ECON 3210 Lecture Notes - Lecture 5: Ceteris Paribus, Panel Data, Tacit Assumption
Document Summary
Superficially, a panel data set has a structure similar to a pooled cross section. The key difference is that with a panel data set the same units (people, houses, schools, and so on) are followed over time. For example, there are a couple of thousand elementary schools in michigan. We can collect information on test pass rates, spending, and some socioeconomic variables annually for each school over, say, the last 10 years. Following the same units over time has advantages when trying to infer causality. Panel data analysis is a more advanced topic and we won"t see much in this course. Finding correlations in data might be suggestive but is rarely conclusive. Crucial to establishing causality is the notion of ceteris paribus: all (relevant) factors equal . If we succeed via statistical methods in holding fixed other relevant factors, then sometimes we establish that changes in one variable (say, education) in fact cause changes in another variable (wage).