PAM 4100:
Research Designs and
Causal Claims
Research Design
For our purposes, research design refers to the set of analyses that will
be implemented to assess the causal effect of X on Y. The design
describes how the constructs of interest are operationa

Estimating Causal Effects
with Regression
When can regression coefficients be given causal
interpretations?
In the population, suppose the true relationship
between Y and X is given by:
Yi = + X i + i
Note that we now distinguish between the true model
pa

1: THE PREGNANT MARE’S LESSON
In a former British colony, most healers believed the conventional wis-
dom that a distillation of ﬂuids extracted from the urine of horses, if
dried to a powder and fed to aging women, could act as a general tonic,
preserv

PAM 4100: Problem Set 1
Prof. Jordan Matsudaira
Problem Set 1: Regression, randomized trials, and causal inference
This problem set has several goals. We will review some basic statistics and the mechanics
of OLS regression, and also think a bit about the

38 POWERFUL MEDICINES
The tens of thousands of extra breast cancers, pulmonary emboli,
strokes, and other drug-related side effects that were caused by the use of
estrogens in millions of women didn’t have to happen. Together, they
amount to one of the la