A partial dependence factorial analysis to deal with selection bias in observational studis

This thesis presents a creative and practical approach to dealing with the problem of selection bias. Selection bias may be the most important vexing problem in program evaluation or in any line of research that attempts to assert causality. Some of the greatest minds in economics and statistics have scrutinized the problem of selection bias, with the resulting approaches – Rubin’s Potential Outcome Approach(Rosenbaum and Rubin,1983; Rubin, 1991,2001,2004) or Heckman’s Selection model (Heckman, 1979) – being widely accepted and used as the best fixes. These solutions to the bias that arises in particular from self selection are imperfect, and many researchers, when feasible, reserve their strongest causal inference for data from experimental rather than observational studies. The innovative aspect of this thesis is to propose a data transformation that allows measuring and testing in an automatic and multivariate way the presence of selection bias. The approach involves the construction of a multi-dimensional conditional space of the X matrix in which the bias associated with the treatment assignment has been eliminated. Specifically, we propose the use of a partial dependence analysis of the X-space as a tool for investigating the dependence relationship between a set of observable pre-treatment categorical covariates X and a treatment indicator variable T, in order to obtain a measure of bias according to their dependence structure. The measure of selection bias is then expressed in terms of inertia due to the dependence between X and T that has been eliminated. Given the measure of selection bias, we propose a multivariate test of imbalance in order to check if the detected bias is significant, by using the asymptotical distribution of inertia due to T (Estadella et al. 2005) , and by preserving the multivariate nature of data. Further, we propose the use of a clustering procedure as a tool to find groups of comparable units on which estimate local causal effects, and the use of the multivariate test of imbalance as a stopping rule in choosing the best cluster solution set. The method is non parametric, it does not call for modeling the data, based on some underlying theory or assumption about the selection process, but instead it calls for using the existing variability within the data and letting the data to speak. The idea of proposing this multivariate approach to measure selection bias and test balance comes from the consideration that in applied research all aspects of multivariate balance, not represented in the univariate variable- by-variable summaries, are ignored. The first part contains an introduction to evaluation methods as part of public and private decision process and a review of the literature of evaluation methods. The attention is focused on Rubin Potential Outcome Approach, matching methods, and briefly on Heckman’s Selection Model. The second part focuses on some resulting limitations of conventional methods, with particular attention to the problem of how testing in the correct way balancing. The third part contains the original contribution proposed , a simulation study that allows to check the performance of the method for a given dependence setting and an application to a real data set. Finally, we discuss, conclude and explain our future perspectives.

Identified primary hadron spectra with the TOF detector of the ALICE experiment at LHC

In this thesis the analysis to reconstruct the transverse momentum p_{t} spectra for pions, kaons and protons identified with the TOF detector of the ALICE experiment in pp Minimum Bias collisions at $\sqrt{s}=7$ TeV was reported. After a detailed description of all the parameters which influence the TOF PID performance (time resolution, calibration, alignment, matching efficiency, time-zero of the event) the method used to identify the particles, the unfolding procedure, was discussed. With this method, thanks also to the excellent TOF performance, the pion and kaon spectra can be reconstructed in the 0.5

Local home bias: Theory and new empirical evidence from Italy

This thesis examines the literature on local home bias, i.e. investor preference towards geographically nearby stocks, and investigates the role of firm’s visibility, profitability, and opacity in explaining such behavior. While firm’s visibility is expected to proxy for the behavioral root originating such a preference, firm’s profitability and opacity are expected to capture the informational one. I find that less visible, and more profitable and opaque firms, conditionally to the demand, benefit from being headquartered in regions characterized by a scarcity of listed firms (local supply of stocks). Specifically, research estimates suggest that firms headquartered in regions with a poor supply of stocks would be worth i) 11 percent more if non-visible, non-profitable and non-opaque; ii) 16 percent more if profitable; and iii) 28 percent more if both profitable and opaque. Overall, as these features are able to explain most, albeit not all, of the local home bias effect, I reasonably argue and then assess that most of the preference for local is determined by a successful attempt to exploit local information advantage (60 percent), while the rest is determined by a mere (irrational) feeling of familiarity with the local firm (40 percent). Several and significant methodological, theoretical, and practical implications come out.

Narratori degli anni zero. Storia, critica, poetiche

Il lavoro si propone come un’indagine sulla letteratura italiana del primo decennio del XXI secolo, in una prospettiva non di semplice ricognizione ma di individuazione di linee interpretative capaci di ripercorrere un archivio di materiali molto vasto e non ancora chiuso. La prima parte affronta questioni relative a condizioni produttive, ricezione e valutazione critica della letteratura contemporanea. Il primo capitolo è dedicato alla discussione di problemi relativi allo studio della narrativa italiana del XXI secolo a partire dalla definizione utilizzata per riferirsi ad essa, quella di “anni zero”. Il secondo capitolo situa la narrativa contemporanea nelle linee di sviluppo della letteratura italiana degli ultimi trent’anni, a partire da un mutamento del rapporto dello scrittore con la tradizione umanistica che risale all’inizio degli anni ottanta. Il terzo capitolo approfondisce uno dei generi maggiormente praticati: il romanzo storico. Considerato negli anni ottanta e novanta un genere d'evasione e intrattenimento, negli anni zero è divenuto veicolo di punti di vista critici nei confronti delle narrazioni dominanti. La seconda parte è dedicata all’approfondimento di romanzi che raccontano, da un’ottica non testimoniale, gli anni settanta italiani, periodo complesso non solo sul piano evenemenziale, ma anche su quello della rielaborazione artistica. I romanzi su cui si concentra l’indagine offrono un racconto degli anni settanta italiani a partire da un’idea di storia plurale, ricostruita attraverso una molteplicità di voci, che muta a seconda della prospettiva da cui viene affrontata. Le storie false dei romanzi sugli anni settanta non chiedono di essere lette come vere, ma dicono comunque qualcosa di vero sulle modalità attraverso le quali si va costruendo il rapporto con il passato recente, nel più ampio contesto dei percorsi della letteratura italiana di inizio millennio, tra spinte che vanno nella direzione del mantenimento dell’autonomia da parte degli autori e pressioni del mercato editoriale.