Lecture 2: Causal inference with experimental method Flashcards
1
Q
What is an experiment?
A
- Golden standard
- Includes intervention/treatment
- Keep everything constant except for the treatment itself
- Clean design? -> simple t-test/ANOVA
2
Q
Random Assignment
A
- Equal chance
- Characteristics of participants between two groups do not differ (limit confounding variables)
- Small but a sufficiently large sample
3
Q
Simple randomization
A
- Toss a coin (random)
- Limitation -> not equal number of persons between groups
4
Q
Block randomization
A
- Randomize subjects into groups
- Sample size is relatively small
- Not intended for controlling confounding variable
5
Q
Stratified randomization
A
- Limit the undesired influence of a known factor
- Based on more than one factor
- Number of strata should be in proportion with the target sample size
6
Q
Laboratory Experiment
A
- Control setting
- Participants informed and compensation
- Allows intrusive design
- Reduces chance of confounding variables
- Improves internal validity but reduces external validity
7
Q
When should we use laboratory experiment?
A
- Stake of making a mistake is high
- Confounding variables tend to occur
- Setup is not feasible in real-world
- Budget and participants available are limited
8
Q
Field experiment
A
- Impact of a treatment in the real-world
- Enabled by digitalization
- Less control over other confounding factors
- Spillover and crossover effects
- Ethical issues
9
Q
Application in marketing
A
- Academic -> testing a theory
- Company -> testing an intervention)
- Public policy -> testing an intervention
- Litigator -> testing a hypothesis based on intuition
10
Q
Designing an experiment
A
Step 1: Formulate your hypothesis Step 2: Select an appropriate sample Step 3: Set up and run your experiment Step 4: Analyse your data & interpret your findings Step 5: Reformulate your hypothesis
11
Q
Research Question
A
A general statement of your observation or assumption
12
Q
A scientific hypothesis should be
A
- Testable
- Falsifiable
- Stated as an expected relationship between variables
- Simple and easy to understand
13
Q
Practical concerns sample size
A
- Availability participants
- Costs
- Time management
- Data collection method
- Ethical concerns
14
Q
Power analysis
A
Assess minimum sample size required given a significance
level, effect size, and statistical power.
15
Q
Power Analysis Advantages
A
- Limit p-hacking
- Avoid over (i.e., waste of resources) or under power (i.e., unable to detect
an effect when there is one)