This article proposes a genetic algorithm, the array histogram-based sampling algorithm (AHBSA), to assemble linear multidimensional forced-choice questionnaires (MFCQs), which are increasingly popular for measuring personality, with forced-choice items including any number of statements (block size). The algorithm also works for traditional multidimensional Likert and cognitive test forms, where items can be seen as having a block size of one. Real and simulated statement pools are used to evaluate AHBSA's performance in terms of test reliability and running speed in assembling Likert forms and MFCQs with two (pair) and three (triplet) statements. Compared to mixed integer programming (MIP) and random assembly, AHBSA achieves as high or higher reliabilities under all conditions: in Likert forms, AHBSA reaches optimal solutions as MIP does, and in the MFCQs, AHBSA gains notable increases in reliabilities over MIP when the forms have no constraint on item direction (i.e., positively versus negatively keyed statements). AHBSA takes more time to converge than MIP. The findings and limitations are discussed, and suggestions for future work are provided.

Using rich data on Chinese schoolchildren, we study the relationships of IQ and personality traits with children's risk preferences and how they affect the precision with which those preferences are measured.Our structural model separates preferences from deliberation noise and guessing, and relates guessing to deliberation noise.Psychological measures have weak direct influences on preferences but strongly affect deliberation noise and guessing behavior.Shocks to choice have persistent individual-specific components and are not independent.Socioeconomic background has little direct influence on preferences or deliberation noise once traits are accounted for.Background variables affect psychological traits, however.Risk preferences differ across and within genders.For small gambles, girls are less risk averse than boys, but the opposite holds for larger gambles.

A growing body of empirical research has developed measures of economic preferences related to risk taking and intertemporal choice. This research has documented pronounced heterogeneity in preferences across and within societies, and also provided evidence that these differences are culturally transmitted. This chapter discusses existing data sets that allow for a comparable measurement across the globe, takes stock of commonalities and differences in approaches, and presents an extended synthetic cross-country data set that combines information from existing data sets. The analysis then establishes various empirical regularities, such as broadly similar patterns of heterogeneity across the globe, revealed by the different datasets, but also some systematic divergences by measurement approach, and substantial correlations of economic preferences with country-aggregate and individual-level outcomes and traits. We also briefly discuss international data sets measuring social preferences, and end with an outlook on avenues for future research.

Personality traits, preferences, and attitudes significantly influence labor market outcomes, and these non-cognitive skills are shaped by the social environment. While curriculum interventions can impact these skills, the effect of compulsory education on non-cognitive skills is less well understood. This study investigates the impact of extending compulsory education by examining educational reforms in four low- and middle-income countries. Utilizing cross-sectional data from the World Bank's 2012/2013 initiative, we analyze the within-country variation in compulsory education years. Our findings indicate that increased compulsory education decreases emotional stability, grit, hostile attribution bias, patience, and willingness to take risks, while enhancing openness to experience and alternative solution or consequential thinking.

Users of forced-choice questionnaires (FCQs) to measure personality commonly assume statement parameter invariance across contexts – between Likert and forced-choice (FC) items and between different FC items that share a common statement. In this paper, an empirical study was designed to check these two assumptions for an FCQ assessment measuring interpersonal and intrapersonal skills. We compared parameters of common statements between two Likert forms and two FCQ forms with a block size of two (statement pairs) and among five FCQ pair forms. In three of the five FCQ forms, statements were paired only with a statement they had appeared with in a triplet block. In the other two FCQ forms, statements were paired with statements they had not been paired with in a triplet block. This design allows us to evaluate statement parameter changes due to changes in context. The results do not support the statement parameter invariance assumption between Likert and FC items or the assumption between FC items when recombining statements form new items. However, the assumption between FC items was generally held for pairs formed by dropping a statement from a triplet item. There were some suggestions for sources of context effects, but the analyses were not definitive. Implications of the findings for test practice are discussed.

We ask if participants in a choice experiment with repeated presentation of the same menus and no feedback provision: (i) exhibit overall behaviour that is consistent with ordinal and expected utility theory under *weak* preferences; (ii) become more consistent with the predictions of these theories under *strict* preferences.To answer these questions we designed and implemented a free-choice lab experiment with 15 distinct menus. Each menu contained two, three and four lotteries with three monetary outcomes, and was shown five times. Subjects could avoid/defer making active choices at a positive expected cost. Among our 308 subjects from the UK and Germany, significantly more were compatible with ordinal and expected utility maximization in their last 15 than in their first 15 identical decision problems. Around a quarter and a fifth of all subjects, moreover, were compatible with those modes *throughout* the experiment, with nearly half of these under weak preferences. Choice consistency is positively correlated with cognitive ability, and subjects who converged to utility-maximizing behaviour were more cognitively able than those who did not. We discuss potential implications of our study's novel set of findings.

As AI systems continue to evolve, their rigorous evaluation becomes crucial for their development and deployment. Researchers have constructed various large-scale benchmarks to determine their capabilities, typically against a gold-standard test set and report metrics averaged across all items. However, this static evaluation paradigm increasingly shows its limitations, including high evaluation costs, data contamination, and the impact of low-quality or erroneous items on evaluation reliability and efficiency. In this Position, drawing from human psychometrics, we discuss a paradigm shift from static evaluation methods to adaptive testing. This involves estimating the characteristics or value of each test item in the benchmark, and tailoring each model's evaluation instead of relying on a fixed test set. This paradigm provides robust ability estimation, uncovering the latent traits underlying a model's observed scores. This position paper analyze the current possibilities, prospects, and reasons for adopting psychometrics in AI evaluation. We argue that psychometrics, a theory originating in the 20th century for human assessment, could be a powerful solution to the challenges in today's AI evaluations.