the statistical model Flashcards
1
Q
All models we use are wrong
A
“All models are wrong, but some are useful” (Box, 1976)
- They are representations of a thing that do not necessarily capture all the complexity of reality
- But they can still be of use to us
- E.g. the underground map or the model of a car’s suspension
2
Q
The statistical model
A
- We don’t make physical models of things
- Small bridges, maps
- Our models are made from data
- We collect data about a phenomenon
- Look for patterns or trends
3
Q
Simple model
A
Describing central tendency and variability in a measure
4
Q
Complex model
A
Network of how different variables connect to each other
5
Q
step 1
A
We find a phenomenon we are interested in
6
Q
step 2
A
We create a theoretical model & create study
7
Q
step 3
A
We collect data about that phenomenon
8
Q
step 4
A
Visualise & interpret the variability in that data
9
Q
step 5
A
Describe the variation using appropriate descriptive statistics
10
Q
step 6
A
- This is where we build and interpret the statistical model (in RStudio)
- Based on our theoretical model and using our data
11
Q
• Why do we need a statistical model?
A
- Make conclusions about lots of people by just studying a few
- Hypothesis testing
- Estimation
- Predict the future
- Compare different theoretical models