Peer-reviewed reanalysis

• Michael Wiebe (2024), “Can We Detect the Effects of Racial Violence on Patenting? Reanalyzing an Article by Lisa Cook,” Econ Journal Watch — questions log specifications, treatment of riots/segregation laws, and reproduces weaker/insignificant effects under alternative, arguably cleaner specifications.
• Journal page/metadata: JournalTalk entry for the Wiebe 2024 EJW article.

Replication notes and data/method issues (preprints & blog)

• Wiebe (2023) reanalysis PDF — documents coding inconsistencies (e.g., differing lynching variables across tables), errors in state dummies, and sensitivity of results to aggregation choices.
• Wiebe (2022) blog: “Can we detect the effects…?” — tests the application-to-grant lag logic and finds the predicted drop in grants does not materialize when violence spikes; many effects lose significance under alternative specifications.

Plausibility/data-construction disputes

• Marginal Revolution (Tyler Cowen, 2022) — amplifies claims that headline graphs/patterns are artifacts of data assembly; urges skepticism about the magnitude/timing of the reported patent collapse.
• Andrew Gelman’s blog (2022) — raises questions about interpretation and basic time-series plausibility based on the displayed figures; links further discussion.
• Andrew Gelman’s blog (2024) — points readers to the Wiebe reanalysis and debates data provenance and concentration of counts circa 1900.

Broader criticism of scholarship conduct

• City Journal (Christopher Rufo, 2024): “Lisa D. Cook’s Careless Scholarship” — alleges a pattern of sloppy scholarship and cites examples beyond the patents paper; highly critical, opinionated, and controversial but widely referenced in the debate.

Target article for context

• Cook (2014) working-paper version PDF and Cook (2012) earlier version PDF.

Here's my analysis of how Lisa Cook blundered her way onto the Federal Reserve Board of Governors by botching up her one famous paper:https://t.co/nDr0QASKsS

— Steve Sailer (@Steve_Sailer) December 22, 2023

Chris Rufo wrote Apr. 10, 2024:

Lisa D. Cook is one of the world’s most powerful economists. She taught economics at Harvard University and Michigan State University and served on the Obama administration’s Council of Economic Advisers before being appointed, in 2022, to the Federal Reserve Board of Governors, which controls the interest rates and money supply of the United States.

Despite her pedigree, questions have long persisted about her academic record. Her publication history is remarkably thin for a tenured professor, and her published work largely focuses on race activism rather than on rigorous, quantitative economics. Her nomination to the Fed required Vice President Kamala Harris to cast a tie-breaking vote; by contrast, her predecessor in the seat, Janet Yellen, now Treasury secretary, was confirmed unanimously.

The quality of her scholarship has also received criticism. Her most heralded work, 2014’s “Violence and Economic Activity: Evidence from African American Patents, 1870 to 1940,” examined the number of patents by black inventors in the past, concluding that the number plummeted in 1900 because of lynchings and discrimination. Other researchers soon discovered that the reason for the sudden drop in 1900 was that one of the databases Cook relied on stopped collecting data in that year. The true number of black patents, one subsequent study found, might be as much as 70 times greater than Cook’s figure, effectively debunking the study’s premise. 

Cook also seems to have consistently inflated her own credentials. In 2022, investigative journalist Christopher Brunet pointed out that, despite billing herself as a macroeconomist, Cook had never published a peer-reviewed macroeconomics article and had misrepresented her publication history in her CV, claiming that she had published an article in the journal American Economic Review. In truth, the article was published in American Economic Review Papers and Proceedings, a less prestigious, non-peer-reviewed magazine.

An exclusive City Journal and Daily Wire investigation reveals additional facts that cast new doubt on Cook’s seriousness as a scholar. 

In a series of academic papers spanning more than a decade, Cook appears to have copied language from other scholars without proper quotation and duplicated her own work and that of coauthors in multiple academic journals without proper attribution. Both practices appear to violate Michigan State University’s own written academic standards.

We will review several examples which, taken together, establish a pattern of careless scholarship at best or, at worst, academic misconduct.

In a 2021 paper titled “The Antebellum Roots of Distinctively Black Names,” Cook copied-and-pasted verbatim language from Charles Calomiris and Jonathan Pritchett, without using quotation marks when describing their findings, as required. Here is the original passage from Calomiris and Pritchett:

During this time, New Orleans was the largest city in the South and the site of its largest slave market. Unlike states with a common law tradition, Louisiana treated slaves like real estate, and slave sales had to be recorded and notarized in order to establish title (Louisiana 1806, section 10). Today, the records of many of these slave sales may be found in the New Orleans Notarial Archives and the New Orleans Conveyance Office. Because of the availability of these records and the size of the market, New Orleans is the best source for data on slave sales within the United States.

Here is Cook’s paper, which, though it cites Calomiris and Pritchett, lifts their language verbatim, which we have marked in italics, substituting only the word “slaves” with the politically correct phrase “the enslaved”:

Unlike states with a common law tradition, Louisiana treated the enslaved like real estate, and slave sales had to be recorded and notarized in order to establish title (Louisiana 1806 section 10). Today the records of many of these slave sales may be found in the New Orleans Notarial Archives and the New Orleans Conveyance Office. Because of the availability of these records and the size of the market, New Orleans is the best source for data on slave sales within the United States. [ . . . ]

During this time New Orleans was the largest city in the South and the site of its largest slave market.

She does something similar in her October 2021 paper, “Closing the Innovation Gap In Pink and Black,” which, despite significant government subsidies and years spent on it by Cook, summarized the work of researchers Charles Becker, Cecilia Elena Rouse, and Mingyu Chen by copying roughly 70 words without quotes.

This appears to be a violation of the standards in Michigan State University’s guidebook, which states that authors must paraphrase or add direct quotations to verbatim passages. “It is your responsibility to make certain that you understand the difference between quoting and paraphrasing, as well as the proper way to cite and delineate quoted material,” the guidebook reads.

In multiple papers, Cook also appears to have copied language from her own prior papers, or those of coauthors, without proper attribution. 

In a 2018 paper, “Rural Segregation and Racial Violence,” Cook appears as the lead author, with scholars Trevon Logan and John Parman as coauthors. But this paper simply duplicates word-for-word much of Logan and Parman’s prior work without Cook. For example, the year prior, Logan and Parman published an original paper, with the following language: 

The 1880 census comes after the Civil War and before the nation moved to Jim Crow. For example, at the time of the 1880 census, the Civil Rights Act of 1875, which guaranteed equal protection in public accommodation, was still in place although not necessarily enforced. The 1940 census, however, depicts residential patterns after the rise of Jim Crow, the Great Migration, and the influx of European immigrants. Importantly, the 1940 census comes largely before the rise of significant suburbanization seen in the post-war years. It is this period from the late-nineteenth century to 1940 that Cutler, Glaeser and Vigdor (1999) cite as the rise of the American ghetto. While urban segregation as measured by isolation and dissimilarity was generally rising, the segregation patterns across cities tended to persist over time, with the most segregated cities at the turn of the century also being the most segregated cities at the end of the century. The complete census returns for 1880 and 1940 allow us to see whether our neighbor-based segregation index shows a similar rise in urban segregation and whether a comparable change in segregation occurred in rural areas. 

[ . . . ]

Table 3 shows the variation in our neighbor-based segregation index by census region in both 1880 and 1940. All statistics are weighted by the number of black households in the county so they should be interpreted as representing the level of segregation experienced by the average black household. Counties are divided between rural and urban to distinguish between the segregation patterns described by Cutler, Glaeser, and Vigdor specific to cities and more general patterns affecting the rest of the population. As noted earlier, we designate a county as urban if more than one-quarter of the households from that county live in an urban area and rural if less than one-quarter of the households live in an urban area. 

Cook duplicates long passages verbatim, marked here in italics, without quotation or proper attribution: 

The 1880 census comes after the Civil War and before the nation moved systematically to Jim Crow. For example, at the time of the 1880 census, the Civil Rights Act of 1875, which guaranteed equal protection in public accommodation, was still in place. The 1940 census, however, depicts residential patterns after the rise of Jim Crow, the Great Migration, and the influx of European immigrants. Importantly, the 1940 census comes largely before the rise of significant suburbanization seen in the postwar years. It is this period from the late-19th century to 1940 that Cutler, Glaeser, and Vigdor (1999) cite as the rise of the American ghetto. While urban segregation as measured by isolation and dissimilarity was generally rising, the segregation patterns across cities tended to persist over time, with the most segregated cities at the turn of the century also being the most segregated cities at the end of the century. The complete census returns for 1880 and 1940 and the Logan-Parman measure provide an opportunity to test whether a comparable change in segregation occurred in rural areas.

[ . . . ]

Figure 3 shows the variation in our segregation index from 1880 through 1940. All statistics are weighted by the number of black households in the county and should therefore be interpreted as representing the level of segregation experienced by the average black household. Counties are divided between rural and urban to distinguish between the segregation patterns described by Cutler, Glaeser, and Vigdor (1999) that were specific to cities and more general patterns affecting the rest of the population. We follow Logan and Parman (2017) and define a county as urban if more than one-quarter of the households from that county live in an urban area and rural if less than one-quarter of the households live in an urban area.

Complicating things further, that 2018 paper by the same three authors also recycled, without proper attribution, long passages of identical language from an article they published in another journal, “Racial Segregation and Southern Lynching.” Here is a passage from the earlier paper:

As such, the predicted correlation of residential segregation in political theories is indeterminate. The effect of segregation could lead to more racial violence or less. The direction of the effect depends on how whites view the potential outcomes of black political advancement. Most narrative histories suggest that whites held great apprehension of black political advances irrespective of their interaction with blacks. At the same time, whether segregation mediated or enhanced any of those sentiments is unknown, particularly because rural segregation has not received sustained attention in the literature. [ . . . ]

The Logan-Parman measure is an intuitive approach to residential segregation. They assert that the location of households in adjacent units can be used to measure the degree of integration or segregation in a community, similar to Schelling’s (1971) classic model of household alignment. Areas that are well integrated will have a greater likelihood of opposite race neighbors that corresponds to the underlying racial proportion of households in the area. The opposite is also true—segregated areas will have a lower likelihood of opposite race neighbors than the racial proportions would predict. The measure relies on the individual-level data available in federal census records. With the 100% sample of the federal census available through the Minnesota Population Center’s Integrated Public Use Microdata Series (IPUMS), it is possible to identify the races of next-door neighbors. Census enumerators went door to door to record households, meaning that next-door neighbors are adjacent to one another on the census manuscript page. The number of black households with white neighbors in a county can therefore be calculated by looking at the order and races of all household heads on the census manuscript pages. The measure is based on comparing this number of black households in a community with white neighbors to the number expected under complete integration and under complete segregation.

And here is a passage from the second paper, with verbatim language in italics. The minor word and punctuation substitutions, which are as trivial as replacing an em dash with a colon, suggest a certain measure of deliberate modification of the copied text:

The predicted correlation of residential segregation in political theories, in contrast, is indeterminate. The effect of segregation could lead to more racial violence or less. The direction of the effect depends on how whites view the potential outcomes of black political advancement. Most narrative histories suggest that whites held great apprehension of black political advances irrespective of their interaction with blacks. At the same time, whether segregation mediated or enhanced any of those sentiments is unknown, particularly because rural segregation has not received sustained attention in the literature. [ . . . ]

They assert that the location of households in adjacent units can be used to measure the degree of integration or segregation in a community, similar to Schelling’s (1971) classic model of household alignment. Areas that are well integrated will have a greater likelihood of different-race neighbors that corresponds to the underlying racial proportion of households in the area. The opposite is also true: segregated areas will have a lower likelihood of different-race neighbors than the racial proportions would predict. The measure relies on the individual-level data available in federal census records. With the 100 percent sample of the 1880 federal census available through the Minnesota Population Center’s Integrated Public Use Microdata Series (IPUMS) and the 100 percent samples of the 1900 through 1940 censuses hosted by the National Bureau of Economic Research (NBER), it is possible to identify the races of next-door neighbors. Census enumerators went door to door to record households, meaning that next-door neighbors are adjacent to one another on the census manuscript page. The number of black households with white neighbors in a county can, therefore, be calculated by looking at the order and races of all household heads on the census manuscript pages. The measure is based on comparing the actual number of black households in a community with white neighbors to the number expected under complete integration and under complete segregation.

Finally, Cook recycled substantial portions of at least three passages from her own 2011 paper, “Inventing social capital: Evidence from African American inventors, 1843–1930,” in the 2014 paper on patents that helped propel her to academic stardom.

When reached for comment, a Federal Reserve spokesman pointed to Cook’s prior testimony to Congress, in which she stated: “I certainly am proud of my academic background.”

Does the deliberate recycling of old material, including material from coauthors, constitute academic misconduct? It is true that journalists, for example, often adapt previous reporting into a compilation or a book. But the standard in academia is more rigorous. According to the Michigan State University guidebook, republishing identical material across multiple journals, without proper attribution, appears to be a violation of the rule against “self-plagiarism.” The standard is that scholars cannot use copied language “regardless of whether [they] are or are not the author of the source of the copied text or idea.”

What should the consequences be for this kind of academic misconduct? At Michigan State, administrators have warned students that “plagiarism is considered fraud and has potentially harsh consequences including loss of job, loss of reputation, and the assignation of reduced or failing grade in a course.” Certainly, for an esteemed professor and now a governor of the Federal Reserve, that standard should be the bare minimum.

Cook is no stranger to mobilizing such punishments against others. In 2020, she participated in the attempted defenestration of esteemed University of Chicago economist Harald Uhlig for the crime of publicly opposing the “defund the police” movement. She called for Uhlig’s removal from the classroom, claiming that he had made an insensitive remark about Martin Luther King, Jr. (The university closed its own inquiry after concluding that there was “not a basis” to investigate further.) Uhlig, in a 2022 op-ed for the Wall Street Journal, asked the pertinent question: Under the leadership of an ideologue such as Lisa Cook, would the Fed continue to pursue its mandate, or succumb to left-wing activism?

Time will tell if the gears of justice turn against Lisa Cook, or if repeated academic misconduct, defended by some as mere sloppiness or isolated mistakes, is fast becoming an acceptable part of the academic order—as long as the alleged author of that behavior is favored by the powerful.