Essays in partial identification and applications to treatment effects and policy evaluation.

Dans cette thèse, je me suis interessé à l’identification partielle des effets de traitements dans différents modèles de choix discrets avec traitements endogènes. Les modèles d’effets de traitement ont pour but de mesurer l’impact de certaines interventions sur certaines variables d’intérêt. Le type de traitement et la variable d’intérêt peuvent être défini de manière générale afin de pouvoir être appliqué à plusieurs différents contextes. Il y a plusieurs exemples de traitement en économie du travail, de la santé, de l’éducation, ou en organisation industrielle telle que les programmes de formation à l’emploi, les techniques médicales, l’investissement en recherche et développement, ou l’appartenance à un syndicat. La décision d’être traité ou pas n’est généralement pas aléatoire mais est basée sur des choix et des préférences individuelles. Dans un tel contexte, mesurer l’effet du traitement devient problématique car il faut tenir compte du biais de sélection. Plusieurs versions paramétriques de ces modèles ont été largement étudiées dans la littérature, cependant dans les modèles à variation discrète, la paramétrisation est une source importante d’identification. Dans un tel contexte, il est donc difficile de savoir si les résultats empiriques obtenus sont guidés par les données ou par la paramétrisation imposée au modèle. Etant donné, que les formes paramétriques proposées pour ces types de modèles n’ont généralement pas de fondement économique, je propose dans cette thèse de regarder la version nonparamétrique de ces modèles. Ceci permettra donc de proposer des politiques économiques plus robustes. La principale difficulté dans l’identification nonparamétrique de fonctions structurelles, est le fait que la structure suggérée ne permet pas d’identifier un unique processus générateur des données et ceci peut être du soit à la présence d’équilibres multiples ou soit à des contraintes sur les observables. Dans de telles situations, les méthodes d’identifications traditionnelles deviennent inapplicable d’où le récent développement de la littérature sur l’identification dans les modèles incomplets. Cette littérature porte une attention particuliere à l’identification de l’ensemble des fonctions structurelles d’intérêt qui sont compatibles avec la vraie distribution des données, cet ensemble est appelé : l’ensemble identifié. Par conséquent, dans le premier chapitre de la thèse, je caractérise l’ensemble identifié pour les effets de traitements dans le modèle triangulaire binaire. Dans le second chapitre, je considère le modèle de Roy discret. Je caractérise l’ensemble identifié pour les effets de traitements dans un modèle de choix de secteur lorsque la variable d’intérêt est discrète. Les hypothèses de sélection du secteur comprennent le choix de sélection simple, étendu et généralisé de Roy. Dans le dernier chapitre, je considère un modèle à variable dépendante binaire avec plusieurs dimensions d’hétérogéneité, tels que les jeux d’entrées ou de participation. je caractérise l’ensemble identifié pour les fonctions de profits des firmes dans un jeux avec deux firmes et à information complète. Dans tout les chapitres, l’ensemble identifié des fonctions d’intérêt sont écrites sous formes de bornes et assez simple pour être estimées à partir des méthodes d’inférence existantes.

Numerical Response of Breeding Birds Following Experimental Selection Harvesting in Northern Hardwood Forests

Silvicultural treatments have been shown to alter the composition of species assemblages in numerous taxa. However, the intensity and persistence of these effects have rarely been documented. We used a before-after, control-impact (BACI) paired design, i.e., five pairs of 25-ha study plots, 1-control and 1-treated plot, to quantify changes in the density of eight forest bird species in response to selection harvesting over six breeding seasons, one year pre- and five years postharvest. Focal species included mature forest associates, i.e., Northern Parula (Setophaga americana) and Black-throated Green Warbler (Setophaga virens), forest generalists, i.e., Yellow-bellied Sapsucker (Sphyrapicus varius) and Swainson’s Thrush (Catharus ustulatus), early-seral specialists, i.e., Mourning Warbler (Geothlypis philadelphia) and Chestnut-sided Warbler (Setophaga pensylvanica), species associated with shrubby forest gaps, i.e., Black-throated Blue Warbler (Setophaga caerulescens), and mid-seral species, i.e., American Redstart (Setophaga ruticilla). As predicted, we found a negative numerical response to the treatment in the Black-throated Green Warbler, no treatment effect in the Yellow-bellied Sapsucker, and a positive treatment effect in early-seral specialists. We only detected a year effect in the Northern Parula and the American Redstart. There was evidence for a positive treatment effect on the Swainson’s Thrush when the regeneration started to reach the pole stage, i.e., fifth year postharvest. These findings suggest that selection harvesting has the potential to maintain diverse avian assemblages while allowing sustainable management of timber supply, but future studies should determine whether mature-forest associates can sustain second- and third-entry selection harvest treatments.

A comparison of three different models for estimating relative risk in meta-analysis of clinical trials under unobserved heterogeneity

We focus on the comparison of three statistical models used to estimate the treatment effect in metaanalysis when individually pooled data are available. The models are two conventional models, namely a multi-level and a model based upon an approximate likelihood, and a newly developed model, the profile likelihood model which might be viewed as an extension of the Mantel-Haenszel approach. To exemplify these methods, we use results from a meta-analysis of 22 trials to prevent respiratory tract infections. We show that by using the multi-level approach, in the case of baseline heterogeneity, the number of clusters or components is considerably over-estimated. The approximate and profile likelihood method showed nearly the same pattern for the treatment effect distribution. To provide more evidence two simulation studies are accomplished. The profile likelihood can be considered as a clear alternative to the approximate likelihood model. In the case of strong baseline heterogeneity, the profile likelihood method shows superior behaviour when compared with the multi-level model. Copyright (C) 2006 John Wiley & Sons, Ltd.

The effect of the GENTLE/s robot-mediated therapy system on arm function after stroke

Objective: To evaluate the effect of robot-mediated therapy on arm dysfunction post stroke. Design: A series of single-case studies using a randomized multiple baseline design with ABC or ACB order. Subjects (n = 20) had a baseline length of 8, 9 or 10 data points. They continued measurement during the B - robot-mediated therapy and C - sling suspension phases. Setting: Physiotherapy department, teaching hospital. Subjects: Twenty subjects with varying degrees of motor and sensory deficit completed the study. Subjects attended three times a week, with each phase lasting three weeks. Interventions: In the robot-mediated therapy phase they practised three functional exercises with haptic and visual feedback from the system. In the sling suspension phase they practised three single-plane exercises. Each treatment phase was three weeks long. Main measures: The range of active shoulder flexion, the Fugl-Meyer motor assessment and the Motor Assessment Scale were measured at each visit. Results: Each subject had a varied response to the measurement and intervention phases. The rate of recovery was greater during the robot-mediated therapy phase than in the baseline phase for the majority of subjects. The rate of recovery during the robot-mediated therapy phase was also greater than that during the sling suspension phase for most subjects. Conclusion: The positive treatment effect for both groups suggests that robot-mediated therapy can have a treatment effect greater than the same duration of non-functional exercises. Further studies investigating the optimal duration of treatment in the form of a randomized controlled trial are warranted.

Partially identified treatment effects under imperfect compliance: the case of domestic violence

The Minneapolis Domestic Violence Experiment (MDVE) is a randomized social experiment with imperfect compliance which has been extremely influential in how police officers respond to misdemeanor domestic violence. This paper re-examines data from the MDVE, using recent literature on partial identification to find recidivism associated with a policy that arrests misdemeanor domestic violence suspects rather than not arresting them. Using partially identified bounds on the average treatment effect I find that arresting rather than not arresting suspects can potentially reduce recidivism by more than two-and-a-half times the corresponding intent-to-treat estimate and more than two times the corresponding local average treatment effect, even when making minimal assumptions on counterfactuals.

Likelihood estimate of treatment effects under selection bias

We consider methods for estimating causal effects of treatment in the situation where the individuals in the treatment and the control group are self selected, i.e., the selection mechanism is not randomized. In this case, simple comparison of treated and control outcomes will not generally yield valid estimates of casual effects. The propensity score method is frequently used for the evaluation of treatment effect. However, this method is based onsome strong assumptions, which are not directly testable. In this paper, we present an alternative modeling approachto draw causal inference by using share random-effect model and the computational algorithm to draw likelihood based inference with such a model. With small numerical studies and a real data analysis, we show that our approach gives not only more efficient estimates but it is also less sensitive to model misspecifications, which we consider, than the existing methods.

Effect of type and severity of intimate partner violence on women's health and service use : findings from a primary care trial of women afraid of their partners

Intimate partner violence (IPV) has major affects on women’s wellbeing. There has been limited investigation of the association between type and severity of IPV and health outcomes. This article describes socio-demographic characteristics, experiences of abuse, health, safety, and use of services in women enrolled in the Women’s Evaluation of Abuse and Violence Care (WEAVE) project. We explored associations between type and severity of abuse and women’s health, quality of life, and help seeking. Women (aged 16–50 years) attending 52 Australian general practices, reporting fear of partners in last 12 months were mailed a survey between June 2008 and May 2010. Response rate was 70.5% (272/386). In the last 12 months, one third (33.0%) experienced Severe Combined Abuse, 26.2% Physical and Emotional Abuse, 26.6% Emotional Abuse and/or Harassment only, 2.7% Physical Abuse only and 12.4% scored negative on the Composite Abuse Scale. A total of 31.6% of participants reported poor or fair health and 67.9% poor social support. In the last year, one third had seen a psychologist (36.6%) or had 5 or more general practitioner visits (34.3%); 14.7% contacted IPV services; and 24.4% had made a safety plan. Compared to other abuse groups, women with Severe Combined Abuse had poor quality of life and mental health, despite using more medications, counseling, and IPV services and were more likely to have days out of role because of emotional issues. In summary, women who were fearful of partners in the last year, have poor mental health and quality of life, attend health care services frequently, and domestic violence services infrequently. Those women experiencing severe combined physical, emotional, and sexual abuse have poorer quality of life and mental health than women experiencing other abuse types. Health practitioners should take a history of type and severity of abuse for women with mental health issues to assist access to appropriate specialist support.

Bounds on functionals of the distribution treatment effects

Bounds on the distribution function of the sum of two random variables with known marginal distributions obtained by Makarov (1981) can be used to bound the cumulative distribution function (c.d.f.) of individual treatment effects. Identification of the distribution of individual treatment effects is important for policy purposes if we are interested in functionals of that distribution, such as the proportion of individuals who gain from the treatment and the expected gain from the treatment for these individuals. Makarov bounds on the c.d.f. of the individual treatment effect distribution are pointwise sharp, i.e. they cannot be improved in any single point of the distribution. We show that the Makarov bounds are not uniformly sharp. Specifically, we show that the Makarov bounds on the region that contains the c.d.f. of the treatment effect distribution in two (or more) points can be improved, and we derive the smallest set for the c.d.f. of the treatment effect distribution in two (or more) points. An implication is that the Makarov bounds on a functional of the c.d.f. of the individual treatment effect distribution are not best possible.

Effect of intravaginal electrical stimulation on pelvic floor muscle strength

The aim of this study was to evaluate the effect of intravaginal electrical stimulation (IES) on pelvic floor muscle (PFM) strength in patients with mixed urinary incontinence (MUI). Between January 2001 and February 2002, 40 MUI women (mean age: 48 years) were studied. Urge incontinence was the predominant symptom; 92.5% also presented mild stress urinary incontinence (SUI). Selection criteria were clinical history and urodynamics. Pre-treatment urodynamic study showed no statistical differences between the groups. Ten percent of the women in each group had involuntary detrusor contractions. Patients were randomly distributed, in a double-blind study, into two groups. Group G 1 (n=20), effective IES, and group G2 (n=20), sham IES, with follow-up at 1 month. The following parameters were studied: (1) clinical questionnaire, (2) examiner's evaluation of perineal muscle strength, (3) objective evaluation of perineal muscle by perineometry, (4) vaginal weight test, and (5) urodynamic study. The IES protocol consisted of three 20-min sessions per week over a 7-week period using a Dualpex Uro 996 at 4 Hz. There was no statistically significant difference in the demographic data of both groups. The number of micturitions per 24 h after treatment was reduced significantly in both groups. Urge incontinence, present in all patients before treatment, was reduced to 15% in G1 and 31.5% in G2 post-treatment. The subjective evaluation of PFM strength demonstrated a significant improvement in G1. Objective evaluation of PFM force by perineometer showed a significant improvement in maximum peak contraction post-treatment in both groups. In the vaginal weight test, there was a significant increase in average number of cone retentions post-treatment in both groups. With regard to satisfaction level, after treatment, 80% of the patients in G1 and 65% of the patients in G2 were satisfied. There was no statistically significant difference between the groups. There was a significant improvement in PFM strength from both effective and sham electrostimulation, questioning the effectiveness of electrostimulation as a monotherapy in treating MUI.

Effect of TiO2 surface modification in Rhodamine B photodegradation

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Effect of thermal cycling on denture base and autopolymerizing reline resins

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Class II malocclusion treatment using high-pull headgear with a splint: a systematic review

Objective: To systematically review the scientific evidence pertaining to the effectiveness of high-pull headgear in growing Class II subjects. Methods: A literature survey was performed by electronic database search. The survey covered the period from January 1966 to December 2008 and used Medical Subject Headings (MeSH). Articles were initially selected based on their titles and abstracts; the full articles were then retrieved. The inclusion criteria included growing subjects between 8 to 15 years of age, Class II malocclusion treatment with high-pull headgear, and a control group with Class II malocclusion. References from selected articles were hand-searched for additional publications. Selected studies were evaluated methodologically. Results: Four articles were selected; none were randomized controlled trials. All of the articles clearly formulated their objectives and used appropriate measures. The studies showed that high-pull headgear treatment improves skeletal and dental relationship, distal displacement of the maxilla, vertical eruption control and upper molars distalization. One of the studies showed a slight clockwise rotation of the palatal plane; the others showed no significant treatment effect. The mandible was not affected by the treatment. Conclusion: While there is still a lack of strong evidence demonstrating the effects of high-pull headgear with a splint, other studies indicate that the AP relations improve due to distalization of the maxilla and upper molars, with little or no treatment effects in the mandible. Greater attention to the design should be given to improve the quality of such trials. © 2013 Dental Press Journal of Orthodontics.

Determinação da melhor dose de virginiamicina em suplementos para bovinos Nelore em pastejo

Pós-graduação em Zootecnia - FCAV

Tifton 419 Bermudagrass (Cynodon dactylon C. transvaaliensis) response to plant grow inhibitors

Tifton 419' bermudagrass cultivar [Cynodon dactylon (L.) Pers. x C. transvaalensis Burtt-Davy] is the most preferred turfgrass for sportive, commercial and residential lawns. On similar species, such as Stenotaphrum secundatum and Zoysia japonica, gibberellic acid-inhibiting plant growth regulators (PGRs) are used to decrease mowing frequency. A very limited research has been reported yet on the PGRs regarding seasonal effects of single vs. multiple applications of these products on turfgrass quality and clipping production on South America. This study aimed to evaluate the effect of sequential applications of different plant growth inhibitors during re-growth and flower rachis emission of 'Tifton 419' Bermudagrass. The treatment pattern includes an initial application followed by one sequential application at 14 days intervals, according to the following: prohexadione-calcium at 100+100 or 200+200 g a.i. ha-1, bispyribac-sodium at 40+40 or 60+60 g a.i. ha-1, trinexapac-ethyl at 113+113, 226+113, 226+226, 452+113, 452+226, 452+452, 678+0 or 904+0 g a.i. ha-1, and untreated control. The treatment effect was evaluated based on measurements of visual injury, height of plants, height and number of flower rachis, and clipping total dry mass production. The results showed that only bispyribac-sodium provided visual injury on 'Tifton 419' Bermudagrass, but the symptoms quickly tend towards zero at 21 days after second application (DASA). 'Tifton 419' Bermudagrass greens could be better handle by sequential application of trinexapac-ethyl, or prohexadione-calcium or bispyribac-sodium, once the height of plants, seedhead emission and total clipping dry mass reduction were over than 37%, 91% and 88%, respectively, for a period up to 60 DASA.

Methods to convert continuous outcomes into odds ratios of treatment response and numbers needed to treat: meta-epidemiological study

Clinicians find standardized mean differences (SMDs) calculated from continuous outcomes difficult to interpret. Our objective was to determine the performance of methods in converting SMDs or means to odds ratios of treatment response and numbers needed to treat (NNTs) as more intuitive measures of treatment effect.