Postselection Inference in Structural Equation Modeling

Abstract

Most statistical inference methods were established under the assumption that the fitted model is known in advance. In practice, however, researchers often obtain their final model by some data-driven selection process. The selection process makes the finally fitted model random, and it also influences the sampling distribution of the estimator. Therefore, implementing naive inference methods may result in wrong conclusions—which is probably a prime source of the reproducibility crisis in psychological science. The present study accommodates three valid state-of-the-art postselection inference methods for structural equation modeling (SEM) from the statistical literature: data splitting (DS), postselection inference (PoSI), and the polyhedral (PH) method. A simulation is conducted to compare the three methods with the commonly used naive procedure under selection events made by L₁-penalized SEM. The results show that the naive method often yields incorrect inference, and that the valid methods control the coverage rate in most cases with their own pros and cons. Real world data examples show the practical use of the valid inference methods.     

The Health Insurance and Life Satisfaction Connection

Prior studies indicate that perceived health is strongly associated with a sense of well-being. The effect of health insurance is much less clear: there has been little rigorous empirical research assessing whether health coverage has an independent impact on individual happiness. This topic is especially important in the US where recently an estimated 18 % of the non-elderly were uninsured and extension of coverage through means such as the Affordable Care Act has been controversial. The present study addresses this question. Drawing from a large survey that collected comprehensive health and personal information about the US adult population, controlling for a wide variety of factors known to influence well-being, and addressing the possible endogeneity of having health insurance, we find that individuals without health insurance coverage were less likely to be “very satisfied” or “satisfied” with life. This may be because health insurance reduces uncertainty. Regardless of other benefits it may bring, the expansion of health insurance coverage should increase the life satisfaction of American society.     

Taking As: Experience & Judgment in the Life of Agents

Although appearances may deceive them, agents are capable of achieving their ends; this success is frequently explained by the fact that the agents may, for example, see a stick in water as bent without believing that it is actually bent. Although the notion of ‘seeing as’ is supposed to both bridge the gap between experience and action and explain our reaction to illusions, such accounts break down because of their exclusive focus on visual episodes and their tendency to interpret the metaphysics of agency in a psychologistic fashion. This paper shows that ‘seeing as’ needs to be understood as a species of the genus ‘taking as.’ The genus admits a wider array of expression, in terms of the kinds of attitudes, actions, and epistemological statuses involved. Such an analysis allows us to avoid the problems of ‘seeing as’ accounts and deepens our understanding of the relationship between practical and theoretical reason.     

Sales Productivity of Insurance Agents During the First Six Months of Employment: Differences Between Older and Younger New Hires

This study investigated the relationship of information-seeking from managers and coworkers, number of prospecting methods used, and number of joint sales calls the new hire went on with managers and coworkers to sales productivity during the first six months of employment. This study also investigated whether age was directly related to sales productivity, indirectly related through its influence on the other independent variables, or moderated the relationship between the independent variables and sales productivity. Results showed that age and going on joint sales calls with managers and coworkers were positively related to sales productivity. Age also served as a moderator. Older new hires who used a variety of prospecting techniques, and younger new hires who asked their peers for information about job and organizational procedures were better performers. The implications of these results for organizations are discussed.     

Double Agents

Jennifer Herdt's Putting On Virtue argues for the theological and normative superiority of noncompetitive accounts of divine and human agency. Although such accounts affirm the indispensability and sovereignty of divine grace they also acknowledge human agents as active participants in their own moral change. Indeed, Herdt contends we cannot coherently describe the human telos as entailing a transformation of character without affirming that human agents meaningfully contribute to that change. Nevertheless, a recurrent worry in Putting On Virtue is that persons may view their growth in virtue as a personal achievement and that the pleasure of positive self‐regard will displace disinterested—and hence truly virtuous—moral aspiration. This discussion of Herdt's volume sympathetically canvasses her argument. It then looks briefly at the reflexive structure of human agency to consider the relationship between the human telos and the transformation of character, and to encourage a more generous attitude toward positive self‐regard.     

Plural Agents

Genuine agents are able to engage in activity because they find it worth pursuing—because they care about it. In this respect, they differ from what might be called “mere intentional systems”: systems like chess‐playing computers that exhibit merely goal‐directed behavior mediated by instrumental rationality, without caring. A parallel distinction can be made in the domain of social activity: plural agents must be distinguished from plural intentional systems in that plural agents have cares and engage in activity because of those cares. In this paper, I sketch an account of what it is for an individual to care about things in terms of her exhibiting a certain pattern of emotions. After extending this account to make sense of an individual's caring about other agents, I then show how a certain sort of emotional connectedness among a group of people can make intelligible the group's having cares and thereby constitute that group as a plural agent. Alternative accounts of social action, by ignoring the difference between mere intentional systems and genuine agents, and so by leaving out these emotional entanglements from their accounts of social action, thereby fail to capture a whole range of social phenomena involving plural agents.     

The Influence of Agents

…We learn from anatomy, that the immediate object of power in voluntary motion, is not the member itself which is moved, but certain muscles, and nerves, and animal spirits, and, perhaps, something still more minute and more unknown, through which the motion is successively propagated, ere it reach the member itself whose motion is the immediate object of volition. Can there be a more certain proof, that the power, by which the whole operation is performed…is, to the last degree, mysterious and unintelligible?¹