Significance Tests Harm Progress in Forecasting

By Armstrong, J. Scott. 2007

167 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/db52dca8c7e0f6ae6125402ec4392f1f20215af0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Björn Schuller
2. Christoph Bergmeir
3. Fotios Petropoulos
4. Sven F. Crone
5. Devon K. Barrow
6. Anton Batliner
7. Spyros Makridakis
8. Stefan Steidl

In Management Science and Operations Research

1. Fotios Petropoulos
2. Rob J Hyndman
3. Konstantinos Nikolopoulos
4. Nikolaos Kourentzes
5. Vassilios Assimakopoulos
6. Spyros Makridakis
7. Sven F. Crone
8. Christoph Bergmeir

In Statistics and Probability

1. Konstantinos Nikolopoulos
2. Nikolaos Kourentzes
3. Fotios Petropoulos
4. Vassilios Assimakopoulos
5. Evangelos Spiliotis
6. Spyros Makridakis
7. Christoph Bergmeir
8. Stephan Kolassa

Citations in the corpus

• Combining Forecasts: An Application to Elections (2014, unknown): “When combining, Armstrong (2001) recommended using at least five forecasts.”
• Data Quality: Some Comments on the NASA Software Defect Datasets (2013, background): “This in itself may be a reason to pay more attention to effect sizes and less to null hypothesis testing and p values [1].”
• Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge (2011, background): “While measures for ground truth evaluation such as kappa (Fleiss et al., 1969; Rosenberg and Binkowski, 2004) are often found, significance tests (Nickerson, 2000; Armstrong, 2007) are practically ignored to the present day, but (cf. Steidl, 2009; Schuller et al., 2009b; Seppi et al., 2010).”
• Evaluating the forecasting performance of econometric models of air passenger traffic flows using multiple error measures (2011, unknown): “the arguments of Armstrong (2007), more importantly,”
• Forecasting: theory and practice (2020, background): “70 Another popular approach to judgmental forecasting using panels of experts is SA, which refers to the recollection of past experiences and the use analogies (Green and Armstrong, 2007).”
• Advances in forecasting with neural networks? Empirical evidence from the NN3 competition on time series prediction (2011, methodology): “Regardless of the recent and vivid discussion about statistical significance within the forecasting community (Armstrong, 2007a,b; Goodwin, 2007), we computed two non-parametric tests, replicating the analysis of the M3 by Koning et al. (2005): ANOM and MCB, both of which are based upon the average…”