Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Statistics > Types of tests > Flashcards

Types of tests Flashcards

1
Q

Describe the Pearson’s r

A
  • Assessing relationships
  • Most widely used correleation coefficient
  • An effect size, ranges between -1 (perfect negative relationship) to +1 (perfect positive relationship) ((-).1-.3: small effect, (-).3-.5: medium effect, (-).5.-1: large effect)

- Assumptions:

  • Two continuous variables (interval or ratio)
  • Normally distributed data
  • Independent observations
  • Linear relationships
  • Non parametric alternatives: Spearman’s rho, Kendall’s tau, Point Biserial Correlation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Describe Spearman’s Rho and Kendall’s tau

A
  • Assessing relationships
  • The non-parametric alternatives to Pearson’s r
  • Can be used when one or both variables are ordinal or when normality assumptions aren’t met
  • Based on ranks of scores
  • Use Kendall’s tau if many tied ranks!
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Describe the Point Biserial Correlation

A

- Assessing relationships

  • Can be used when one variable is binary and the other is continuous
  • Calculated using Pearson’s r formula
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Describe the linear regression

A
  • Exploring predictions
  • Used to predict the value of a continuous outcome variable using the value of a single (continuous) predictor variable
  • Assumptions:
  • linear relationships
  • two continuous variables
  • Normal distribution

- Independent observations

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

Describe the independent t-test

A
  • Assessing differences, 2 groups, independent design
  • Tests whether means differ for two independent groups that we have collected data for (e.g. average grades of AU and CPH psychology students)
  • Assumptions:
  • Outcome variable (DV) must be continuous
  • Grouping variable (IV) must be categorical and binary (2 categories)
  • Normally distributed DV data
  • Groups must be mutually exclusive

- Homogeneity of varaince (similar spread of scores around the mean)

  • Test statistic: t
  • Effect size: r or d
  • Non-parametric alternative: Mann-Whitney U test
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Describe the Mann-Whithey U test

A
  • Assessing relationships - independent designs

- Non-parametric alternative to an independent t-test!

  • Tests whether medians differ for two independent groups that we have collected data for (e.g. average grades of AU and CPH psychology students)

- Can be used when you have ordinal data or non-normal continuous data

  • Uses medians instead of means
  • Test statistic: U statistic
  • Effect size: r
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Describe the dependent t-test

A
  • Assessing relationships - repeated measures designs
  • Tests wheter the means for two conditions differ within a single group (e.g. psychology student’s grades in statistics vs work psychology)
  • Assumptions:
  • Outcome variable (DV) must be continuous
  • Grouping variable (IV) must be categorical and binary (2 categories)
  • Normally distributed sampling distribution of differences
  • Each participant must be in both conditions!

- Test statistic: t

  • Non-parametric alternative: Wilcoxon signed-rank
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Describe the wilcoxon signed rank-test

A
  • Assessing relationships - repeated measures designs

- Non-parametric alternative to a dependent t-test!

- Can be used when you have non-normal continous data or ordinal data

  • Converts all raw data into ranks

- Uses medians instead of means

  • Test statistic: T (sum of positive ranks)
  • Effect size: r​
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Describe the independent ANOVA

A
  • Assessing relationships - independent designs
  • tests whether means differ for 3+ independent groups that we have collected data for (e.g. average grades of AU, CPH and Odense psychology students)
  • an omnibus test (tells us if there are differences, but doesnt specify which means differ)
  • Test statistic: F

- Assumptions:

  • Outcome variable (DV) must be continuous
  • Normal sampling distribution (in each group)
  • 3+ levels of groups variable (IV)
  • Groups must be mutually exclusive
  • Homogeneity of variance
  • If significant F: Follow up with post-hoc bonferroni test (t-test comparisons between all groups)

- Non-parametric alternative: Krustal-Wallis test

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

Describe the Kruskall-Wallis test

A
  • Assessing relationships - independent design

- The non-parametric alternative to an independent ANOVA!

  • Can be used to test whether medians differ for 3+ independent groups that we have collected data for (e.g. grades of AU, CPH, Odense psychology students)
  • Can be used when you have non-normal continuous data or ordinal data
  • Converts all raw data into ranks before analysing them
  • Test statistic: H

- Significant H-test: follow up with non-parametric post hoc tests (Mann-Whitney U)

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

Describe the dependent (repeated-measures) ANOVA

A
  • Assessing relationships - repeated measures design
  • Tests whether means differ between 3+ conditions that we have collected data for (e.g. average mean grades for the same AU students in semester 1, semester 2, semester 3)
  • An omnibus test (tells us if there are differences, but doesn’t specify which means differ)
  • Assumptions:
  • Outcome variable (DV) must be continuous
  • Normal sampling distribution
  • 3+ levels of grouping variable (IV)
  • Sphericity

- Test statistic: F

  • If F is significant: Follow up with post-hoc bonferroni tests

- Non-parametric alternative: Friedman’s test

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

Describe the Friedman’s test

A
  • Assessing relationships - repeated measures design

- The non-parametric alternative to a dependent ANOVA!

  • Can be used to test whether medians differ for 3+ conditions that we have collected data for (e.g. grades of the same AU students in 1st, 2nd and 3rd semester)
  • Can be used when you have non-normal continuous data or ordinal data
  • Converts all raw data into ranks before analysing them
  • Test statistic: x2
  • Significant x2: follow up with non-parametric post hoc test (Wilcoxon signed rank)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Describe the Chi-Square test

A
  • Exploring categorical associations
  • Can be used to examine whether, and how, two categorical variables are associated (e.g. what association, if any, exists between political affiliation (democrat/republican) and support for the death penalty (for/against)?)
  • Non-parametric

- test statistic: χ​2

  • DF: (no of rows-1)*(no of coloums-1)
  • Effect size: Odds ratio for 2x2 (SPSS: Risk), Cramer’s V for larger
  • Assumptions:
  • 2 categorical variables (non-parametric)
  • Mutually exclusive categories (independence)
  • For 2x2 tables, expected frequencies must not be <5
  • For larger tables, all expected frequencies must be at least 1, with no more than 20% of cells in the contingency table having expeted frequency <5
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the non-parametric alternative for an independent t-test?

A

The Mann-Whitney U test

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

What is the non-parametric alternative for a dependent t-test?

A

The Wilcoxon-signed rank test

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

What is the non-parametric alternative to an independent ANOVA?

A

The Krustal-Wallis H test

17
Q

What is the non-parametric alternative to a repeated ANOVA?

A

The Friedman’s test

18
Q

What is What is the non-parametric alternative to a Pearson’s correlation?

A

Spearmans Rho or Kendalls Tau (Tau if small sample, many tied ranks)

Statistics (4 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions