Mathiness in the theory of economic growth

发表时间：2026-07-16 06:15

Paul Romer criticized the use of mathematics in economic literature, especially in the theory of economic growth. He introduced the concept of mathiness.

Academic politics, like any other type of politics, is better served by words that are evocative and ambiguous, but if an argument is transparently political, economists interested in science will simply ignore it. The style that I am calling mathiness lets academic politics masquerade as science. Like mathematical theory, mathiness uses a mixture of words and symbols, but instead of making tight links, it leaves ample room for slippage between statements in natural versus formal language and between statements with theoretical as opposed to empirical content. (p 89)

Before that paragraph, he provided some background.

Economists usually stick to science. Robert Solow (1956) was engaged in science when he developed his mathematical theory of growth. But they can get drawn into academic politics. Joan Robinson (1956) was engaged in academic politics when she waged her campaign against capital and the aggregate production function. (p. 89)

I don’t know much about Joan Robinson’s work. I asked Gemini,

"Joan Robinson (1956) was engaged in academic politics when she waged her campaign against capital and the aggregate production function." This is a sentence from Paul Romer's 2015 paper, Mathiness in the Theory of Economic Growth. What does it mean?

Gemini’s response was very interesting.

When Nobel laureate Paul Romer wrote that "Joan Robinson (1956) was engaged in academic politics when she waged her campaign against capital and the aggregate production function," he was delivering a highly calculated punchline.

To understand what he meant, you have to look at the historical economic battle he is referencing, and why he used it to frame his modern critique of "mathiness."

1. The Context: The Cambridge Capital Controversy

In the 1950s and 1960s, a fierce academic war erupted between two groups of economists:

Cambridge, USA (MIT): Led by Robert Solow and Paul Samuelson, who championed neoclassical growth models.
Cambridge, UK (University of Cambridge): Led by Joan Robinson and Piero Sraffa, who championed a Post-Keynesian/Marxist-adjacent view.

At the center of this battle was the aggregate production function. Neoclassical economists write equations like:

$$Y = F(K, L)$$

Where $Y$ is total economic output, $L$ is labor, and $K$ is "Capital".

Joan Robinson launched a devastating critique against this equation. She asked a deceptively simple question: How do you actually measure $K$?

You can count workers ($L$) by counting heads. But "Capital" ($K$) is a messy pile of non-identical physical objects: hammers, conveyor belts, computers, and office buildings. You cannot add a shovel to a computer chip unless you convert them into a dollar value. But to calculate their dollar value, you need to know the rate of interest (or profit rate). However, the neoclassical model was using the production function to determine the rate of interest in the first place.

Robinson argued this was circular reasoning. Neoclassical economists, she claimed, were hiding this logical flaw behind beautiful but physically meaningless mathematics to justify the "natural" returns of capitalists.

2. Why Paul Romer Calls This "Academic Politics"

In his 2015 paper Mathiness in the Theory of Economic Growth, Romer defines "mathiness" as the misuse of mathematical models to sneak ideological or political biases into economics under the guise of objective science.

In the quote you referenced, Romer sets up a direct contrast:

Robert Solow was doing science: According to Romer, Solow used math to map abstract symbols directly onto observable, physical things (like actual machines and structures) to build a useful, albeit imperfect, model.
Joan Robinson was doing academic politics: Romer asserts that Robinson’s goal wasn't to refine scientific measurement, but to destroy the neoclassical framework because she fundamentally disagreed with its ideological conclusions about capitalism, wealth distribution, and markets.

Romer is arguing that Robinson was weaponizing methodological nitpicking to win an ideological debate. Because her attack was "transparently political," Romer claims that scientific economists simply chose to ignore it and kept using the aggregate production function because, despite its mathematical flaws, it was a highly useful "map" of reality.

3. The Irony of Romer’s Critique

Your previous points about how economists use models to preserve "general equilibrium" rather than reality apply beautifully here. Many heterodox economists pointed out a deep irony in Romer's paper:

Romer wrote his paper to complain that modern Chicago-school economists (like Robert Lucas and Edward Prescott) were using "mathiness" (sleight-of-hand equations) to politically argue for deregulation and state-free markets.
Yet, in the very same paper, Romer attacks Joan Robinson.

Why? Because Robinson’s mathematical critique of the neoclassical model was actually correct. Even Samuelson eventually admitted that Robinson and Sraffa won the theoretical debate on the math of capital aggregation.

By labeling Robinson's critique as mere "academic politics," Romer was attempting to protect the neoclassical foundation of his own life's work—the "Endogenous Growth Theory," which relies heavily on aggregate production functions.

Romer's sentence is a perfect, meta-example of the very "academic politics" he was trying to diagnose. He dismissed a logically valid mathematical critique of his discipline's core tool by branding its creator as a political actor, thereby preserving the elegant, equilibrium-based models he built his career on.

Reference

Romer, P.M., 2015. Mathiness in the theory of economic growth. American Economic Review, 105(5), pp.89-93.