Jump to content

Talk:Loss function

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia


Comment

[edit]

Though a loss function often has to do with economic cost or utility, my impression is that it doesn't always. Somebody who understands this better than I do should make sure this article is right. --RedHouse18 16:38, 17 April 2008 (UTC)

I added another domain in which loss function is used --Akats, 18 Oct 2011 — Preceding unsigned comment added by Akats (talkcontribs) 13:13, 18 October 2011 (UTC)[reply]

Dr. Benchimol's comment on this article

[edit]

Dr. Benchimol has reviewed this Wikipedia page, and provided us with the following comments to improve its quality:


General comment 1: this article is badly organized. I suggest a first section about theoretical loss functions (Quadratic loss function, Expected loss, 0-1 loss function, Regret), and a second about applications (statistics, Bayesian statistics, economics, decision rules, selection). Moreover, some other WikiPedia articles can be merged with this one (for instance: https://en.wikipedia.org/wiki/Loss_functions_for_classification )

General comment 2: this article does not cite relevant and recent literature about the core subject as well as about applications.

Specific comment: this article should mention the wide literature about loss functions in micro and macroeconomics (for instance, central bank's loss function). Some ideas:

Waud, Roger N, 1976. "Asymmetric Policymaker Utility Functions and Optimal Policy Under Uncertainty," Econometrica, Econometric Society, vol. 44(1), pages 53-66, January.

Cecchetti, Stephen G, 2000. "Making Monetary Policy: Objectives and Rules," Oxford Review of Economic Policy, Oxford University Press, vol. 16(4), pages 43-59, Winter.

Horowitz, Ann R., 1987. "Loss functions and public policy," Journal of Macroeconomics, Elsevier, vol. 9(4), pages 489-504.


Some general references:

L. Rosasco, A. Caponnetto, M. Piana and A. Verri, "Are loss functions all the same?", Neural Comput., vol. 16, pp. 1063-1076, 2004

Bao, Yong, Tae-Hwy Lee, and Burak Saltoglu. 2007. Comparing Density Forecast Models. Journal of Forecasting 26: 203–225.

Diebold, Francis X., and Glenn D. Rudebusch. 1989. Scoring the Leading Indicators. Journal of Business 62 (3): 369–391.

Diebold, Francis X., Todd A. Gunther, and Anthony S. Tay. 1998. Evaluating Density Forecasts with Applications to Financial Risk Management. International Economic Review 39: 863–883.

González-Rivera, Gloria, Tae-Hwy Lee, and Santosh Mishra. 2004. Forecasting Volatility: A Reality Check Based on Option Pricing, Utility Function, Value-at-Risk, and Predictive Likelihood. International Journal of Forecasting 20 (4): 629–645.

Granger, Clive W. J. 1999. Outline of Forecast Theory Using Generalized Cost Functions. Spanish Economic Review 1: 161–173.

Granger, Clive W. J., and M. Hashem Pesaran. 2000a. A Decision Theoretic Approach to Forecasting Evaluation. In Statistics and Finance: An Interface, eds. Wai-Sum Chan, Wai Keung Li, and Howell Tong. London: Imperial College Press.

Granger, Clive W. J., and M. Hashem Pesaran. 2000b. Economic and Statistical Measures of Forecast Accuracy. Journal of Forecasting 19: 537–560.

Harter, H. L. 1977. Nonuniqueness of Least Absolute Values Regression. Communications in Statistics—Theory and Methods A6: 829–838.

Hong, Yongmiao, and Tae-Hwy Lee. 2003. Inference on Predictability of Foreign Exchange Rates via Generalized Spectrum and Nonlinear Time Series Models. Review of Economics and Statistics 85 (4): 1048–1062.

Kullback, L., and R. A. Leibler. 1951. On Information and Sufficiency. Annals of Mathematical Statistics 22: 79–86.

Lee, Tae-Hwy, and Yang Yang. 2006. Bagging Binary and Quantile Predictors for Time Series. Journal of Econometrics 135: 465–497.

Manski, Charles F. 1975. Maximum Score Estimation of the Stochastic Utility Model of Choice. Journal of Econometrics 3 (3): 205–228.

Money, A. H., J. F. Affleck-Graves, M. L. Hart, and G. D. I.Barr. 1982. The Linear Regression Model and the Choice of p. Communications in Statistics—Simulations and Computations 11 (1): 89–109.

Nyquist, Hans. 1983. The Optimal Lp-norm Estimation in Linear Regression Models. Communications in Statistics—Theory and Methods 12: 2511–2524.

Powell, James L. 1986. Censored Regression Quantiles. Journal of Econometrics 32: 143–155.

Sawa, Takamitsu. 1978. Information Criteria for Discriminating among Alternative Regression Models. Econometrica 46:1273–1291.

West, Kenneth D. 1996. Asymptotic Inference about Prediction Ability. Econometrica 64: 1067–1084.

White, Halbert. 1994. Estimation, Inference, and Specification Analysis. Cambridge, U.K.: Cambridge University Press.

Zellner, Arnold. 1986. Bayesian Estimation and Prediction Using Asymmetric Loss Functions. Journal of the American Statistical Association 81: 446–451.


We hope Wikipedians on this talk page can take advantage of these comments and improve the quality of the article accordingly.

Dr. Benchimol has published scholarly research which seems to be relevant to this Wikipedia article:


  • Reference : Jonathan Benchimol, 2015. Money in the production function: A new Keynesian DSGE perspective. Southern Economic Journal, vol. 82(1), pages 152-184.

ExpertIdeasBot (talk) 16:18, 19 May 2016 (UTC)[reply]

Dr. Hyndman's comment on this article

[edit]

Dr. Hyndman has reviewed this Wikipedia page, and provided us with the following comments to improve its quality:


Each section is not too bad, but they don't flow and are not ordered in any kind of sensible manner.

A better structure would be:

1. Uses of loss functions * statistical estimation * classification * actuarial science * optimal control * risk management 2. Some popular loss functions * quadratic loss * 0-1 loss * regret

3. Selecting a loss functions


We hope Wikipedians on this talk page can take advantage of these comments and improve the quality of the article accordingly.

Dr. Hyndman has published scholarly research which seems to be relevant to this Wikipedia article:


  • Reference : Heather Booth & Rob J Hyndman & Leonie Tickle & Piet de Jong, 2006. "Lee-Carter mortality forecasting: a multi-country comparison of variants and extensions," Monash Econometrics and Business Statistics Working Papers 13/06, Monash University, Department of Econometrics and Business Statistics.

ExpertIdeasBot (talk) 11:14, 1 June 2016 (UTC)[reply]

Dr. Timmermann's comment on this article

[edit]

Dr. Timmermann has reviewed this Wikipedia page, and provided us with the following comments to improve its quality:


Additional important loss functions such as Linex loss, lin-lin loss, quad-quad, and the Elliott, Komunjer and Timmermann (2005) loss function should be covered. See, e.g., chapter 2 in Elliott and Timmermann (2016). Properties of optimal predictors under different loss functions (e.g., asymmetric loss leads to an optimally biased forecast) would also benefit from being covered.

Elliott, G., I. Komunjer, and A. Timmermann, 2005, Estimation and testing of forecast rationality under flexible loss. The Review of Economic Studies 72:1107--25.

Elliott, G. and A. Timmermann, 2016, Economic Forecasting. Princeton University Press.


We hope Wikipedians on this talk page can take advantage of these comments and improve the quality of the article accordingly.

We believe Dr. Timmermann has expertise on the topic of this article, since he has published relevant scholarly research:


  • Reference : Elliott, Graham & Timmermann, Allan G, 2007. "Economic Forecasting," CEPR Discussion Papers 6158, C.E.P.R. Discussion Papers.

ExpertIdeasBot (talk) 16:08, 12 July 2016 (UTC)[reply]

Dr. Walde's comment on this article

[edit]

Dr. Walde has reviewed this Wikipedia page, and provided us with the following comments to improve its quality:


The structure of this article could be improved. One could start with the discipline which provides the foundation for all other application, i.e. with mathematics. In mathematics, some function is maximized or minimized. In an application, this function can represent something desirable or non-desirable. In the latter, one can talk about a loss function.

Once the basics from maths are clear, one could introduce uncertainty and then talk about expected loss.

At this point, the introduction mixes very many aspects without clear organizing principle

These are then the principles. After the principles, one can talk about the applications in decision theory, economics, machine learning and so on.

Quadratic loss function and 0-1 functions seem to be examples. They could be grouped into one section on "examples for loss functions".

The section on regret is pretty short and should be part of some larger section e.g. on decision theory.


We hope Wikipedians on this talk page can take advantage of these comments and improve the quality of the article accordingly.

We believe Dr. Walde has expertise on the topic of this article, since he has published relevant scholarly research:


  • Reference : Christian Bayer & Klaus Walde, 2010. "Matching and Saving in Continuous Time: Theory," Working Papers 1004, Gutenberg School of Management and Economics, Johannes Gutenberg-Universitat Mainz, revised 13 Jan 2010.

ExpertIdeasBot (talk) 20:24, 24 September 2016 (UTC)[reply]

Requirements on being continuous

[edit]

Does it have to be c0, c1 or c2 continuous? Is that a requirement, or does it just make quasi-newton methods faster? Could someone add this content to section 2, along with any other requirements, thanks.

Feel free to delete this comment

[edit]

Given the absence of a means by which I can rate this article, I am unfortunately forced to abuse of the "Talk" function to give my opinion.

I would like to say nonetheless that this article is one of the most clear, concrete and elegant pieces of presentation I have read in a long time on Wikipedia, and in my humble opinion, many articles could benefit from a style guide that leans on this article in particular.

Feel free to delete this comment, as it truly does not belong here. :bow 2001:818:E264:2900:64FE:91ED:3736:462A (talk) 05:30, 21 August 2024 (UTC)[reply]