ECN741: Urban Economics Estimating Housing Demand.

ECN741: Urban EconomicsEstimating Housing Demand

Estimating Housing Demand

Class Outline

Constant Elasticity Case

Linear Expenditure System

Housing price variable

Submarkets and the Demand for Structures

Tenure Choice

Housing Durability

Endogeneity of neighborhood choice

Endogeneity of household formation


Constant Elasticity Demand

Let’s begin with a standard formulation of the demand for housing services, H.

The notation

▫ Y = income▫ P = price of housing services▫ u = distance from worksite▫ t = round-trip commuting costs per mile▫ R = apartment rent = PH (≠ land rent, at least not

today!!)▫ V = house value = R/r


Constant Elasticity Demand, 2

The demand function is

where C is a constant

Multiplying both sides by P, we obtain

( ) { }H C Y tu P u

1{ } { } { } ( ) { }R u P u H u C Y tu P u



Taking logs, we obtain the estimating equation:

In practice, empirical work ignores theory!

Everybody uses Y instead of Y- tu;

P is usually measured with a metropolitan area construction index; some studies divide R by P to get H;

Some studies use V instead of R.

ln{ { }} ln{ } ln{ } (1 ) ln{ { }}R u C Y tu P u



Example: Zabel, Journal of Housing Economics, March 2004.

Uses data from AHS.

The 2001 AHS data, including a few control variables, imply that

▫ θ = 0.362

▫ μ = -0.052


Linear Expenditure System

Recall this problem with a Stone-Geary utility function:

Recall as well that the resulting demand for H is

1Maximize: ( )

Subject to : { }Z HU Z S H S

Y Z P u H tu

{ }

{ }Z H

H

Y tu S P u SH S

P u


Linear Expenditure System, 2

Now if we multiply both sides by P{u}, we have

This is called a linear expenditure system.

The survival quantities are coefficients to be estimated.

If the price of Z varies in the data, it needs to be included, too.

{ } { } (1 ) { } ( )Z HR u P u H S S P u Y tu


Linear Expenditure System, 3

Note that this functional form is quite different from the constant elasticity form.

The linear expenditure system has been widely used in other contexts, but not so much in housing.

An idea for a study: Use standard specification tests to determine which of these specifications is appropriate.

The Davidson/MacKinnon test, for example, calls for including the predicted value from regression A as an explanatory variable in regression B. If it is significant, the specification in regression A adds explanatory power.


The Housing Price Variable

The standard approach allows prices to vary across urban areas, but the basic urban model indicates that P varies within an urban area, too.

Some studies (e.g. Goodman, JUE, May 1988) first regress V on u, A (neighborhood amenities that appear in P), and X (housing characteristics that appear in H): { , } { }P u A H X

Vr


The Housing Price Variable

These studies then predict P based on u and A and use the predicted P in housing demand estimation.

Allowing intra-area variation in P appears to make a big difference:

His price elasticities for owners and renters are -0.502 and -0.786, respectively, much larger (in absolute value) than Zabel’s—as one would expect when correcting the errors in a metropolitan level price variable!


Submarkets and the Demand for Structures

Zabel’s study with AHS data pools across metropolitan areas, treating each as a submarket.

He allows the coefficients of the Xs to vary across metropolitan areas.

Then he defines a “structure price” to be the price of a given housing bundle (set of Xs) in each metropolitan area.


Submarkets and the Demand for Structures, 2

As an aside, some early studies applied the same type of logic to data for a single urban area.

The allow the coefficients of the X’s to vary across exogenously determined “submarkets” within an urban area.

In my judgment, this approach adds a lot of complexity without much insight.

But the interactions across submarkets are sometimes significant, and some scholars think submarkets are important.



Back to Zabel: Let N be neighborhood traits (indexed by n) and X be structural housing traits (indexed by m). Then Zabel estimates:

The estimated coefficients are allowed to vary across urban areas.

n m

n mn m

R PH N X



Zabel’s “structure price index,” PS, is defined by holding the Xs at their mean and the λs at their estimated values.

The amount of “structure,” H*, is R/PS .

With these terms, he can estimate the constant elasticity demand function using H* as the housing variable and PS (and the comparably defined neighborhood price index, PN ) as explanatory variables.



Zabel’s logic is fine, but I find his terminology to be misleading.

In an urban model, H stands for “structure” already, and P{u} is its price.

It is fine to allow the weights that define H to vary across urban areas, but it is confusing to create a new term for the “price of structures.”

I also prefer estimates based on a single urban area—with intra-area variation in P.


Adding Tenure Choice

One of the most important behavioral issues in the study of housing markets is tenure choice.

Why do some households decide to buy a house while others choose to rent?

This topic has been widely studied. We will return to it when we study race and ethnicity.

But today it is important because it is a major source of selection bias in estimating housing demand.


Sample Selection Bias in Estimating Housing Demand

Owner-occupied houses tend to be larger than apartments.

Thus the amount of H (the dependent variable) is correlated—highly—with tenure choice.

This violates the principle that a sample selection rule (a study of just owners or just renters) should not be correlated with the dependent variable.


Selection Bias in Housing Demand, 2

H

Y

Owners

Renters

Error Distribution

True Relationship

Estimated Line for Owners

Estimated Line for Renters

H*



One way to handle this is to pool owners and renters.

Use R, apartment rent, as the dependent variable for owners.

Use rV = annualized value as the dependent variable for owners.

But this can be complicated because of different tax treatment, depreciation, mortgage interest, etc.

And owners and renters may have different elasticities.



Another approach is provided by Goodman (1988 and several more recent articles).

He estimates three equations:

Housing demand for owners

Housing demand for renters

Tenure choice



In his model ψ is the ratio of value to rent, a measure of expected appreciation in owner occupied housing (expected appreciation lowers the real discount rate), which identifies investment incentives.

In addition, λ is the ratio of owner to renter P, a measure of relative price; f is the probability that a household is an owner; C is a constant, and A is age.

The resulting equations with owner, O, and renter, R, subscripts are:



{ } OO O OO O OH C Y P u A

{ } RR R RR R RH C Y P u A

f f f f

ff C Y A



Now overall housing demand is

Differentiating with respect to income yields the overall income elasticity, θ:

(1 )O RH f H f H

(1 )1O O R R R

f

f H f H H

H H



Goodman results, are as follows:

Recall that Goodman also accounts for intra-urban variation in P. If you are interested in housing demand, his work is well worth studying!

0.308; 0.134; 0.423O R

Housing Demand Theory

Accounting for the Long Lifetime of Housing

The long lifetime of housing makes housing decisions different from many other decisions.

One implication is that housing demand is more closely linked to permanent income than to temporary income.

Households may not immediately adjust their housing consumption in response to temporary income shocks.

Thus, temporary shocks are like measurement error, and the income elasticity of demand for housing is higher when permanent income is used instead of current income.


The Long Lifetime of Housing, 2

Olsen (Handbook chapter 1988) emphasizes the long time frame of housing decisions.

Because housing decisions are forward-looking, models of housing demand need to consider wealth, age, and expectations.

At the very least, studies should try to have controls for wealth, education, and age (which help to predict permanent income).


The Long Lifetime of Housing, 3

The Olsen chapter is valuable because it presents all these issues in fairly straightforward models.

He shows, for example, that one might also want to interact age with other parameters in the demand model, because age changes expectations and time horizons!

Moreover, the formulations given above implicitly assume static expectations, and a formal treatment of expectations might alter the estimating equation.


The Endogeneity of Neighborhood Choice

Households must decide where to live as well as how much housing to consume.

These decisions are related, so failure to consider neighborhood choice might bias estimates of housing demand.

Papers that make this argument include Rapaport (JUE, September 1997) and Iaonnides and Zabel (J. of Applied Econometrics, 2003).


The Endogeneity of Neighborhood Choice, 2

Rapaport’s methodology is complicated.

She estimates a logit model of neighborhood choice and then includes the predicted probabilities in a constant-elasticity housing demand equation.

In effect, she adds to the standard model an additional variable for each neighborhood.

She finds that accounting for neighborhood choice increases the estimated (absolute value of) price elasticities considerably.


Endogeneity of Neighborhood Choice, 3

A similar endogeneity will show up later in the class when we study “hedonics,” which is the name economists give to a regression of house value or rent on neighborhood and housing attributes.

Because households compete for entry into desirable neighborhoods, prices rise with neighborhood quality.

As a result, households simultaneously select housing price and neighborhood quality.

As we will see, this form of endogeneity makes it difficult to study the demand for neighborhood amenities.


The Endogeneity of Household Formation

Individuals must decide how to form themselves into households when they make housing decisions.

Single adults may decide to move in with other single adults or with their parents when the price of housing is high.

Elderly parents may move in with their adult children when the price of housing is high.


Endogeneity of Household Formation, 2

A few studies have shown that accounting for household formation decisions is important in estimating housing demand.

See, for example, Boersch-Supan and Pitkin (JUE September 1988).

This study uses nested logit analysis; in level 1, adults decide on household formation; in level 2 they decide on tenure; and in level 3 they decide on housing type.

ECN741: Urban Economics Estimating Housing Demand.

Documents

Transcript of ECN741: Urban Economics Estimating Housing Demand.