Not by me, but by Jeffrey A. Tucker, today:

In 2024, Brownstone Institute commissioned a study (by E.J. Antoni and Peter St. Onge) that concluded that we have never really entered recovery after 2022. We’ve been in a technical recession since that time. They got this with some limited adjustments of price data bumped up against output data. That study was met with brutal attacks, with every critic falling back on official data and doubting the supposed extremism of the conclusion.

To remind people, here is the relevant graph from that paper.

Source: Antoni and St. Onge (2024).

For those who are interested, in this paper, I document the impossibility of replicating their results, without an explanation of how they constructed their alternative deflator.

Now, I think I understand how Antoni and St. Onge (2024) obtained their results. It’s hinted at in reference to a “Reality Index”, credited to “independent intellectual Tom Elliott“.

The Reality Index v1 tracks the retail price of fifteen specific items in five categories: food, energy, housing, health care, and services. Each item is selected on three criteria: (a) the item is a fixed-specification good or service that households actually purchase, (b) an authoritative retail-price time series exists for it going back at least to 1980, and (c) the item is non-discretionary, in the sense that the typical household consumes some amount of it whether or not its price has risen.

There are several key distinctions from the CPI, including using fixed weights (i.e., Laspeyres price index), no hedonic adjustments, different treatment of housing. (While it’s true that CPI used to be characterized as Laspeyres, over time the treatment has changed so it approaches the chained measure).

Here’s the relevant comparison:

Source: Tucker (2026).

I’ve got no beef with anybody analyzing data, making up their own indices (as long as properly documented, and data posted for replication). However, Tucker then conducts this interesting exercise.

Source: Tucker (2026).

I can say two things with perfect certitude: (1) the above graph, labeling “Official Real GDP (FRED) is definitively NOT official real GDP from FRED — it’s much too straight. (2) It makes no sense to deflate nominal GDP with a deflator for consumption, unless prices rose at the same rate for firms (investment), government (government spending on tanks and civil servants) and exports (purchases of American goods and services imported by other countries).

From this, I can only conclude that in the original Antoni-St. Onge paper obtained their bizarre result by deflating GDP using their (undocumented, unreproducible) consumer price deflator.