways to increase ES?

A
  1. Increase the mean difference (numerator)
  2. Decrease the standard deviation (denominator)
48
Q

What is the effect “size” for each of the below cohen’s D?

d = .2
d = .5
d = .8

A

d = .2 Small Effect
d = .5 Medium Effect
d = .8 Large Effect

49
Q

What is power?

A

Probability the statistical test will reject the null hypothesis when the treatment does have an effect

50
Q

What are 4 ways to increase power?

A
  1. Increase ES
  2. Increase sample size
  3. Increase the alpha
  4. Use a 1-tail test
51
Q

What is an independent t-test?

A

compares 2 means based on independent data

e.g. data from different groups of people

52
Q

What is a dependent t-test?

A

Repeated or Paired

compares 2 means based on related data

e.g. pre-post testing; matched samples or twins

53
Q

If SPSS tells you your sig. or p value is .0000, what should you do?

A

NEVER write this, it’s never 0

Write <.0005 or smaller

54
Q

What is the statistical advantage for repeated measures t-test over independent t-test?

A

Less error because you use the same person and test them twice

55
Q

What is the non-parametric equivalent for independent t-tests?

A

Mann Whitney U-Test

56
Q

What is the non-parametric equivalent for repeated measures t-test?

A

Wilcoxon signed ranks test

57
Q

Which non-parametric test is more powerful?

A

Mann-Whitney U-Test

different from t-test

58
Q

What data is the non-parametric tests done on?

A

Mean rankings

e.g. both sets of data are put in rank order and the test is done to see if the MEAN ranks are different

59
Q

As you repeatedly test the same dataset, you are more likely to commit a _____ Error

A

Type 1

60
Q

What is the Bonferroni Correction?

A

Divides alpha by the # of tests you plan to run

61
Q

Would you apply Bonferroni here:

12 correlations are to be conducted between SAT scores and 12 demographic variables?

A

Yes