Response improvement in complex experiments by co-information composite likelihood optimization

We propose an adaptive procedure for improving the response outcomes of complex combinatorial experiments. New experiment batches are chosen by minimizing the co-information composite likelihood (COIL) objective function, which is derived by coupling importance sampling and composite likelihood principles. We show convergence of the best experiment within each batch to the globally optimal experiment in finite time, and carry out simulations to assess the convergence behavior as the design space size increases. The procedure is tested as a new enzyme engineering protocol in an experiment with a design space size of order 10⁷.     

An Algorithm to Simulate VMA Processes Having a Spectrum with Fixed Condition Number

This article proposes an algorithm to generate vector moving average (VMA) processes with a variable spectrum having a fixed condition number across frequencies. This method is based on the theory of multivariate linear spectrum for VMA processes, and is developed in a two-step procedure. Specific examples are provided, and the precision of generated time series is discussed. Such an algorithm is a useful tool to assess the performance of selected multivariate spectral estimators, and it turns out to be particularly appropriated in the Kolmogorov asymptotic estimation framework.     

A note on convergence rates for posterior distributions via large deviations techniques

This paper provides rates of convergence for a class of posterior distributions which are exchangeable with respect to a tree of partitions. The derivations rely on large deviations techniques.     

It is not just escalation: The one dollar game revisited

This paper examines the one-dollar auction game ruling out escalation. The aim of the paper is to understand if players’ expectations about competitors’ moves are strong enough to induce at least one player to bid more than the auctioned euro. Any other bid represents an expected loss for the bidder, so he maximises his own payoff by choosing a bid, which produces a null expected payoff. The empirical results and the analysis based on them support theoretical findings. It is possible that the winner pays more than €1 to get €1 because of his expectations about competitors’ bids and because of his indifference over a certain interval. The results are symptoms of some risk aversion. In an English auction escalation leads to this result, but when escalation is ruled out, expectations and indifference of preferences can lead to the same result.     

Deception in psychology: moral costs and benefits of unsought self-knowledge

Is it ethically permissible to use deception in psychological experiments? We argue that, provided some requirements are satisfied, it is possible to use deceptive methods without producing significant harm to research participants and without any significant violation of their autonomy. We also argue that methodological deception is at least at the moment the only effective means by which one can acquire morally significant information about certain behavioral tendencies. Individuals in general, and research participants in particular, gain self-knowledge which can help them improve their autonomous decision-making. The community gains collective self-knowledge that, once shared, can play a role in shaping education, informing policies and in general creating a more efficient and just society.     

When Catholics turn right: the effects of the Islamic terrorism threat on the fragmented Catholic Italian voters

Italy, as well as most European countries, has been hit by a wave of anxiety arising from groups such as ISIS and Al Qaeda, whose effects on political attitudes are still under-examined. This article investigates the effect of the perceived threat of Islamic terrorism as a potential driver for a ‘right turn’ in the Catholic Italian electorate with open-ended interviews and an Internet-based experiment in which voters were randomly assigned to a terrorism threat manipulation and to a control condition (N?=?138). The results show that the Islamic terroristic threat significantly increased the support for centre-right leaders who promoted in-group identity and out-group hostility towards Muslims. Implications for the debate about the effects of perceived threat on political opinions and the relevance of the findings beyond the Italian case are discussed at the end of the article.     

Langevin incremental mixture importance sampling

This work proposes a novel method through which local information about the target density can be used to construct an efficient importance sampler. The backbone of the proposed method is the incremental mixture importance sampling (IMIS) algorithm of Raftery and Bao (Biometrics 66(4):1162–1173, 2010), which builds a mixture importance distribution incrementally, by positioning new mixture components where the importance density lacks mass, relative to the target. The key innovation proposed here is to construct the mean vectors and covariance matrices of the mixture components by numerically solving certain differential equations, whose solution depends on the local shape of the target log-density. The new sampler has a number of advantages: (a) it provides an extremely parsimonious parametrization of the mixture importance density, whose configuration effectively depends only on the shape of the target and on a single free parameter representing pseudo-time; (b) it scales well with the dimensionality of the target; (c) it can deal with targets that are not log-concave. The performance of the proposed approach is demonstrated on two synthetic non-Gaussian densities, one being defined on up to eighty dimensions, and on a Bayesian logistic regression model, using the Sonar dataset. The Julia code implementing the importance sampler proposed here can be found at https://github.com/mfasiolo/LIMIS.     

Computational challenges and temporal dependence in Bayesian nonparametric models

Müller et al. (Stat Methods Appl, 2017) provide an excellent review of several classes of Bayesian nonparametric models which have found widespread application in a variety of contexts, successfully highlighting their flexibility in comparison with parametric families. Particular attention in the paper is dedicated to modelling spatial dependence. Here we contribute by concisely discussing general computational challenges which arise with posterior inference with Bayesian nonparametric models and certain aspects of modelling temporal dependence.     

Should we talk of “extinction society”? A socio-cultural reading

In this work, we intend to present a reading of current society as the extinction society. Extinction society here means the characterization, both social and individual, of a highly developed reality, especially in terms of personal freedom, unable to face global collective threats, first of all the climate disaster. This involves the risk, within a few generations, of the extinction of both the type of society that at least in the West we have been accustomed to for a few hundred years, and in the apocalyptic perspective of the species. The attempt to represent this question is addressed here by referring to some recent authors of cultural studies and sociology, to try and understand the principles of this extinction process. Following the analysis of what is in fact a process of individual liberation, that is, of increasingly advanced individualization, we proceed by looking at the macro-themes of consumption, politics and psyche. This is in order to understand the possible outcomes of this process and the overall sense of an extinction of the current society if not of the species.     

The influence of the Milan approach: Five decades of intergenerational change. A conversation with Matteo Selvini

The ‘Milan Approach’ made an enormous contribution to psychotherapy and psychiatry and has been viewed as a bedrock in the family therapy field. Mara Selvini-Palazzoli made a revolutionary shift in the early 1970’s to abandon individual therapy and adopt family therapy to treat anorexia in young women. The goal of the three systemic principles; hypothesising, circularity and neutrality, proposed by the Milan Team is to elicit a useful method to interview families which encourages the production of meaningful information. The Milan group took special care of language. Rather than overly focusing on the label and referring to schizophrenia as a diagnosis, for instance, they used the term ‘families in schizophrenic transaction’. This perspective more realistically explored the origin of problems while looking at ways how to effectively generate change. In the early stages of its development, heavily influenced by the work of the MRI, the team adopted a pragmatic and strategic approach, however the focus gradually shifted towards semantics and the story of the system. While the ‘systemic identity’ was the principal guiding principle, the model was also influenced by social constructionism. This paper is a distillation of a conversation held with Matteo Selvini, son of Mara Selvini Palazzoli. We discussed the four key influential figures who developed the ‘Milan approach’, Selvini Palazzoli, Boscolo, Cecchin and Prata. The focus of the conversation is on Mara and on her influence shaping the approach, its evolution through the years leading to the creation of the Scuola di Psicoterapia Mara Selvini Palazzoli. Matteo also shares his own influence in the evolution of the school through the intervening years. He explains the adapted version of the Milan approach and the amalgam of the original and emerging therapeutic concepts. His key messages to therapists are the importance of working in teams and client follow-ups.