DRAFT handbook
Software:
1
Introduction
2
Statistics
2.1
Goals of statistical analysis
2.1.1
Description
2.1.2
Assessment of quality
2.1.3
Inference
2.2
General principles of statistical practice
2.2.1
Self-skepticism and humility
2.2.2
Robustness
2.2.3
Parsimony
2.2.4
Transparency
3
Software and organization
3.1
Helpful software or websites
3.1.1
Reference software
3.1.2
Statistical software
3.2
Project organization
4
Basic concepts
4.1
Variability
4.2
Evidence and test statistics
4.3
Significance
4.4
Power
5
2×2 contingency tables
5.1
Readings and Resources
5.2
Example data set
5.3
Visualization
5.4
Assessing the effect size
5.4.1
Yule’s
\(Q\)
coefficient
5.4.2
Difference between proportions
5.4.3
Odds ratio
5.5
Assessing the null hypothesis of no relationship
5.6
A full report
5.6.1
Yule’s
\(Q\)
5.6.2
Difference between proportions
5.6.3
Odds ratio
5.7
Things to watch out for
5.7.1
Probability vs odds
5.7.2
Small cell counts
5.7.3
Dependence between observations
6
General contingency tables
6.1
Readings and Resources
6.2
Example data set
6.2.1
Polychoric correlation
6.3
Things to watch out for
7
One-sample and paired designs
8
Two-sample designs
8.1
Readings and Resources
8.2
Example data set
8.3
Description
8.4
Visualization
8.4.1
Mean/standard error plot
8.4.2
Box plot
8.4.3
Dot or violin plot
8.4.4
Quantile-Quantile (QQ)
8.5
Assessing the effect size
8.5.1
Difference in means
8.5.2
Standardized difference in means
8.5.3
Difference in trimmed means
8.5.4
Data transformations
8.6
Model checks
8.7
Assessing the null hypothesis of no difference
8.8
A full report
8.9
Things to watch out for
9
One-way designs
9.1
Sanity checks
9.2
Visualization
9.3
Transformation
9.3.1
Logarithmic
9.3.2
Rank
9.4
Nonparametric
10
Multi-way designs
10.1
Readings and Resources
10.1.1
ANOVA
10.1.2
Ordered logistic model
10.2
Example data set
10.3
Descriptives
10.4
Visualizations
10.4.1
Means / standard errors
10.4.2
Dot plot, with dodge/jitter
10.4.3
Frequencies
10.5
ANOVA
10.5.1
Model checking
10.6
Ordinal analysis
10.6.1
Model checking
11
Mixed designs
11.1
Sanity checks
11.2
Visualizations
11.3
Linear mixed effects model
11.4
MANOVA
12
Correlational designs
12.1
Description
12.1.1
Descriptive table
12.1.2
Correlation matrix (numerical)
12.2
Visualization
13
Regression designs
13.1
Description
13.2
Visualization
13.3
Regression analysis
13.3.1
Model checking
13.3.2
Sequential model testing
14
Higher-order regression analyses
14.1
Example data set
14.2
Description
14.3
Visualization
14.4
Regression analysis
14.4.1
Model checking
15
Count-based designs
15.1
Readings and Resources
15.2
Visualizations
15.3
Model checking
15.3.1
Pearson residual
15.3.2
Deviance residual
16
Linear mixed effects models
17
Multiple DV designs
17.1
Description
17.2
Visualization
17.3
Why not
\(t\)
tests?
17.4
Why not ANCOVA?
17.5
MANOVA
17.5.1
Model check
17.6
Linear Discriminant Analysis
18
Data manipulation tips
18.1
Common tasks
18.1.1
Splitting and filtering
18.1.2
Long-to-wide, wide-to-long
18.1.3
Combining multiple data sets
18.1.4
Recoding data
19
Simulation techniques
19.1
Permutation tests
19.2
The bootstrap
20
Quantile-Quantile (QQ) plots
20.1
Readings and Resources
20.2
What is a QQ plot?
20.3
Comparing two variables
20.4
Comparing one variable with a theoretical distribution
20.5
Interpreting QQ plots
20.5.1
Same distribution
20.5.2
Same shape, central tendency difference
20.5.3
Same shape, scale difference
20.5.4
Same shape, location and scale difference
20.5.5
Different shapes
References
Published with bookdown
Statistics review handbook
Chapter 19
Simulation techniques
Permutation tests
The “bootstrap”
19.1
Permutation tests
19.2
The bootstrap
×