Washington, DC — A new CEPR paper finds new problems with analysis purporting to show that economic sanctions on Venezuela do not drive migration. The paper, by CEPR Senior Research Fellow Francisco Rodríguez and economist Giancarlo Bravo, examines methodology used by Dany Bahar and Ricardo Hausmann earlier this year in which Bahar and Hausmann claimed to find evidence against the hypothesis that oil sanctions on Venezuela lead to increased migration flows to the United States. Rodríguez and Bravo find that Bahar and Hausmann incorrectly applied cointegration methods, and that once this misspecification was corrected, Bahar and Hausmann’s evidence of cointegration in the data disappeared.

“Data clearly show that economic sanctions on Venezuela have directly and significantly negatively affected millions of Venezuelans,” Rodríguez said. “Data also show that millions of people have left Venezuela after these sanctions were enacted. No one has been able to show that sanctions haven’t been a factor in pushing people to leave Venezuela, let alone that somehow sanctions lead to less migration.”

• The CEPR paper examines claims made by Bahar and Hausmann that sanctions on Venezuela’s oil industry do not drive migration to the United States and finds no support for these claims in their own data. The CEPR economists have shown that Bahar and Hausmann’s results were based on an error: the use of a nonstandard and misspecified test to evaluate the existence of a long-run relationship between Venezuelan migration to the US and Venezuelan oil revenues. 

Rodríguez and Bravo explain that Bahar and Hausmann used a method known as cointegration testing to assess whether there was a long-run relationship between migration and oil revenues, but applied the method incorrectly. “This method is designed to be applied to the levels of variables, but Bahar and Hausmann mistakenly took first-differences of the series before running the test,” explained Rodríguez. “Once you correct that mistake, their results disappear.”

Rodríguez and Bravo tested Bahar and Hausmann’s methodology by running Monte Carlo simulations on time series of the length that Bahar and Hausmann used. Rodríguez and Bravo found that these yielded a false positive rate of 100 percent, identifying a long-term relationship even when two variables were completely unrelated. “These results imply that the Bahar-Hausmann approach is guaranteed to find evidence of cointegration even when no such relationship exists.”

This is not the first time that CEPR researchers found problems in the research of Bahar and Hausmann. In April of this year, Rodríguez and Bravo uncovered a coding error in Bahar and Hausmann’s paper that claimed that sanctions led to lower migration. Bahar and Hausmann acknowledged the mistake and corrected it, yet still claimed that their results supported their thesis. “This was a very odd response, as their coefficients had turned statistically insignificant after correcting the coding error,” said Rodríguez. “The norm in economics research is that you don’t claim that you have found evidence of an effect unless you can establish that it is statistically significant,” said Rodríguez. “Bahar and Hausmann have deviated substantially from this norm.”

Bahar and Hausmann cited US border encounters with Venezuelan nationals “to assess hypotheses about the effects of sanctions on migration flows,” but Rodríguez and Bravo point out that “A large share of Venezuelans who attempt to enter the United States today have spent several years living outside of Venezuela, often in countries like Colombia, Peru, or Mexico. It is unclear why their decisions to migrate to the United States would be affected by fluctuations in the resources under the control of Nicolás Maduro’s government.” 

CEPR has also noted that Bahar and Hausmann failed to consider the possible impact of US labor market conditions on Venezuelan migration, and Rodríguez and Bravo note that while “Bahar (2025) argues that labor market conditions in the US are a key determinant of border crossings, […] Bahar and Hausmann make no effort to control for this effect.”

###