Beyond Subjective and Objective in Statistics

Abstract

We argue that the words "objectivity" and "subjectivity" in statistics discourse are used in a mostly unhelpful way, and we propose to replace each of them with broader collections of attributes, with objectivity replaced by transparency, consensus, impartiality, and correspondence to observable reality, and subjectivity replaced by awareness of multiple perspectives and context dependence. The advantage of these reformulations is that the replacement terms do not oppose each other. Instead of debating over whether a given statistical method is subjective or objective (or normatively debating the relative merits of subjectivity and objectivity in statistical practice), we can recognize desirable attributes such as transparency and acknowledgment of multiple perspectives as complementary goals. We demonstrate the implications of our proposal with recent applied examples from pharmacology, election polling, and socioeconomic stratification.

The Prior Can Often Only Be Understood in the Context of the Likelihood

“…These different roles often motivate a distinction between "subjective" and "objective" choices of priors, but we are unconvinced of the relevance of this distinction [1]. We prefer to characterize Bayesian priors, and statistical models more generally based on the information they include rather than the philosophical interpretation of that information.…”

“…Perhaps most formally the prior serves to encode information germane to the problem being analyzed, but in practice it often becomes a means of stabilizing inferences in complex, high-dimensional problems. In other settings, the prior is treated as little more than a nuisance, serving simply as a catalyst for the expression of uncertainty via Bayes' theorem.These different roles often motivate a distinction between "subjective" and "objective" choices of priors, but we are unconvinced of the relevance of this distinction [1]. We prefer to characterize Bayesian priors, and statistical models more generally based on the information they include rather than the philosophical interpretation of that information.…”

The objectivity of Subjective Bayesianism

“…There is no surrogate for sound individual scientific judgment in this task. Subjective plausibility judgments are not only essential to Bayesian inference: they are part and parcel of NHST, and in fact, any method of scientific inference (for a practitioner's perspective, see Gelman and Hennig, 2017 to be much more convincing than the conventional p < .05 (Wagenmakers et al, 2011a). Indeed, what counts as substantial evidence against the null seems to be highly context-sensitive.…”

“…This move opens exactly those avenues for mutual criticism that are demanded from objective science (cf. Gelman and Hennig, 2017). In frequentist inference, however, such assumptions are often hidden behind the curtain (see Section 4).…”

Asking the public: Citizens´ views on priority setting and resource allocation in democratically governed healthcare

“…To assume that scholars who perform quantitative research are not aware of the multifacity of priority setting, is not credible. The division of the epithelium objective and subjective that is sometimes described to characterise quantitative and qualitative research has also been questioned (Gelman & Hennig, 2015). When science is thought of as objective, the subjectivity that the researchers must apply in their collecting and choice of data, in the analysis and in their presentation of data, is not acknowledged.…”