POLS 2400 Lecture Notes - Lecture 11: Causal Inference, Counterfactual Conditional, Quantile
25 Oct 2018
School
Department
Course
Professor
Document Summary
Participants are divided by chance into separate groups that compare different treatments: observational study: look at the world around us. Since we can"t control the treatment, we risk missing confounding variables so we try to measure the confounding effects: natural experiments: we don"t have control over the treatment, but we can assume the assignment is random. Considering both the value and occurrence of each observation: median: the middle observation that splits the distribution into two halves. Approximates distribution of a variable: probability sampling: every member of the population has a known and equal chance of being selected, simple random sampling: most basic form of probability sampling. Randomly chooses units from a population of interest. The key assumption here is that the outcome variable follows a parallel trend in the absence of treatment: correlation: how strong two things are related. Measured by correlation coefficient: linear regression: simple way of describing relationship between 2 variables.
