Essays in the econometrics of asset pricing and public health

Abstract

In this thesis, I employ techniques from time series econometrics to study the detection of asset price bubbles and the measurement of vaccine uptake. In Chapter 1, I analyse some commonly used bubble detection tests that have been derived from simplified present value relationships. I apply the tests to a flexible, estimated present value model and study their size and power properties. I find that, under the null hypothesis of price being equal to fundamental value, no time series based test allows for correct inference under conventional critical values. Comparing tests under the alternative hypothesis, tests for periodically explosive growth minimize maximum regret. The next two chapters analyse human papillomavirus (HPV) vaccinations in Denmark. In Chapter 2, coauthored with Peter R. Hansen, we develop a dynamic model of vaccine compliance, based on the score-driven paradigm. The model estimates a time-varying compliance parameter, controlling for age effects and changing seasonality, and can diagnose events that impacted vaccine compliance. We apply the model to the weekly HPV vaccination data and find that compliance fell sharply following the broadcast of a controversial TV documentary. We also find that vaccine-critical media stories predict drops in compliance. Chapter 3, coauthored with Peter R. Hansen and Noel T. Brewer, analyses more recent HPV vaccination data that have been sampled monthly. The lower frequency enables us to employ a simple method to control for seasonal and age effects. The longer sample period allows for the evaluation of a national information campaign that advertised the HPV vaccine's safety and effectiveness. We find that, after the information campaign began, HPV uptake recovered to its baseline level. Still, we estimate that 26,000 fewer girls received their first HPV vaccination as a result of the period of low compliance studied in Chapter 2, compared to a scenario in which uptake had not declined.