Dr. Marcel Neunhoeffer

ongoing Projects

• Synthetic data in statistics and computer science - a systematic evaluation and methodological improvements

• Continual Release of Differentially Private Synthetic Data from Longitudinal Data Collections

  Bun, M., Gaboardi, M., Neunhoeffer, M. & Zhang, W. (2024): Continual Release of Differentially Private Synthetic Data from Longitudinal Data Collections. In: Proceedings of the ACM on Management of Data, Vol. 2, No. 2, p. 1-26. DOI:10.1145/3651595

• On the Formal Privacy Guarantees of Synthetic Data

  Neunhoeffer, M., Latner, J. & Drechsler, J. (2024): On the Formal Privacy Guarantees of Synthetic Data. In: National Bureau of Economic Research (2024): Data Privacy Protection and the Conduct of Applied Research: Methods, Approaches and their Consequences, Spring 2024, Washington, p. 1-16.

• The Role of Hyperparameters in Machine Learning Models and How to Tune them

  Arnold, C., Biedebach, L., Küpfer, A. & Neunhoeffer, M. (2024): The Role of Hyperparameters in Machine Learning Models and How to Tune them. In: Political Science Research and Methods, Vol. 12, No. 4, p. 841-848. DOI:10.1017/psrm.2023.61

• How to improve the substantive interpretation of regression results when the dependent variable is logged

  Rittmann, O., Neunhoeffer, M. & Gschwend, T. (2023): How to improve the substantive interpretation of regression results when the dependent variable is logged. In: Political Science Research and Methods, p. 1-9. DOI:10.1017/psrm.2023.29

• Observing many researchers using the same data and hypothesis reveals a hidden universe of uncertainty

  Breznau, N., Rinke, E., Wuttke, A., Storz, N., Wolf, C., Ignácz, Z., Winter, F., Hunger, S., Tibajev, A., Hochman, O., Werner, H., Malancu, N., Sonntag, N., Langenkamp, A., Wagemans, F., Hirsch, M., Voicu, B., Maldonado, L., Vogtenhuber, S., Lutscher, P., Hootegem, A., Lersch, P., Noll, J., Kurti Sinatra, D., Linden, M., Kuk, J., Assche, J., Kolb, J., Wiernik, B., Löbel, L., Merhout, F., Burger, K., Otte, G., Damian, E., Nygård, O., Connelly, R., Nüst, D., Eger, M., Neunhoeffer, M., Ellerbrock, S., Moya, C., Burgdorf, K., Schulte-Cloos, J., Bostic, A., Micheli, L., Bohman, A., Prosser, C., Gnambs, T., Merk, S., Heisig, J., Mijs, J., Gummer, T., Mellon, J., Groß, M., Meierrieks, D., Godefroidt, A., Meeusen, C., Gessler, T., McWagner, K., Gavras, K., McManus, P., Forster, A., Mayorga, O., Grömping, M., Mayerl, J., Schumann, S., Steiber, N., Stroppe, A., Schmiedeberg, C., Jungkunz, S., Meyer, D., Stiers, D., Schneider, J., Steiner, N., Raes, L., Staudt, A., Schmidt-Catran, A., Sleegers, W., Schmidt, K., Seuring, J., Schmidt, R., Schunck, R., Schlueter, E., Wehl, N., Schieferdecker, D., Zins, S., Schaeffer, M., Zhang, N., Schachter, A., Huth, N., Sand, G., Hjerm, M., Samuel, R., Brzozowska, Z., Ropers, G., Madia, J., Rogers, J., Kleinert, M., Roets, A., Kołczyńska, M., Ramos, M., Busch, K., Ralston, K., Czymara, C., Schoonvelde, M., Carlos-Castillo, J., Kauff, M., Pechenkina, A., Jungmann, N., Chan, N., Hellmeier, S., Hadjar, A., Edelmann, A., Jacobs, L., Gayle, V., Gaasendam, C., Nguyen, H., Forke, A., Teltemann, J., Adem, M., Stojmenovska, D., Vagni, G., Jaeger, B., Silber, H., Jacobsen, J., Sternberg, S., Bobzien, L., Ziller, C., Blumenberg, J., Hövermann, A., Hunkler, C., Marahrens, H., Mader, M., Blinzler, K., Klinger, J., Biegert, T., Christmann, P., Bethke, F., Bol, T., Berthold, A., Heyne, S., Berning, C., Striessnig, E., Bernauer, J., Martinez, P., Benoit, V., Żółtak, T., Baute, S., Adriaans, J., Baumann, M., Ecker, A., Bauer, P., Gruber, S., Bauer, G., Tung, B., Balzer, D., Yamada, Y., Bahnsen, O., Martin, N., Azevedo, F., Schupp, J., Auer, D., Ochsenfeld, F., Andersen, H., Kunißen, K. & Alvarez-Benjumea, A. (2022): Observing many researchers using the same data and hypothesis reveals a hidden universe of uncertainty. In: Proceedings of the National Academy of Sciences of the United States of America, Vol. 119, No. 44. DOI:10.1073/pnas.2203150119

• Private Post-GAN Boosting

  Neunhoeffer, M., Wu, Z. & Dwork, C. (2021): Private Post-GAN Boosting. In: ICLR (Hrsg.) (2021): International Conference on Learning Representations 2021, p. 1-19.

• Ein Ansatz zur Vorhersage der Erststimmenanteile bei Bundestagswahlen

  Neunhoeffer, M., Gschwend, T., Munzert, S. & Stoetzer, L. (2020): Ein Ansatz zur Vorhersage der Erststimmenanteile bei Bundestagswahlen. In: Politische Vierteljahresschrift, Vol. 61, No. 1, p. 111-130. DOI:10.1007/s11615-019-00216-3

• How Cross-Validation Can Go Wrong and What to Do About It

  Neunhoeffer, M. & Sternberg, S. (2019): How Cross-Validation Can Go Wrong and What to Do About It. In: Political analysis, Vol. 27, p. 101-106. DOI:10.1017/pan.2018.39

• Forecasting Elections in Multiparty Systems: A Bayesian Approach Combining Polls and Fundamentals

  Stoetzer, L., Neunhoeffer, M., Gschwend, T., Munzert, S. & Sternberg, S. (2019): Forecasting Elections in Multiparty Systems: A Bayesian Approach Combining Polls and Fundamentals. In: Political analysis, Vol. 27, p. 255-262. DOI:10.1017/pan.2018.49

• Zweitstimme.org. Ein strukturell-dynamisches Vorhersagemodell für Bundestagswahlen

  Munzert, S., Stötzer, L., Gschwend, T., Neunhoeffer, M. & Sternberg, S. (2017): Zweitstimme.org. Ein strukturell-dynamisches Vorhersagemodell für Bundestagswahlen. In: Politische Vierteljahresschrift, Vol. 58, No. 3, p. 418-441. DOI:10.5771/0032-3470-2017-3-418