Robust SEs were computed because of heteroscedasticity. (academic.oup.com)
This study utilizes an econometric approach based on univariate and multivariate logit regressions with heteroscedasticity robust standard errors. (scirp.org)
The estimator can be used to try to overcome autocorrelation and heteroscedasticity of the residuals, which can impact the standard errors and thus the calculated t - statistics and p - values. (portfoliovisualizer.com)