Comments on: Bipartisanship http://hea-www.harvard.edu/AstroStat/slog/2008/bipartisanship/ Weaving together Astronomy+Statistics+Computer Science+Engineering+Intrumentation, far beyond the growing borders Fri, 01 Jun 2012 18:47:52 +0000 hourly 1 http://wordpress.org/?v=3.4 By: Alex http://hea-www.harvard.edu/AstroStat/slog/2008/bipartisanship/comment-page-1/#comment-839 Alex Thu, 18 Dec 2008 05:09:32 +0000 http://hea-www.harvard.edu/AstroStat/slog/?p=1360#comment-839 I have seen "robustness" brought up in conversations about Bayesian methods in astronomy. However, in such cases, the robustness typically comes from some features of the underlying probability model, not the Bayesian nature of the analysis. For example, when modeling luminosities, the use of fatter tailed distribution (say, a power law or even a log-normal) often serves to make inferences more robust to than inclusion of very bright sources than traditional least-squares methods. So, in my experience at least, it has really been a matter of getting a better, highly structured model for the phenomenon in place. These models are typically well-suited to Bayesian inference methods, but it is essentially a separate issue. I have seen “robustness” brought up in conversations about Bayesian methods in astronomy. However, in such cases, the robustness typically comes from some features of the underlying probability model, not the Bayesian nature of the analysis. For example, when modeling luminosities, the use of fatter tailed distribution (say, a power law or even a log-normal) often serves to make inferences more robust to than inclusion of very bright sources than traditional least-squares methods. So, in my experience at least, it has really been a matter of getting a better, highly structured model for the phenomenon in place. These models are typically well-suited to Bayesian inference methods, but it is essentially a separate issue.

]]>
By: TomLoredo http://hea-www.harvard.edu/AstroStat/slog/2008/bipartisanship/comment-page-1/#comment-834 TomLoredo Tue, 16 Dec 2008 21:46:55 +0000 http://hea-www.harvard.edu/AstroStat/slog/?p=1360#comment-834 Hyunsook summarized her encounters with astronomers who favor Bayesian procedures: me: <b>Why Bayesian methods?</b> astronomers: <b>Because Bayesian is robust. Because frequentist method is not robust.</b> Hyunsook, before you spend too much time with future posts addressing this, I thought I'd chime in by noting (1) I have never heard "robustness" used as a prime motivation for a Bayesian approach; (2) I have never offered that motivation myself. I don't know who you've been speaking with about this, but I suspect there is a misunderstanding on one or the other side of the conversations (perhaps about Bayesian statistics, or about the statistical meaning of "robust"). For what it's worth, a few years ago, on the occasion of a review talk for an interdisciplinary gathering of astronomers, statisticians, and philosophers of science, I did a quick and informal survey of a dozen or so astronomers who have prominently featured Bayesian methods in their work, asking them why they adopted the Bayesian approach. Not a single respondent using the word "robust." Overarching themes to their responses included: (1) Bayesian methods more directly answered their actual scientific questions or more straightforwardly addressed their problems, (2) conceptual/philosophical soundness or simplicity in terms of foundations, (3) teaching experience (physics students find frequentist reasoning confusing), (4) a level of trust in domain-specific scientific intuition, and wanting to reason as directly and explicitly as possible from that intuition. (This latter motivation, expounded at length by one respondent, is almost the opposite of robustness.) There were also numerous more technical motivations given, such as needing to straightforwardly combine disparate sources of information, or needing to handle nuisance parameters in complex settings. I do think robustness is an interesting issue in itself (and one that, narrowly defined, could well be used to motivate a frequentist approach to some problems), but I don't think you'll find robustness to be the primary motivation for Bayesian approaches in astronomy. Hyunsook summarized her encounters with astronomers who favor Bayesian procedures:

me: Why Bayesian methods?
astronomers: Because Bayesian is robust. Because frequentist method is not robust.

Hyunsook, before you spend too much time with future posts addressing this, I thought I’d chime in by noting (1) I have never heard “robustness” used as a prime motivation for a Bayesian approach; (2) I have never offered that motivation myself. I don’t know who you’ve been speaking with about this, but I suspect there is a misunderstanding on one or the other side of the conversations (perhaps about Bayesian statistics, or about the statistical meaning of “robust”).

For what it’s worth, a few years ago, on the occasion of a review talk for an interdisciplinary gathering of astronomers, statisticians, and philosophers of science, I did a quick and informal survey of a dozen or so astronomers who have prominently featured Bayesian methods in their work, asking them why they adopted the Bayesian approach. Not a single respondent using the word “robust.” Overarching themes to their responses included: (1) Bayesian methods more directly answered their actual scientific questions or more straightforwardly addressed their problems, (2) conceptual/philosophical soundness or simplicity in terms of foundations, (3) teaching experience (physics students find frequentist reasoning confusing), (4) a level of trust in domain-specific scientific intuition, and wanting to reason as directly and explicitly as possible from that intuition. (This latter motivation, expounded at length by one respondent, is almost the opposite of robustness.) There were also numerous more technical motivations given, such as needing to straightforwardly combine disparate sources of information, or needing to handle nuisance parameters in complex settings.

I do think robustness is an interesting issue in itself (and one that, narrowly defined, could well be used to motivate a frequentist approach to some problems), but I don’t think you’ll find robustness to be the primary motivation for Bayesian approaches in astronomy.

]]>