Earlier in the regression section, we mentioned that the Ultimatum Game dataset we were working with was actually a repeated design, which means that there was a correlated variance structure because all of the observations were nested within each subject. The standard solution to this problem in a GLM framework is to treat subject as a fixed effect and add (n-1) variables indicating a dummy co...

In this paper we consider the asymptotic properties of the Instrumental Variables (IV) estimator of the parameters in a linear regression model with some random regressors, and other regressors that are dummy variables. The latter have the special property that the number of non-zero values is fixed, and does not increase with the sample size. We prove that the IV estimator of the coefficient v...

Researchers in education and the social sciences make extensive use of linear regression models in which the dependent variable is continuous-valued while the explanatory variables are a combination of continuous-valued regressors and dummy variables. The dummies partition the sample into groups, some of which may contain only a few observations. Such groups may easily include enough outliers t...

In this paper we consider estimation and unit root testing in AR(1) models with infinite variance innovations. Specifically, we study the asymptotic properties of estimators obtained by dummying out ”large” innovations, i.e. exceeding a given threshold. These estimators reflect the common practice of dealing with large residuals by including impulse dummies in the estimated regression. Iterativ...

Time and brand dummy variables are typically used as controls for omitted variables. The operating assumption made is that time dummies control for unobserved factors affecting price and brand dummies control for unobserved factors affecting quality. We investigate the validity of the latter assumption by explicitly controlling for supply and demand factors in hedonic regressions for stereo rec...