Overview of the Course
Topics we will cover
Learning Outcomes
Data sets
Schedule
Expectations
Lets stay in touch
Authorship
1
CoopR
1.1
Think algorithmically
1.2
Don’t be scared
2
RStudio
3
Basic principles of
R
programming
3.1
If you want to keep it, put it in a box
3.2
You can’t
really
change an object
3.3
It’s elementary, my dear Watson
3.3.1
Data structures
3.4
There are only three ways to ask for elements
3.4.1
Indices
3.4.2
Logical vectors
3.4.3
Complementary subsetting
3.4.4
Names -
$
subsetting
3.5
Think of commands in terms of their output
3.6
Know what to expect
4
Putting it all together
4.1
Are there quicker ways?
5
Functions
5.1
Packages
5.2
Using functions
5.2.1
The
()
s
5.2.2
Specifying arguments
5.3
Function output
5.3.1
Command is a representation of its output
5.3.2
Knowe thine output as thou knowest thyself
5.4
Output is an object
5.4.1
Where does the output go?
6
Making the computer do the heavy lifting
6.1
Avoiding repetition and avoiding repetition
6.2
The
apply()
family
6.3
Conditional code evaluation
6.3.1
if
6.3.2
else
6.3.3
else if
6.3.4
ifelse()
6.3.5
Nesting clauses
6.4
Writing your own functions
6.4.1
Functions are objects too!
6.4.2
Anatomy of a function
6.4.3
DIY
7
Reshaping Data
7.1
Tidyverse
7.2
Wide to long
7.2.1
gather()
7.2.2
separate()
7.2.3
select()
7.3
Descriptives in tidyverse
8
Data visualisation
8.1
qplot()
8.2
ggplot()
9
Useful tips
9.1
Break it down
9.2
Handy functions that return logicals
10
Tests and modelling in R
10.1
Hypothesis testing
11
Examining Relationships (more than one variable)
11.1
T test
11.2
Chi squared distribution and test
11.2.1
Contingency tables
11.3
Chi squared distribution
11.4
One way Anova example
12
Lets take a break!
13
Correlation, Causation and LM
13.1
Sharks and ice cream example
13.2
Simple Linear Regression in R
13.3
Regression Diagnostics
13.3.1
Violations of the assumptions: available treatments
13.4
Interaction (simple slope) and multiple explanatory factors
14
Model selection
15
Linear Model and Mixed Methods
15.1
Longitudinal Data
15.2
Why do we do this?
15.3
Ecological Fallacy (quick illustration)
15.4
Simple model
15.4.1
Pooling
15.4.2
No pooling
15.4.3
Partial Pooling (varying intercepts)
15.4.4
Partial Pooling (varying intercepts and/or slopes)
15.5
Multilevel modelling with random intercepts and slopes
15.5.1
Prepare
15.6
Random slopes, intercepts and cross level interactions (optional)
16
High Dimensional Analysis
17
Extra Resources
17.1
More R practice
17.2
Data Cleaning
17.3
Visualisations
17.4
Stuff we did not cover
17.5
Big Data
PhD Training Workshop: Statistics in R
Chapter 12
Lets take a break!