Qualitative economics

Qualitative economics refers to representation and analysis of qualitative information, that is, information about the direction of change (+ or -) in at least one economic variable as related to change of at least one other economic variable (James Quirk, 1987, p. 1). Variables may be continuous or discrete. GDP approximates a contnuous variable. Buying a car or not over a given year is a discrete variable. So is being at war or not in a given year. For a continuous variable, what makes the change qualitative is that its magnitude is not specified. Typical exercises in qualitative economics include comparative-statics models and comparative equilibrium states in a neoclassical growth model.

Consider the the case of an economic model with only two variables, both of them continuous in real numbers, say GDP and the money supply M. The quantity theory of money hypothesizes a positive relationship between GDP the dependent variable and M the independent variable. Common equivalent ways to represent such a qualitative relationship between them are with respectively signed functional notation and derivative notation:

$+$

$GDP=f(M)$ OR ${\frac {dGDP}{dM}}>0.$

where the '+' indexes a positive relationship relationship.

Consider another simple model in which total taxes T are hypothesized to have a negative relationship to GDP. The relationship can be similarly represented (with appropriate sign changes compared to the first example) as:

$-$

$GDP=f(T)$) OR ${\frac {dGDP}{dT}}<0.$

Next consider a combined model that uses both M and T as independent variables. The hypothesized relationships can be equivalently represented, using signed functional notation and partial derivative notation (suitable for more than one independent variable) as:

$+$ $-$

$GDP=f(M,T)$ OR ${\frac {\partial GDP}{\partial M}}>0,$ ${\frac {\partial GDP}{\partial T}}<0.$

where the signs index the hypothesized relationships of GDP to M and T respectively.

See Paul A. Samuelson, (1947) for a classic example of such theoretical representations.

Standard theoretical or econometric representation of discrete variables is with dummy variables or qualitative-choice models. The latter model choices in a probabilistic or odds-ratio sense.

See also

• Discrete choice
• Dummy variable
• Logit
• Probit
• G.S. Maddala
• Daniel McFadden, winner of the Bank of Sweden Prize in Economic Sciences in Memory of Alfred Nobel for development of a particular logit model used in economics
• JEL classification codes, scroll down to JEL: C25 - Discrete regression; Qualitative choice models

References

• James Quirk, 1987, “qualitative economics," The New Palgrave: A Dictionary of Economics, v. 4, pp. 1-3
• Paul A. Samuelson (1947). Foundations of Economic Analysis, Harvard University Press. ISBN 0-674-31301-1