Daniel Kuehn

What Explains Variation in Title Charges? A Study of Five Large Markets

Title insurance and settlement costs represent a substantial proportion of real estate closing costs paid by consumers and add significantly to the cost of purchasing a home. This study uses data on mortgages in counties covering five major metropolitan real estate markets to estimate the extent of variation in title charges faced by consumers and the factors associated with those charges. The analyses address the following research questions:How much do title charges vary? What factors are associated with variation in total title charges and components of title charges? How much variation in these charges remains unexplained after controlling for a series of factors commonly thought to influence title charges?

An estimate of the error in self-reported college major

ABSTRACT This letter provides an estimate of the extent of error in self-reports of college major. A student’s field of study is an important determinant of labour market outcomes and of increasing interest to labour economists, but little is known about the reliability of survey data on college major. A unique dataset from the United States with both transcript and survey data on major field of study suggests that the error rate of self-reported college major is almost 20%. Error rates are higher for relatively small or obscure majors, and are lower for larger majors or majors closely associated with licensed professions (e.g. health care). Although these error rates are not trivial, they are comparable to prior estimates of error in reporting educational attainment.

Information Theory and Propensity Score Matching

This paper develops a generalized maximum entropy (GME) approach to propensity score matching (PSM). A GME discrete choice model is used to develop propensity scores and estimate treatment effects in a set of Monte Carlo simulations. The GME PSM is compared to a more traditional logit PSM. Sample sizes and common support regions are varied across simulations to reflect common problems in the program evaluation literature. The GME PSM exhibits bias levels that are comparable to the logit PSM, but it provides substantial improvements in the precision of treatment effect estimates (including lower standard deviation of the treatment effect estimate and lower RMSE).