Statistical modelling

Office: V8-232 (UHG).
Office hours: on appointment.

Email: timo.adam@uni-bielefeld.de.
Phone: +49 521 106 4875.

Web profiles: LinkedIn, Google scholar.

Research

My research focuses on the development, implementation, and application of statistical models for stochastic processes. I am particularly interested in hidden Markov models (HMMs), Markov-switching regression models, and stochastic differential equations (SDEs) as well as their application in ecology (animal movement modelling) and economics (stock market modelling).

Publications in peer-reviewed journals (15)

1. Adam., T., Ötting, M., and Michels, R. (2023): Markov-switching decision trees. AStA Advances in Statistical Analysis, accepted.
2. Oelschläger, L., Adam, T., and Michels, R. (2023): fHMM: hidden Markov models for financial time series in R. Journal of Statistical Software, accepted.
3. Lennox, R.J., Afonso, P., Birnie-Gauvin, K., Dahlmo, L.S., Nilsen, C.I., Arlinghaus, R., Cooke, S.J., Souza, A.T., Jarić, I., Prchalová, M., Říha, M., Westrelin, S., Twardek, W., Aspillaga, E., Kraft, S., Šmejkal, M., Baktoft, H., Brodin, T., Hellström, G., Villegas-Ríos, D., Wiik Vollset, K., Adam, T., Sortland, L.K., Bertram, M.G., Crossa, M., Vogel, E.F., Gillies, N., and Reubens, J. (2023): Electronic tagging and tracking aquatic animals to understand a world increasingly shaped by a changing climate and extreme weather events. Canadian Journal of Fisheries and Acquatic Sciences, accepted.
4. Glennie, R., Adam, T., Leos-Barajas, V., Michelot, T., Photopoulou, T., and McClintock, B.T. (2023): Hidden Markov models: pitfalls and opportunities in ecology. Methods in Ecology and Evolution, 14(1), 43-56.
5. Oelschläger, L. and Adam, T. (2023): Detecting bearish and bullish markets in financial time series data using hierarchical hidden Markov models. Statistical Modelling, 23(2), 107-126.
6. Pohle, J., Adam, T., and Beumer, L. (2022): Flexible estimation of the state dwell-time distribution in hidden semi-Markov models. Computational Statistics and Data Analysis, 172, 107479.
7. Nathan, R., Monk, C.T., Arlinghaus, R., Adam, T., Alós, J., Assaf, M., Baktoft, H., Beardsworth, C.E., Bertram, M.G., Bijleveld, A.I., Brodin, T., Brooks, J.L., Campos-Candela, A., Cooke, S.J., Gjelland, K.Ø., Gupte, P.R., Harel, R., Hellström, G., Jeltsch, F., Killen, S.S., Klefoth, T., Langrock, R., Lennox, R.J., Lourie, E., Madden, J.R., Orchan, Y., Pauwels, I.S., Říha, M., Roeleke, M., Schlägel, U.E., Shohami, D., Signer, J., Toledo, S., Vilk, O., Westrelin, S., Whiteside, M.A., and Jarić, I. (2022): Big-data approaches lead to an increased understanding of the ecology of animal movement. Science, 375(6582), eabg1780.
8. Adam, T., Mayr, A., and Kneib, T. (2022): Gradient boosting in Markov-switching generalized additive models for location, scale, and shape. Econometrics and Statistics, 22, 3-16.
9. Lennox, R.J., Westrelin, S., Souza, A.T., Šmejkal, M., Říha, M., Prchalová, M., Nathan, R., Monk, C., Koeck, B., Killen, S., Jarić, I., Gjelland, K., Hollins, J., Hellstrom, G., Hansen, H., Cooke, S.J., Boukal, D., Brooks, J.L., Brodin, T., Baktoft, H., Adam, T., and Arlinghaus R. (2021): A role for lakes in revealing the nature of animal movement using high dimensional telemetry systems. Movement Ecology, 9(40), 1-28.
10. Nagel, R., Mews, S., Adam, T., Stainfield, C., Fox-Clarke, C., Toscani, C., Langrock, R., Forcada, J., and Hofmann, J.I. (2021): Movement patterns and activity levels are shaped by the neonatal environment in Antarctic fur seal pups. Scientific Reports, 11(14323).
11. Aquino-Baleytó, M., Leos-Barajas, V., Adam, T., Hoyos-Padilla, M., Santana-Morales, O., Galván-Magaña, F., González-Armas, R., Lowe, C.G., Ketchum, J.T., and Villalobos-Ortiz, H. (2021): Diving deeper into the underlying white shark behaviours at Guadalupe Island, Mexico. Ecology and Evolution, 11(21), 14932-14949.
12. Adam, T., Griffiths, C.A., Leos-Barajas, V., Meese, E.N., Lowe, C.G., Blackwell, P.G., Righton, D., and Langrock, R. (2019): Joint modelling of multi-scale animal movement data using hierarchical hidden Markov models. Methods in Ecology and Evolution, 10(9), 1536-1550.
13. Adam, T., Langrock, R., and Weiß, C.H. (2019): Penalized estimation of flexible hidden Markov models for time series of counts. METRON, 77(2), 87-104.
14. Langrock, R., Adam, T., Leos-Barajas, V., Mews, S., Miller, D.L., and Papastamatiou, Y.P. (2018): Spline-based nonparametric inference in general state-switching models. Statistica Neerlandica, 72(3), 179-200.
15. Leos-Barajas, V., Gangloff, E.J., Adam, T., Langrock, R., van Beest, F.M., Nabe-Nielsen, J., and Morales, J.M. (2017): Multi-scale modeling of animal movement and general behavior data using hidden Markov models with hierarchical structures. Journal of Agricultural, Biological and Environmental Statistics, 22(3), 232-248.

Preprint (1)

1. Byrnes, E.E., Adam, T., Feldmann, C.C., Kaplinskaya, L., Sticker, K., Fredebeul, R.J., Lear, K.O., Morgan, D.L., Beatty, S.J., Langrock, R., and Gleiss, A.C. (2023): Daily time constraints limit behavioural capacity to cope with thermally increased metabolic demands. bioRxiv.

Publications in conference proceedings (9)

1. Michels, R., Adam, T., and Ötting, M. (2023): Tree-based regression within a hidden Markov model framework. Book of Short Papers of the 13th Scientific Meeting on Classification and Data Analysis, accepted.
2. Adam, T., Ötting, M., and Michels, R. (2023): State-switching decision trees. Proceedings of the 37th International Workshop on Statistical Modelling, 1, 321-325.
3. Adam, T., Glennie, R., and Michelot, T. (2022): State-switching varying-coefficient stochastic differential equations. Proceedings of the 36th International Workshop on Statistical Modelling, 1, 3-7.
4. Adam, T. and Oelschläger, L. (2020): Hidden Markov models for multi-scale time series: an application to stock market data. Proceedings of the 35th International Workshop on Statistical Modelling, 1, 2-7.
5. Pohle, J., Adam, T., Beumer, L., and Langrock, R. (2020): Flexible estimation of the state dwell-time distribution in hidden semi-Markov models. Proceedings of the 35th International Workshop on Statistical Modelling, 1, 189-193.
6. Adam, T., Langrock, R., and Kneib, T. (2019): Model-based clustering of time series data: a flexible approach using non-parametric state-switching quantile regression models. Book of Short Papers of the 12th Scientific Meeting on Classification and Data Analysis, 19-22.
7. Adam, T., Langrock, R., and Weiß, C.H. (2019): Non-parametric inference in hidden Markov models for time series of counts. Proceedings of the 34th International Workshop on Statistical Modelling, 1, 135-140.
8. Adam, T., Mayr, A., Kneib, T., and Langrock, R. (2018): Statistical boosting for Markov-switching distributional regression models. Proceedings of the 33rd International Workshop on Statistical Modelling, 1, 30-35.
9. Adam, T., Leos-Barajas, V., Langrock, R., and van Beest, F.M. (2017): Using hierarchical hidden Markov models for joint inference at multiple temporal scales. Proceedings of the 32nd International Workshop on Statistical Modelling, 2, 181-184.

Dissertation (1)

1. Adam, T. (2020): On some flexible extensions of hidden Markov models. Dissertation, Bielefeld University.

Software (2)

1. Oelschläger, L., Adam, T., and Michels, R. (2023): fHMM: fitting hidden Markov models to financial data. R package, published on CRAN.
2. Adam, T. (2019): countHMM: penalized estimation of flexible hidden Markov models for time series of counts. R package, published on CRAN.

Blog post (1)

1. Adam, T. (2022): Hidden Markov models have pitfalls… Methods Blog: the Latest Methods in Ecology and Evolution.

Click here for a more detailed overview of my research activities.

Talks

Invited talks (12)

1. Multi-scale modelling of animal movement data using state-switching varying-coefficient stochastic differential equations. 15th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics), London, UK, December 2022.
2. Multi-scale movement modelling using state-switching varying-coefficient stochastic differential equations. IMS International Conference on Statistics and Data Science (ICSDS), Florence, Italy, December 2022.
3. State-switching varying-coefficient stochastic differential equations. 14th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics), London, UK/online, December 2021.
4. Hierarchical hidden Markov models: applications in ecology and economics. Seminar at the University of St Andrews, online, May 2021.
5. Statistical modeling of animal tracking data using hidden Markov models. Seminar at the Natural Resources Institute Finland (LUKE), Helsinki, Finland, September 2019.
6. Model-based clustering of time series data: a flexible approach using non-parametric state-switching quantile regression models. 12th Scientific Meeting on Classification and Data Analysis, Cassino, Italy, September 2019.
7. Statistical modelling of animal telemetry data at multiple temporal resolutions: hidden Markov models and extensions. 7th Nordic-Baltic Biometric Conference, Vilnius, Lithuania, June 2019.
8. Joint modeling of multi-scale time series data using hierarchical hidden Markov models. 11th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics), Pisa, Italy, December 2018.
9. Statistical modeling of animal telemetry data: hidden Markov models and extensions. 1st International Lake Fish Telemetry Group Workshop, Czech Academy of Sciences, České Budějovice, Czech Republic, November 2018.
10. Joint modelling of multi-scale animal movement data using hierarchical hidden Markov models: a practical introduction using R. Seminar at Iowa State University, Ames, USA, September 2018.
11. Gradient boosting in generalized Markov-switching regression models. 23rd International Conference on Computational Statistics (COMPSTAT), Iași, Romania, August 2018.
12. Statistical boosting in Markov-switching generalized additive models for location, scale, and shape. 10th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics), London, UK, December 2017.

Contributed talks (9)

1. A state-switching varying-coefficient stochastic differential equation model for narwhal diving behaviour and responses to sound exposure. Annual meeting of the British Ecological Society (BES), Belfast, UK, December 2023.
2. Understanding narwhal diving behaviour using varying-coefficient stochastic differential equations. Illulissat, Greenland, May 2023.
3. Multi-scale movement modelling using state-switching varying-coefficient stochastic differential equations. 8th International Statistical Ecology Conference (ISEC), Cape Town, South Africa/online, June 2022.
4. Hidden Markov models for multi-scale time series: an application to stock market data. 35th International Workshop on Statistical Modelling (IWSM), Bilbao, Spain/online, July 2021.
5. Modelling the state-switching dynamics in animal movement data using hidden semi-Markov models with non-parametric dwell-time distributions. Virtual National Centre for Statistical Ecology (NCSE) Conference, online, June 2021.
6. Non-parametric inference in hidden Markov models for time series of counts. 34th International Workshop on Statistical Modelling (IWSM), Guimarães, Portugal, July 2019.
7. Semi-parametric hidden Markov models for time series of counts. 5th DagStat, Munich, Germany, March 2019.
8. Statistical boosting for Markov-switching distributional regression models. 33rd International Workshop on Statistical Modelling (IWSM), Bristol, UK, July 2018.
9. Joint modelling of multi-scale animal movement data using hierarchical hidden Markov models. 6th International Statistical Ecology Conference (ISEC), St Andrews, UK, July 2018.

Poster presentations (2)

1. Multi-scale modeling of animal movement data using hierarchical hidden Markov models. 6th International Bio-Logging Science Symposium, Constance, Germany, September 2017.
2. Using hierarchical hidden Markov models for joint inference at multiple temporal scales. 32nd International Workshop on Statistical Modelling (IWSM), Groningen, The Netherlands, July 2017.