|
06. Oktober 2018, 00:36 |
|||
Inference in Difference-in-Differences Studies with Observational Data Using Non-Parametric Tests (with S. Bunnenberg) |
|||
|
Researchers use difference-in-differences models to evaluate the causal effects of policy changes. As the empirical correlation across firms and time can be ambiguous, estimating consistent standard errors is difficult and statistical inferences may be biased. We apply an approximate permutation test using simulated interventions to reveal the empirical error distribution of estimated policy effects. In contrast to existing econometric corrections, such as single- or double-clustering, this approach does not impose any parametric form on the data. In comparison with alternative parametric tests, this procedure maintains correct size with simulated and real-world interventions. Simultaneously, it improves power.
Paper Download |
|||
|
|||
|
|
|||
|
06. Oktober 2018, 00:34 |
|||
Fee-based Financial Advice (with B. Loos und A. Hackethal) |
|||
|
What happens when clients can choose between fee-only advice (no inducements) and inducement-based advice while the advisors and the lists for selecting recommendations remain the same? Our data from a unique field experiment allows answering this question while controlling for changes in the behavior of the demand and supply side. Sophisticated customers and those who should benefit the most from fee-only advice are most likely to obtain it. Fee-only advice leads to an increase in adherence, portfolio values, trading, and also has a positive effect on performance. This suggests that individual investors could benefit from new business models or regulation of the supply side.
|
|||
|
|||
|
|
|||
|
06. Oktober 2018, 00:33 |
|||
Does Feedback on Personal Investment Success Help? (with L. Urban and S. Ahlswede) |
|||
|
In this natural field experiment with almost 2.000 customers of an online-broker we test what happens when investors receive feedback on their investment success in a monthly securities account report over a period of fifteen months.
An updated version will with extended results will be available soon. |
|||
|
|||
|
|
|||
| << Zurück | Seite 2 von 2 |
© Steffen Meyer