Some nonparametric dimensionality assessment procedures, such as DIMTEST and DETECT, use nonparametric estimates of item pair conditional covariances given an appropriately chosen subtest score as their basic building blocks. Such conditional covariances given some subtest score can be regarded as an approximation to the conditional covariances given an appropriately chosen unidimensional latent composite, where the composite is oriented in the multidimensional test space direction in which the subtest score measures best. In this paper, the structure and properties of such item pair conditional covariances given a unidimensional latent composite are thoroughly investigated, assuming a semiparametric IRT modeling framework called a generalized compensatory model. It is shown that such conditional covariances are highly informative about the multidimensionality structure of a test. The theory developed here is very useful in establishing properties of dimensionality assessment procedures, current and yet to be developed, that are based upon estimating such conditional covariances.

In particular, the new theory is used to justify the DIMTEST procedure. Because of the importance of conditional covariance estimation, a new bias reducing approach is presented. A byproduct of likely independent importance beyond the study of conditional covariances is a rigorous score information based definition of an item's and a score's direction of best measurement in the multidimensional test space.

An information-theoretic framework is used to analyze the knowledge content in multivariate cross classified data. Several related measures based directly on the information concept are proposed: the knowledge content (S) of a cross classification, its terseness (Zeta), and the separability (GammaX) of one variable, given all others. Exemplary applications are presented which illustrate the solutions obtained where classical analysis is unsatisfactory, such as optimal grouping, the analysis of very skew tables, or the interpretation of well-known paradoxes. Further, the separability suggests a solution for the classic problem of inductive inference which is independent of sample size.

It is shown that IRTs information function for an item is functionally related to “local” versions of classical test theories' signal/noise ratio and reliability coefficient.

We examine how monetary incentives and information about others’ dishonesty affect lying decisions and whether these two dimensions interact with each other. Our experiment consists of a repeated cheating game where we vary the monetary incentives (Low, High, and Very High) and information about others’ dishonesty (With or Without information). We find that dishonesty decreases when payoffs are Very High. Information has only a weak positive effect on average. Conditioning on beliefs, we find that those who overestimate (underestimate) cheating reduce (increase) dishonesty. Information and payoffs do not interact with each other.

Multidimensional forced-choice (MFC) tests are increasing in popularity but their construction is complex. The Thurstonian item response model (Thurstonian IRT model) is most often used to score MFC tests that contain dominance items. Currently, in a frequentist framework, information about the latent traits in the Thurstonian IRT model is computed for binary outcomes of pairwise comparisons, but this approach neglects stochastic dependencies. In this manuscript, it is shown how to estimate Fisher information on the block level. A simulation study showed that the observed and expected standard errors based on the block information were similarly accurate. When local dependencies for block sizes $>2$\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$>\,2$$\end{document} were neglected, the standard errors were underestimated, except with the maximum a posteriori estimator. It is shown how the multidimensional block information can be summarized for test construction. A simulation study and an empirical application showed small differences between the block information summaries depending on the outcome considered. Thus, block information can aid the construction of reliable MFC tests.

In computerized adaptive testing (CAT), a variable-length stopping rule refers to ending item administration after a pre-specified measurement precision standard has been satisfied. The goal is to provide equal measurement precision for all examinees regardless of their true latent trait level. Several stopping rules have been proposed in unidimensional CAT, such as the minimum information rule or the maximum standard error rule. These rules have also been extended to multidimensional CAT and cognitive diagnostic CAT, and they all share the same idea of monitoring measurement error. Recently, Babcock and Weiss (J Comput Adapt Test 2012. https://doi.org/10.7333/1212-0101001) proposed an “absolute change in theta” (CT) rule, which is useful when an item bank is exhaustive of good items for one or more ranges of the trait continuum. Choi, Grady and Dodd (Educ Psychol Meas 70:1–17, 2010) also argued that a CAT should stop when the standard error does not change, implying that the item bank is likely exhausted. Although these stopping rules have been evaluated and compared in different simulation studies, the relationships among the various rules remain unclear, and therefore there lacks a clear guideline regarding when to use which rule. This paper presents analytic results to show the connections among various stopping rules within both unidimensional and multidimensional CAT. In particular, it is argued that the CT-rule alone can be unstable and it can end the test prematurely. However, the CT-rule can be a useful secondary rule to monitor the point of diminished returns. To further provide empirical evidence, three simulation studies are reported using both the 2PL model and the multidimensional graded response model.

We introduce stochastic loss into a gift exchange game to study how information on intentions affects reciprocity. In one treatment, the respondent observes the amount received and whether a loss occurred, so both the consequential outcome and the sender’s original intention are known. In the other two treatments, information about whether a loss occurred is hidden, and the respondent is only informed of the amount received (outcome) or the amount initially sent (intention). Using both regression-based approaches and non-parametric tests, we find greater reciprocity in the two treatments that reveal intentions. These differences arise even in a simple one-shot setting without reputational benefits and are economically meaningful; they are similar in magnitude to the difference attributable to a full point reduction in the amount received. Our findings show the impact of the information environment on reciprocity in settings with uncertainty and suggest that transparency is important to reciprocity.

Offline volunteering was faced with new challenges during the COVID-19 pandemic. Using a survey experiment with 1207 student participants, we test the impact of informing subjects about blood donation urgency (shortage information), and secondly, the effect of providing information about measures taken to reduce SARS-CoV-2 transmission at blood donation centers (hygiene information), on their inclination to donate during and after the COVID-19 lockdown. The results show that shortage information increases extensive-margin willingness to donate for non-donors by 15 percentage points (pp), on average, and increases the willingness to donate quickly for all respondents. Hygiene information, however, reduces prior donors’ intention to donate again by 8pp, on average, and reduces the willingness of non-donors to donate quickly.

Control over the legislative messaging agenda has important political, electoral and policy consequences. Existing models of congressional agenda-setting suggest that national polarization drives the agenda. At the same time, models of home style and formal models of leadership hypothesize that legislators shift their messaging as they balance coordination and information problems. We say the coordination problem dominates when conditions incentivize legislators to agree on the same message rather than fail to reach consensus. Conversely, the information problem is said to dominate in circumstances where legislators prefer to say nothing at all rather than reach consensus on the wrong political message. Formal theories predict that when coordination problems are pressing, legislative members follow the policy positions of party leaders. When their party’s information problem is acute, party members instead rely on the wisdom of the caucus to set the party’s agenda. To test these theories, we analyze the Twitter accounts of U.S. House members with a Joint Sentiment Topic model, generating a new understanding of House leadership power. Our analyses reveal complex leader-follower relationships. Party leaders possess the power to substantially affect the propensity of rank-and-file members to discuss topics, especially when the coordination problem dominates; these effects are pronounced even when coordination problems are pressing. That said, when the underlying politics are unclear, rank-and-file members exert influence on the discussion of a topic because the information problem is more acute. At the same time and for these uncertain topics, leadership influence decreases, consistent with theory. We show these results are robust to the underlying dynamics of contemporary political discussion and context, including leading explanations for party leadership power, such as national polarization.

A rise in the number of moral individuals in a group can hurt the morality of the group’s collective action. In this paper, we characterize strategic environments and models of morality where this is true solely because, after all, individual morals are private information.

Theoretical expectations regarding communication patterns between legislators and outside agents, such as lobbyists, agency officials, or policy experts, often depend on the relationship between legislators’ and agents’ preferences. However, legislators and nonelected outside agents evaluate the merits of policies using distinct criteria and considerations. We develop a measurement method that flexibly estimates the policy preferences for a class of outside agents—witnesses in committee hearings—separate from that of legislators’ and compute their preference distance across the two dimensions. In our application to Medicare hearings, we find that legislators in the U.S. Congress heavily condition their questioning of witnesses on preference distance, showing that legislators tend to seek policy information from like-minded experts in committee hearings. We do not find this result using a conventional measurement placing both actors on one dimension. The contrast in results lends support for the construct validity of our proposed preference measures.

It is a high honor to be invited to give this first Brindley Memorial Lecture. I view it as taking the first step on a ladder, to be followed by suceeeding talks that climb higher to the pinnacle that George Brindley erected for us in clay mineralogy. If George were with us, he would be sitting on the front row, as usual, keeping the speakers and audience "honest" in our deliberations. In turn, I would be privileged to ask him personally to enlighten us with his valued opinion on the many questions I will be asking in this talk.