Imagine you would like to estimate the following model health = β_0 + β_1 Bicigarettes_day + u where health is self-rated health on a 1 to 5 scale (5 = very healthy) and cigarettes_day is the number of cigarettes the person smokes per day (on average). Imagine you would like to estimate β₁ using an instrumental variable (IV) regression. As instrument, you would use the variable female, which is equal to 1 if the person is female and 0 otherwise. For the situation described above, a) state the IV relevance assumption b) state the IV exogeneity assumption In your answer, use the actual variable names (instead of e.g. x,y and z). 2)
In one sentence, what does it mean for an estimator to be unbiased?
(Hint: you do not need to state the formal definition of unbiasedness)
3)
In one sentence, what does it mean for an estimator to be consistent?
(Hint: you do not need to state the formal definition of consistency)