Forecasting

Course summary

The future is uncertain, yet we strive to predict what may happen hours, days, weeks, months or even years in advance. What team will win the Swiss Football League? What party or candidate will clinch the next election? When will the next scientific breakthrough discovery be made, and who wil make it? All too often we imagine ourselves as expert forecasters, and opine to know what will happen in the future. But, despite the lure of the superforecasters, making good forecasts is equally fascinating as it is difficult. What information should a good forecast be based on, versus what are many forecasts actually based on? How should information be integrated versus how is information integrated? What actually is a good forecast, how can we judge its performance? Who is the better forecaster: Man or machine? In this seminar we cover the basic principles and psychology of (successful) prediction and examine how well various prediction techniques work under different conditions.

Aim of the course

This seminar is aimed at Master students, who will acquire an overview of different forecasting techniques, including judgmental and statistical methods, as well as hybrid forms. Weekly sessions will enable students to critically assess the pros, cons and required conditions of different methods, and to quantify their performance. Based on regular programming exercises in R Studio, students will learn to apply the theoretical insights and compute, assess and improve their own forecasts.

Background literature

Prerequisites

Basic programming skills in R (Studio) are essential for some of the weekly exercises. To practice and further develop your R skills, we will identify individually relevant opportunities for asynchronous learning, including online R tutorials and literature recommendations.

Sessions Spring Semester 2024

The Forecasting seminar in FS24 takes place on Tuesdays, 2:15 pm - 3:45 pm (GMT+1).

WEEK DATE TOPIC
1 27.02.24 Course overview & introduction
2 05.03.24 Overview of forecasting methods and scoring rules
+ Green, K. C., Graefe, A., & Armstrong, J. S. (2011). Forecasting Principles. In M. Lovric (Ed.), International Encyclopedia of Statistical Science (pp. 527–534). Springer.
+ Armstrong, J. S. (2006). Findings from evidence-based forecasting: Methods for reducing forecast error. International Journal of Forecasting, 22(3), 583–598.
3 12.03.24 Judgmental forecasting I: General framework for judgment
+ Hastie, R., & Dawes, R. M. (2010). A general framework for judgment. In R. Hastie & R. M. Dawes (Eds.), Rational choice in an uncertain world: The psychology of judgment and decision making (2nd ed., pp. 45–69). SAGE.
+ Hyndman, R.J. & Athanasopoulos, G. (2021). Judgmental forecasts. In R. Hyndman & G. Athanasopoulos (Eds.), Forecasting: Principles and Practice (chapter 6). OTexts.
4 19.03.24 Judgmental forecasting II: Group methods
+ Rowe, G., & Wright, G. (1999). The Delphi technique as a forecasting tool: Issues and analysis. International Journal of Forecasting, 15(4), 353–375.
+ Hastie, R., & Kameda, T. (2005). The robust beauty of majority rules in group decisions. Psychological Review, 112(2), 494–508.
5 26.03.24 Judgmental forecasting III: Heuristics and biases
+ Arkes, H. R. (2001). Overconfidence in Judgmental Forecasting. In J. S. Armstrong (Ed.), Principles of Forecasting: A Handbook for Researchers and Practitioners (pp. 495–515). Kluwer.
+ Hogarth, R. M. (2006). On ignoring scientific evidence: The bumpy road to enlightenment. In SSRN 1002512.
6 02.04.24 Judgmental versus statistical forecasting / General(ized) linear models
+ Dawes, R. M., Faust, D., & Meehl, P. E. (1989). Clinical versus actuarial judgment. Science, 243(4899), 1668–1674.
+ Yaniv, I., & Hogarth, R. M. (1993). Judgmental versus Statistical Prediction: Information Asymmetry and Combination Rules. Psychological Science, 4(1), 58–62.
+ Song, C. U., Boulier, B. L., & Stekler, H. O. (2007). The comparative accuracy of judgmental and model forecasts of American football games. International Journal of Forecasting, 23(3), 405–413.
+ Dawes, R. M. (1979). The robust beauty of improper linear models in decision making. American Psychologist, 34(7), 571–582.
+ Armstrong, J. S. (2001). Judgmental Bootstrapping: Inferring Experts’ Rules for Forecasting. In J. S. Armstrong (Ed.), Principles of Forecasting: A Handbook for Researchers and Practitioners (pp. 171–192). Kluwer.
7 09.04.24 RStudio bootcamp (asynchronous!)
8 16.04.24 Introduction to statistical forecasting using the R package fpp3: tsibbles, plotting, seasonal patterns
+ Hyndman, R.J., & Athanasopoulos, G. (2021). Time series graphics. Forecasting: Principles and Practice, 3rd edition, OTexts: Melbourne, Australia. https://otexts.com/fpp3/graphics.html. Accessed on 17.04.2023.
9 23.04.24 Statistical forecasting I: Time-series analysis I
+ Armstrong, J. S. M. (2001). Extrapolation for time-series and cross-sectional data. In J. S. Armstrong (Ed.), Principles of Forecasting: A Handbook for Researchers and Practitioners (pp. 215–243). Kluwer.
+ Hyndman, R.J., & Athanasopoulos, G. (2021) Forecasting: Principles and Practice, 3rd edition, OTexts.
10 30.04.24 Statistical forecasting II: Time-series analysis II
+ Armstrong, J. S. M. (2001). Extrapolation for time-series and cross-sectional data. In J. S. Armstrong (Ed.), Principles of Forecasting: A Handbook for Researchers and Practitioners (pp. 215–243). Kluwer.
+ Hyndman, R.J., & Athanasopoulos, G. (2021) Forecasting: Principles and Practice, 3rd edition, OTexts.
11 07.05.24 Statistical forecasting III: Overfitting, selection bias, & machine learning
+ Babyak, M. A. (2004). What you see may not be what you get: A brief, nontechnical introduction to overfitting in regression-type models. Psychosomatic Medicine, 66(3), 411–421.
+ Yarkoni, T., & Westfall, J. (2017). Choosing Prediction Over Explanation in Psychology: Lessons From Machine Learning. Perspectives on Psychological Science, 12(6), 1100–1122.
12 14.05.24 Statistical forecasting IV: Forecasting in social settings
+ Makridakis, S., Hyndman, R. J., & Petropoulos, F. (2020). Forecasting in social settings: The state of the art. International Journal of Forecasting, 36(1), 15–28.
+ Science special issue on Prediction.
13 21.05.24 Student presentations
14 28.05.24 Student presentations

Forecasting

Course summary

The future is uncertain, yet we strive to predict what may happen hours, days, weeks, months or even years in advance. What team will win the Swiss Football League? What party or candidate will clinch the next election? When will the next scientific breakthrough discovery be made, and who wil make it? All too often we imagine ourselves as expert forecasters, and opine to know what will happen in the future. But, despite the lure of the superforecasters, making good forecasts is equally fascinating as it is difficult. What information should a good forecast be based on, versus what are many forecasts actually based on? How should information be integrated versus how is information integrated? What actually is a good forecast, how can we judge its performance? Who is the better forecaster: Man or machine? In this seminar we cover the basic principles and psychology of (successful) prediction and examine how well various prediction techniques work under different conditions.

Aim of the course

This seminar is aimed at Master students, who will acquire an overview of different forecasting techniques, including judgmental and statistical methods, as well as hybrid forms. Weekly sessions will enable students to critically assess the pros, cons and required conditions of different methods, and to quantify their performance. Based on regular programming exercises in R Studio, students will learn to apply the theoretical insights and compute, assess and improve their own forecasts.

Background literature

Prerequisites

Basic programming skills in R (Studio) are essential for some of the weekly exercises. To practice and further develop your R skills, we will identify individually relevant opportunities for asynchronous learning, including online R tutorials and literature recommendations.

Sessions Spring Semester 2024

The Forecasting seminar in FS24 takes place on Tuesdays, 2:15 pm - 3:45 pm (GMT+1).

WEEK DATE TOPIC
1 27.02.24 Course overview & introduction
2 05.03.24 Overview of forecasting methods and scoring rules
+ Green, K. C., Graefe, A., & Armstrong, J. S. (2011). Forecasting Principles. In M. Lovric (Ed.), International Encyclopedia of Statistical Science (pp. 527–534). Springer.
+ Armstrong, J. S. (2006). Findings from evidence-based forecasting: Methods for reducing forecast error. International Journal of Forecasting, 22(3), 583–598.
3 12.03.24 Judgmental forecasting I: General framework for judgment
+ Hastie, R., & Dawes, R. M. (2010). A general framework for judgment. In R. Hastie & R. M. Dawes (Eds.), Rational choice in an uncertain world: The psychology of judgment and decision making (2nd ed., pp. 45–69). SAGE.
+ Hyndman, R.J. & Athanasopoulos, G. (2021). Judgmental forecasts. In R. Hyndman & G. Athanasopoulos (Eds.), Forecasting: Principles and Practice (chapter 6). OTexts.
4 19.03.24 Judgmental forecasting II: Group methods
+ Rowe, G., & Wright, G. (1999). The Delphi technique as a forecasting tool: Issues and analysis. International Journal of Forecasting, 15(4), 353–375.
+ Hastie, R., & Kameda, T. (2005). The robust beauty of majority rules in group decisions. Psychological Review, 112(2), 494–508.
5 26.03.24 Judgmental forecasting III: Heuristics and biases
+ Arkes, H. R. (2001). Overconfidence in Judgmental Forecasting. In J. S. Armstrong (Ed.), Principles of Forecasting: A Handbook for Researchers and Practitioners (pp. 495–515). Kluwer.
+ Hogarth, R. M. (2006). On ignoring scientific evidence: The bumpy road to enlightenment. In SSRN 1002512.
6 02.04.24 Judgmental versus statistical forecasting / General(ized) linear models
+ Dawes, R. M., Faust, D., & Meehl, P. E. (1989). Clinical versus actuarial judgment. Science, 243(4899), 1668–1674.
+ Yaniv, I., & Hogarth, R. M. (1993). Judgmental versus Statistical Prediction: Information Asymmetry and Combination Rules. Psychological Science, 4(1), 58–62.
+ Song, C. U., Boulier, B. L., & Stekler, H. O. (2007). The comparative accuracy of judgmental and model forecasts of American football games. International Journal of Forecasting, 23(3), 405–413.
+ Dawes, R. M. (1979). The robust beauty of improper linear models in decision making. American Psychologist, 34(7), 571–582.
+ Armstrong, J. S. (2001). Judgmental Bootstrapping: Inferring Experts’ Rules for Forecasting. In J. S. Armstrong (Ed.), Principles of Forecasting: A Handbook for Researchers and Practitioners (pp. 171–192). Kluwer.
7 09.04.24 RStudio bootcamp (asynchronous!)
8 16.04.24 Introduction to statistical forecasting using the R package fpp3: tsibbles, plotting, seasonal patterns
+ Hyndman, R.J., & Athanasopoulos, G. (2021). Time series graphics. Forecasting: Principles and Practice, 3rd edition, OTexts: Melbourne, Australia. https://otexts.com/fpp3/graphics.html. Accessed on 17.04.2023.
9 23.04.24 Statistical forecasting I: Time-series analysis I
+ Armstrong, J. S. M. (2001). Extrapolation for time-series and cross-sectional data. In J. S. Armstrong (Ed.), Principles of Forecasting: A Handbook for Researchers and Practitioners (pp. 215–243). Kluwer.
+ Hyndman, R.J., & Athanasopoulos, G. (2021) Forecasting: Principles and Practice, 3rd edition, OTexts.
10 30.04.24 Statistical forecasting II: Time-series analysis II
+ Armstrong, J. S. M. (2001). Extrapolation for time-series and cross-sectional data. In J. S. Armstrong (Ed.), Principles of Forecasting: A Handbook for Researchers and Practitioners (pp. 215–243). Kluwer.
+ Hyndman, R.J., & Athanasopoulos, G. (2021) Forecasting: Principles and Practice, 3rd edition, OTexts.
11 07.05.24 Statistical forecasting III: Overfitting, selection bias, & machine learning
+ Babyak, M. A. (2004). What you see may not be what you get: A brief, nontechnical introduction to overfitting in regression-type models. Psychosomatic Medicine, 66(3), 411–421.
+ Yarkoni, T., & Westfall, J. (2017). Choosing Prediction Over Explanation in Psychology: Lessons From Machine Learning. Perspectives on Psychological Science, 12(6), 1100–1122.
12 14.05.24 Statistical forecasting IV: Forecasting in social settings
+ Makridakis, S., Hyndman, R. J., & Petropoulos, F. (2020). Forecasting in social settings: The state of the art. International Journal of Forecasting, 36(1), 15–28.
+ Science special issue on Prediction.
13 21.05.24 Student presentations
14 28.05.24 Student presentations