Health Econ Midterm 1

Front 1

What are the 3 Key Assumptions for Rationality?

Back 1

1. Completeness
2. Transitivity
3. Local Non-Satiation (More is Better)

Front 2

What is Adverse Selection?

Back 2

Tendency for riskiest people to buy insurance due to asymmetric information

Front 3

What is Moral Hazard?

Back 3

Increased risk taking brought on by the presence of insurance

or
A situation where there is a tendency to take additional risks because the costs are not borne by the party taking the risk

Front 4

What are Elasticities?

Back 4

A way to measure responsiveness

Front 5

What is Price elasticity? What is Income elasticity? What is Cross-price elasticity?

Back 5

How a percentage in price affects quantity demanded (in percentages)

Income Elasticity:
How a percentage in income affects quantity demanded (in percentages)

Cross-Price:
How a percentage change in the price of another good affects the quantity demanded (in percentages).

Front 6

What are the OLS assumptions?

Back 6

1. Correct specification (linear in parameters)
2. Strict Exogeneity - E(ui|xi) = 0. (Also implies E(uixi) = 0 3. Homoskedasticity - E (ui2 |xi ) = σ2
4. Normality ui|xi~N(o,σ2In)

Front 7

1. Suppose that an individual has a utility function U(c, h) = ln(c) + h

c Represents consumption of a necessity good such as shelter, and h represents health

a. Find that optimal amount of c and h if the individual is income is 5, the price of “c” is 1 and the price of “h” is 1.

Back 7

U(c, h) = ln(c) + h
Ph= 1
Pc= 1
I = 5

MRS= Pc/Ph

1. MUc/MUh= Pc/Ph
Take derivative of ln(c)+h with respect to c to get MUc
Take derivative of ln(c)+h with respect to h to get MUh
2. MUc= 1/c
3. MUh= 1
4. (1/c)/1= 1/1
5. 1/c=1
6. c=1

Constraint formula:
I= Ph*h+Pc*c
5= 1*h+1*1
h=4

Front 8

1. Suppose that an individual has a utility function U(c, h) = ln(c) + h

c Represents consumption of a necessity good such as shelter, and h represents health

b. What happens to the consumption of c and h if the individual is income increases to 10? Is health a normal or inferior good, or neither? What about c?

Back 8

Constraint formula:
I= Ph*h+Pc*c
10= 1*h+1*1
h=9

health is a normal good
consumption is neither normal or inferior

Front 9

1. Suppose that an individual has a utility function U(c, h) = ln(c) + h

c Represents consumption of a necessity good such as shelter, and h represents health

c. Suppose the price of c increases to 2, while income remains constant at 10. What happens to the consumption of c and h? Are c and h substitute goods, complementary goods, or neither?

Back 9

1/c= 2/1
c= 1/2

Constraint formula:
I= Ph*h+Pc*c
10= 1*h+2*(1/2)
h=9

The consumption of consumption decreases, while health remains the same. This means consumption and health are neither substitute nor complementary goods.

Front 10

2. Suppose you are interested in assessing the effect that education has health. You find a data set on education and health. You consider running the following OLS regression:
Health_i=β_0+β_1 education_i+u_i

a. Theoretically, why would we expect education to affect health?

Back 10

1) More education leads to higher incomes which may lead to higher demand for health if health is a normal good.

2) More edcation may lead to more information on the benefits of health

3) More education may lead individuals to have lower discount rates which would lead to increased returns on future utility increasing the return for health.

4) More education may improve the ability of individuals to process information/follow doctors orders

5) More educaiton may place individuals in safer jobs/jobs with higher medical care

6) More education may reduce fertility (family size) which may increase the amount of spending per family availble for medical care.

Front 11

2. Suppose you are interested in assessing the effect that education has health. You find a data set on education and health. You consider running the following OLS regression:
Health_i=β_0+β_1 education_i+u_i

b. What assumption(s) do you need for this estimator to be unbiased?

Back 11

1. We need to assume strict exogeneity for this estimator to be unbiased.
E(ui|educ)=o
2. Linear in parameters
3. Homoskedasticity - E (ui^2 |xi ) = σ^2
4. Normality ui|xi~N(o, σ^2In)

Front 12

2. Suppose you are interested in assessing the effect that education has health. You find a data set on education and health. You consider running the following OLS regression:
Health_i=β_0+β_1 education_i+u_i

b. What assumption(s) do you need for this estimator to be unbiased?

c. Continuing on with answer to part B, do you think that assumption is likely to be justified? Why or why not.

Back 12

This will likely be violated. There are many factors which are unobserved (such a parental income or risk aversion) which likely affect both your
educational pursuits and your health directly.

Front 13

2. Suppose you are interested in assessing the effect that education has health. You find a data set on education and health. You consider running the following OLS regression:
Health_i=β_0+β_1 education_i+u_i

b. What assumption(s) do you need for this estimator to be unbiased?

c. Continuing on with answer to part B, do you think that assumption is likely to be justified? Why or why not.

d. What is an alternative approach one could use to learn the true value of β_1 if your assumption in part b wouldn’t hold true. What new assumptions would this approach require?

Back 13

We need instrumental variables (IV).

New assumptions:
1. α_1 ≠ 0 must be relevant

2. excludability E(Ui|Xi) =0