Patrick W. Schmidt

Welcome to my website! I am a researcher at the University of Zurich at the chair of Quantitative Methods of Intervention and Evaluation, currently on leave and a visiting Professor at Goethe University Frankfurt, where I teach econometrics. I studied Mathematics with a major in computational statistics at Heidelberg University and obtained my PhD in Economics from the Graduate School for Economics, Finance and Management (GSEFM) at Goethe University Frankfurt.

I work on uncertainty quantification in forecasting, surveys, experiments, health, and economic modeling. My work lies at the crossroads between decision science, computational statistics, and economics.

Contact:

Email: PatrickWolfgang.Schmidt@uzh.ch

Publications

Inference under Superspreading: Determinants of SARS-CoV-2 Transmission in Germany.

Statistics in Medicine, 2024.

Replication repository

Data repository

Identifying dynamic shifts to non-compliant behavior in questionnaire responses; A novel approach and experimental validation .

Structural Equation Modeling, 2024.

with Zachary Joseph Roman, Jason Michael Miller, Holger Brandt

Belief elicitation with multiple point predictions.

European Economic Review, 2021.

with Markus Eyting (GSEFM Frankfurt)

Online Supplement

Interpretation of point forecasts with unknown directive,

Journal of Applied Econometrics, 36(6), 728--743, 2021.

with Matthias Katzfuss (Texas A&M) and Tilmann Gneiting (HITS, KIT)

Github repository

Discussion of "Elicitability and backtesting: Perspectives for banking regulation".

The Annals of Applied Statistics, 11(4):1883-1885, 2017.

Working Papers

Elicitation of ambiguous beliefs with mixing bets (first version: 2019).

Conditionally Accepted at American Economic Journal: Microeconomics.

Online Supplement

Testing forecast rationality for measures of central tendency (first version: 2019).

R&R at Review of Economics and Statistics.

with Andrew J. Patton (Duke) and Timo Dimitriadis (Heidelberg)

Subjective belief distributions in an Indian consumption panel with ﬁsher households (2022)

with Xavier Giné (World Bank)

Generalized Mincer-Zarnowitz regressions (2022)

Work in Progress

Dynamic Measurement Invariance with Bayesian shrinkage

with Holger Brandt (University of Tübingen)

Beyond simulations: Stratified randomization and regression adjustments for experimental data (draft available upon request)

with Simon Heß (University of Vienna)

Optimal state-dependent forecasting for Value-at-Risk under the Basel Accord (slides available upon request)

Software Package in R

PointFore (available on CRAN and Github):

Estimate specification models for the state-dependent level of an optimal quantile/expectile forecast. Wald Tests and the test of overidentifying restrictions are implemented. Plotting of the estimated specification model is possible. The package contains two data sets with forecasts and realizations: the daily accumulated precipitation at London, UK from the high-resolution model of the European Centre for Medium-Range Weather Forecasts (ECMWF) and GDP growth Greenbook data by the US Federal Reserve. See Schmidt, Katzfuss and Gneiting (2021) for more details on the identification and estimation of a directive behind a point forecast.

Further R-Packages are currently available upon request and will be uploaded when research papers are finished. Please get in contact.

Inference under Superspreading: Determinants of SARS-CoV-2 Transmission in Germany (2020). Github project: InfSup.
Testing rationality of mean, median and mode forecasts based on the paper "Testing forecast rationality for measures of central tendency".
Fitting probability distributions to quantiles and interval probabilities and extract functionals and scores from fitted distributions based on the paper "Belief elicitation with multiple point predictions".