Inference on Filtered and Smoothed Probabilities in Markov-Switching Autoregressive Models

ABSTRACT

We derive a statistical theory that provides useful asymptotic approximations to the distributions of the single inferences of filtered and smoothed probabilities, derived from time series characterized by Markov-switching dynamics. We show that the uncertainty in these probabilities diminishes when the states are separated, the variance of the shocks is low, and the time series or the regimes are persistent. As empirical illustrations of our approach, we analyze the U.S. GDP growth rates and the U.S. real interest rates. For both models, we illustrate the usefulness of the confidence intervals when identifying the business cycle phases and the interest rate regimes.     

Estimations of parental and self intelligence as a function of parents’ status: A cross-cultural study in Germany and Spain

With reference to the extensively reported gender differences in estimated intelligence, we used a cross-cultural study to investigate whether employment status and education of mothers and fathers (at the time of data collection, in early childhood, and in later childhood) influenced the estimation of parents’ general intelligence. Data showed that mothers’ as well as fathers’ general intelligence was significantly predicted by their education and current employment status. We additionally found a similar relationship between women’s (men’s) and mothers’ (fathers’) intelligence compared with the relationship of intelligence ascribed to their fathers (mothers). Furthermore, women’s self-estimated intelligence was significantly predicted by their mothers’ current employment, whereas men’s self-estimated intelligence was predicted by their fathers’ education. We furthermore investigated how women’s and men’s estimations differ between Germany and Spain. Results indicate that the more pronounced gender segregation in Spain was not expressed in larger gender differences in self- or parents’ intelligence estimations.     

Visitations and Transfers After Divorce

Recent research reveals that divorce negatively impacts children's welfare as a consequence of the reduction in monetary and time contributions of the non-custodial parent. After divorce, the variables that link the absent parent to the child are visitations, child support transfers, and direct expenditures the non-custodial parent makes on the child. In our framework parents constitute a bilateral exchange economy where the mother is endowed with control over visitations and the father has control over financial resources. We use data from National Longitudinal Study of the High School Class of 1972 (5th follow up) to estimate the parameters of the model. We then use the estimates to simulate the effects of alternative endowment levels (such as joint custody) on the proportion of time spent with the non-custodial parent and the ex post parental income distribution. The results indicate that an endowment of equal time for both parents, reducing time under the mother's control implies a reduction in the child support transfers from the father, and, therefore, a loss in the mother's consumption levels. However, a more equally shared time with the children also increases the father's direct expenditures on the child, with the effect of allowing the mother to spend less on child goods and partially compensate her consumption loss.     

Effects of Multiple Exemplar Training on the Emergence of Derived Relations in Preschool Children Learning a Second Language

We evaluated the facilitative effects of multiple exemplar training (MET) on the establishment of derived tact relations in typically developing children. A multiple-probe design across stimulus sets was implemented to introduce MET. Participants were first taught to conditionally relate dictated names in English to their corresponding objects (listener behavior; A-B relations), followed by tests for derived tacts (B-A relations). If participants failed these tests, MET was implemented whereby tact relations were explicitly taught with novel stimulus sets, followed by test probes with the original training set. MET continued with novel stimuli until participants met criterion for the emergence of derived tact relations or after exposure to three MET sets. Results indicated failed tests for tact relations following direct training in listener relations, and marked improvements in derived tact relations following MET across all participants.     

Robust Nonparametric Confidence Intervals for Regression‐Discontinuity Designs

In the regression‐discontinuity (RD) design, units are assigned to treatment based on whether their value of an observed covariate exceeds a known cutoff. In this design, local polynomial estimators are now routinely employed to construct confidence intervals for treatment effects. The performance of these confidence intervals in applications, however, may be seriously hampered by their sensitivity to the specific bandwidth employed. Available bandwidth selectors typically yield a “large” bandwidth, leading to data‐driven confidence intervals that may be biased, with empirical coverage well below their nominal target. We propose new theory‐based, more robust confidence interval estimators for average treatment effects at the cutoff in sharp RD, sharp kink RD, fuzzy RD, and fuzzy kink RD designs. Our proposed confidence intervals are constructed using a bias‐corrected RD estimator together with a novel standard error estimator. For practical implementation, we discuss mean squared error optimal bandwidths, which are by construction not valid for conventional confidence intervals but are valid with our robust approach, and consistent standard error estimators based on our new variance formulas. In a special case of practical interest, our procedure amounts to running a quadratic instead of a linear local regression. More generally, our results give a formal justification to simple inference procedures based on increasing the order of the local polynomial estimator employed. We find in a simulation study that our confidence intervals exhibit close‐to‐correct empirical coverage and good empirical interval length on average, remarkably improving upon the alternatives available in the literature. All results are readily available in R and STATA using our companion software packages described in Calonico, Cattaneo, and Titiunik (2014d, 2014b).     

Simple But Powerful Health Messages for Increasing Condom Use in Young Adults

In a large longitudinal study involving young adults, we conducted an eight-hour STD educational intervention and examined the impact of the intervention on the efficacy of a message for promoting condom use. The message was framed in positive or negative terms and was presented visually or in numbers (percentages or frequencies). Results indicated that the numerical positive-framed message increased condom use among young adults who did not receive the intervention, whereas the numerical negative-framed message did not. Attitudes toward condom use along with changes in intentions to use condoms mediated this framing effect. In contrast, the positive-framed and negative-framed messages were equally and highly effective for promoting condom use when the messages were presented visually or when young adults received the STD educational intervention before reading the message, suggesting that the simple brochures featuring visual aids were as effective in changing attitudes and behavioral intentions as the extensive intervention. These findings add to a growing body of evidence detailing the mechanisms that allow well-constructed visual aids to be among the most effective, transparent, memorable, and ethically desirable means of risk communication. Clinical and public health implications are discussed.     

Why Are Some Subsidiaries of Multinationals the Source of Novel Practices while Others Are Not? National,Corporate and Functional Influences

It has frequently been argued that multinational companies are moving towards network forms whereby subsidiaries share different practices with the rest of the company. This paper presents large‐scale empirical evidence concerning the extent to which subsidiaries input novel practices into the rest of the multinational. We investigate this in the field of human resources through analysis of a unique international data set in four host countries – Canada, Ireland, Spain and the UK – and address the question of how we can explain variation between subsidiaries in terms of whether they initiate the diffusion of practices to other subsidiaries. The data support the argument that multiple, rather than single, factor explanations are required to more effectively understand the factors promoting or retarding the diffusion of human resource practices within multinational companies. It emerges that national, corporate and functional contexts all matter. More specifically, actors at subsidiary level who seek to initiate diffusion appear to be differentially placed according to their national context, their place within corporate structures and the extent to which the human resource function is internationally networked.     

Correlates of Depressive Symptom Severity in Problem and Pathological Gamblers in Couple Relationships

Problem and pathological gamblers (PPG) often suffer from depressive symptoms. Gambling problems have negative consequences on multiple aspects of gamblers’ lives, including family and marital relationships. The objectives of the current study were to (1) replicate the results of studies that have suggested a stronger and more significant relationship between gambling and depression in PPG than in non-problem gamblers (NPG) and (2) explore specific correlates of depressive symptom severity in PPG in couple relationships. Variables demonstrated to be significantly correlated with depressive symptoms in the general population were selected. It was hypothesized that gender, age, gambler’s mean annual income, perceived poverty, employment status, clinical status (i.e., problem or pathological gambler versus non-problem gambler), trait anxiety, alcoholism, problem-solving skills, and dyadic adjustment would be significant predictors of depressive symptoms. Sixty-seven PPG were recruited, primarily from an addiction treatment center; 40 NPG were recruited, primarily through the media. Results revealed that PPG reported significantly greater depressive symptoms than did NPG. Further, elevated trait anxiety and poor dyadic adjustment were demonstrated to be significant and specific correlates of depressive symptom severity in PPG. These findings contribute to the literature on depressive symptomatology in PPG in relationships, and highlight the importance of the influence of the couple relationship on PPG.     

Are Migrants Going Up a Blind Alley? Economic Migration and Life Satisfaction around the World: Cross-National Evidence from Europe, North America and Australia

Are migrants satisfied with their decision to move to another country? Research shows that the income-wellbeing relationship is weak in wealthy countries, usually countries of destination. Are then economic migrants mistaken? Employing data from the Gallup World Poll, a representative sample of the world population, we investigate whether a general pattern of association exists between income and the cognitive component of subjective wellbeing, and whether this pattern differs by immigration status in 16 high-income countries. In only a handful of countries do we find a distinctive immigrant advantage in translating income into higher life evaluation or life satisfaction: Australia, Belgium, the Netherlands, Portugal and Sweden. For immigrants in most of these countries, income increases cognitive wellbeing even in the fifth income quintile. Depending on the measure used, immigrants in Canada, Denmark, Finland, Italy and the US only have positive income-wellbeing associations at or below the third quintile. We take this as evidence that, among recent arrivals, income is positively associated with wellbeing up to the point in which non-pecuniary factors associated with long-term residence become dominant. We also find a number of “frustrated achievers” among the foreign born in the US, France and Finland. These immigrants report a negative association, in absolute value, between income and life satisfaction or life evaluation.     

Measuring feelings about choices and risks: The Berlin Emotional Responses to Risk Instrument (BERRI)

We introduce a brief instrument specifically validated for measuring positive and negative feelings about risks—the Berlin Emotional Responses to Risk Instrument (BERRI). Based on seven studies involving diverse adults from three countries (n = 2120), the BERRI was found to robustly estimate anticipatory affective reactions derived from subjective evaluations of positive (i.e., assured, hopeful, and relieved) and negative emotions (i.e., anxious, afraid, and worried). The brief BERRI outperformed a 14-item assessment, uniquely tracking costs/benefits associated with cancer screening among men and women (Studies 1 and 2). Predictive validity was further documented in paradigmatic risky choice studies wherein options varied over probabilities and severities across six contexts (health, social, financial, technological, ethical, and environmental; Study 3). Studies 4–6, conducted during the Ebola epidemic and COVID-19 pandemic, indicated BERRI responses were sensitive to subtle effects caused by emotion-related framing manipulations presented in different cultures and languages (the United States, Spain, and Poland). Study 7 indicated BERRI responses remained stable for 2 weeks. Although the BERRI can provide an estimate of overall affect, choices were generally better explained by the unique influences of positive and negative affect. Overall, results suggest the novel, brief instrument can be an efficient tool for high-stakes research on decision making and risk communication.