Objective. Major depressive disorder (MDD) is a common condition following treatment in the Intensive Care Unit (ICU). Long-term data on MDD in chronically critically ill (CCI) patients are scarce. Hence, the primary aim of the present study was to investigate the frequency and predictors of MDD after intensive care of CCI patients. Materials and Methods. In a prospective cohort study, patients with long-term mechanical ventilation requirements () were assessed with respect to a diagnosis of MDD, using the Structured Clinical Interview for DSM-IV, three and six months after the transfer from acute ICU to post-acute ICU. Sociodemographic, psychological, and clinical risk factors with values ≤ 0.1 were identified in a univariate logistic regression analysis and entered in a multivariable logistic regression model. A mediator analysis was run using the bootstrapping method, testing the mediating effect of perceived helplessness during the ICU stay, between the recalled traumatic experience from the ICU and a post-ICU MDD. Results. 17.6% () of the patients showed a full- or subsyndromal MDD. Perceived helplessness, recalled experiences of a traumatic event from the ICU, symptoms of acute stress disorder, and the diagnosis of posttraumatic stress disorder (PTSD) after ICU could be identified as significant predictors of MDD. In a mediator analysis, perceived helplessness could be proved as a mediator. Conclusions. Every fifth CCI patient suffers from MDD up to six months after being discharged from ICU. Particularly, perceived helplessness during the ICU stay seems to mainly affect the long-term evolvement of MDD. CCI patients with symptoms of acute stress disorder/PTSD should also be screened for MDD.

Dans cette étude, j’examine la propension à former une union interethnique parmi les Canadiens arabes de seconde génération et de génération 1.5 en utilisant les données du recensement canadien de 2016. L’analyse descriptive montre que les unions interethniques sont fréquentes au sein de cette population. Environ la moitié des hommes (56%) et des femmes (49%) sont dans une union interethnique avec une personne non-Arabe d’origine immigrante ou un(e) Canadien(ne) de troisième génération ou des générations suivantes. La régression logistique multinomiale révèle que les hommes et les femmes avec un niveau d’éducation plus élevé, une ascendance partiellement arabe et un statut d’immigrant de deuxième génération sont significativement plus enclins à être en union interethnique qu’à être en union intraethnique avec un immigrant de première génération. Conformément à la théorie de l’assimilation segmentée, ces résultats suggèrent que l’intégration socioéconomique et l’acculturation contribuent à la propension des descendants arabes à former des unions avec des individus non-arabes. La propension des descendants arabes à être en union intraethnique avec des immigrants de première génération ou des descendants est aussi une problématique dont je discute. / In this study, I examine the propensity to form interethnic unions among the 1.5 and second generations of Arab Canadians using the 2016 Canadian census data. The descriptive analysis shows that interethnic unions are common within this population. About half the men (56%) and the women (49%) are in an interethnic union with a non-Arab person with an immigrant background or a Canadian of third generation or subsequent generations. The multinomial logistic regression reveals that men and women with higher educational attainment, part Arab ancestry and second-generation immigrant status are significantly more prone to be in an interethnic union than in an intraethnic union with a first-generation immigrant. In accordance with the segmented assimilation theory, these results suggest that socioeconomic integration and acculturation contribute to the propensity of Arab descendants to form unions with non-Arab individuals. The propensity of Arab descendants to be in intraethnic unions with first generation-immigrants or with descendants of immigrants (1.5 and second generations) is also discussed in this thesis.

Indiana University-Purdue University Indianapolis (IUPUI) / Epidemiologic studies suggest that depression is an independent risk factor for cardiovascular disease (CVD). Although several possible mediators of this association have been proposed, few studies have examined the role of moderators. Accordingly, I examined adverse childhood experiences (ACE) as a potential moderator of the depression-CVD association, given that individuals with a history of ACE show a greater inflammatory response to depression, and inflammation plays a role in the development of CVD. Data from Waves 1 and 2 of the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC) were analyzed. Participants were 29,282 adults (58% female, 42% non–white) aged 18–97 years, free of CVD diagnoses at baseline. Lifetime depressive disorder (LDD) was assessed by the Alcohol Use Disorder and Associated Disabilities Interview Schedule–IV (AUDADIS–IV), and adverse childhood experiences (abuse, neglect, and household dysfunction), and CVD were assessed during separate interviews. The primary outcome was incident CVD (n = 1,255), defined as nonfatal arteriosclerosis, angina pectoris, myocardial infarction, and/or stroke reported during the Wave 2 interviews. All analyses were adjusted for demographic and traditional CVD risk factors. Logistic regression models revealed that both LDD (OR = 1.44, 95% CI: 1.28–1.62, p < .001) and any ACE (OR = 1.25, 95% CI: 1.16–1.35, p < .001) were independent predictors of incident CVD. Interactions between LDD x any ACE (p = .024), LDD x neglect (p = .003), and LDD x household dysfunction (p < .001), but not LDD x abuse (p = 0.16), were detected. Analyses stratified by the ACE variables revealed that LDD was a predictor of incident CVD among adults with a history of (1) any ACE (OR = 1.51, 95% CI: 1.32–1.73, p < .001), but not among those without a history (OR = 1.15, 95% CI: 0.87–1.50, p = .332); (2) neglect (OR = 1.59, 95% CI: 1.36–1.87, p < .001) and among those without a history (OR = 1.25, 95% CI: 1.07–1.62, p = .005); (3) household dysfunction (OR = 1.73, 95% CI: 1.46–2.04, p < .001), but not among those without a history (OR = 1.18, 95% CI: 0.96–1.43, p = .11). Overall, the present findings suggest that depression may be a stronger risk factor for CVD among adults with a history of ACE, especially neglect and household dysfunction, than among adults who did not have these experiences.

Les modèles uplift (levier en français) traitent de l'inférence de cause à effet pour un facteur spécifique, comme une intervention de marketing. En pratique, ces modèles sont construits sur des données individuelles issues d'expériences randomisées. Un groupe traitement comprend des individus qui font l'objet d'une action; un groupe témoin sert de comparaison. La modélisation uplift est utilisée pour ordonner les individus par rapport à la valeur d'un effet causal, par exemple, positif, neutre ou négatif. Dans un premier temps, nous proposons une nouvelle façon d'effectuer la sélection de modèles pour la régression uplift. Notre méthodologie est basée sur la maximisation du coefficient Qini. Étant donné que la sélection du modèle correspond à la sélection des variables, la tâche est difficile si elle est effectuée de manière directe lorsque le nombre de variables à prendre en compte est grand. Pour rechercher de manière réaliste un bon modèle, nous avons conçu une méthode de recherche basée sur une exploration efficace de l'espace des coefficients de régression combinée à une pénalisation de type lasso de la log-vraisemblance. Il n'y a pas d'expression analytique explicite pour la surface Qini, donc la dévoiler n'est pas facile. Notre idée est de découvrir progressivement la surface Qini comparable à l'optimisation sans dérivée. Le but est de trouver un maximum local raisonnable du Qini en explorant la surface près des valeurs optimales des coefficients pénalisés. Nous partageons ouvertement nos codes à travers la librairie R tools4uplift. Bien qu'il existe des méthodes de calcul disponibles pour la modélisation uplift, la plupart d'entre elles excluent les modèles de régression statistique. Notre librairie entend combler cette lacune. Cette librairie comprend des outils pour: i) la discrétisation, ii) la visualisation, iii) la sélection de variables, iv) l'estimation des paramètres et v) la validation du modèle. Cette librairie permet aux praticiens d'utiliser nos méthodes avec aise et de se référer aux articles méthodologiques afin de lire les détails. L'uplift est un cas particulier d'inférence causale. L'inférence causale essaie de répondre à des questions telle que « Quel serait le résultat si nous donnions à ce patient un traitement A au lieu du traitement B? ». La réponse à cette question est ensuite utilisée comme prédiction pour un nouveau patient. Dans la deuxième partie de la thèse, c’est sur la prédiction que nous avons davantage insisté. La plupart des approches existantes sont des adaptations de forêts aléatoires pour le cas de l'uplift. Plusieurs critères de segmentation ont été proposés dans la littérature, tous reposant sur la maximisation de l'hétérogénéité. Cependant, dans la pratique, ces approches sont sujettes au sur-ajustement. Nous apportons une nouvelle vision pour améliorer la prédiction de l'uplift. Nous proposons une nouvelle fonction de perte définie en tirant parti d'un lien avec l'interprétation bayésienne du risque relatif. Notre solution est développée pour une architecture de réseau de neurones jumeaux spécifique permettant d'optimiser conjointement les probabilités marginales de succès pour les individus traités et non-traités. Nous montrons que ce modèle est une généralisation du modèle d'interaction logistique de l'uplift. Nous modifions également l'algorithme de descente de gradient stochastique pour permettre des solutions parcimonieuses structurées. Cela aide dans une large mesure à ajuster nos modèles uplift. Nous partageons ouvertement nos codes Python pour les praticiens désireux d'utiliser nos algorithmes. Nous avons eu la rare opportunité de collaborer avec l'industrie afin d'avoir accès à des données provenant de campagnes de marketing à grande échelle favorables à l'application de nos méthodes. Nous montrons empiriquement que nos méthodes sont compétitives avec l'état de l'art sur les données réelles ainsi qu'à travers plusieurs scénarios de simulations. / Uplift models deal with cause-and-effect inference for a specific factor, such as a marketing intervention. In practice, these models are built on individual data from randomized experiments. A targeted group contains individuals who are subject to an action; a control group serves for comparison. Uplift modeling is used to order the individuals with respect to the value of a causal effect, e.g., positive, neutral, or negative. First, we propose a new way to perform model selection in uplift regression models. Our methodology is based on the maximization of the Qini coefficient. Because model selection corresponds to variable selection, the task is haunting and intractable if done in a straightforward manner when the number of variables to consider is large. To realistically search for a good model, we conceived a searching method based on an efficient exploration of the regression coefficients space combined with a lasso penalization of the log-likelihood. There is no explicit analytical expression for the Qini surface, so unveiling it is not easy. Our idea is to gradually uncover the Qini surface in a manner inspired by surface response designs. The goal is to find a reasonable local maximum of the Qini by exploring the surface near optimal values of the penalized coefficients. We openly share our codes through the R Package tools4uplift. Though there are some computational methods available for uplift modeling, most of them exclude statistical regression models. Our package intends to fill this gap. This package comprises tools for: i) quantization, ii) visualization, iii) variable selection, iv) parameters estimation and v) model validation. This library allows practitioners to use our methods with ease and to refer to methodological papers in order to read the details. Uplift is a particular case of causal inference. Causal inference tries to answer questions such as ``What would be the result if we gave this patient treatment A instead of treatment B?" . The answer to this question is then used as a prediction for a new patient. In the second part of the thesis, it is on the prediction that we have placed more emphasis. Most existing approaches are adaptations of random forests for the uplift case. Several split criteria have been proposed in the literature, all relying on maximizing heterogeneity. However, in practice, these approaches are prone to overfitting. In this work, we bring a new vision to uplift modeling. We propose a new loss function defined by leveraging a connection with the Bayesian interpretation of the relative risk. Our solution is developed for a specific twin neural network architecture allowing to jointly optimize the marginal probabilities of success for treated and control individuals. We show that this model is a generalization of the uplift logistic interaction model. We modify the stochastic gradient descent algorithm to allow for structured sparse solutions. This helps fitting our uplift models to a great extent. We openly share our Python codes for practitioners wishing to use our algorithms. We had the rare opportunity to collaborate with industry to get access to data from large-scale marketing campaigns favorable to the application of our methods. We show empirically that our methods are competitive with the state of the art on real data and through several simulation setting scenarios.

In this study I examine voter response at an interview level using a dataset of 7562 voter contacts (including responses and nonresponses) in the 2004 Utah Colleges Exit Poll. In 2004, 4908 of the 7562 voters approached responded to the exit poll for an overall response rate of 65 percent. Logistic regression is used to estimate factors that contribute to a success or failure of each interview attempt. This logistic regression model uses interviewer characteristics, voter characteristics (both respondents and nonrespondents), and exogenous factors as independent variables. Voter characteristics such as race, gender, and age are strongly associated with response. An interviewer's prior retail sales experience is associated with whether a voter will decide to respond to a questionnaire or not. The only exogenous factor that is associated with voter response is whether the interview occurred in the morning or afternoon.

It is essential for a bank to estimate the credit risk it carries and the magnitude of exposure it has in case of non-performing customers. Estimation of this kind of risk has been done by statistical methods through decades and with respect to recent development in the field of machine learning, there has been an interest in investigating if machine learning techniques can perform better quantification of the risk. The aim of this thesis is to examine which method from a chosen set of machine learning techniques exhibits the best performance in default prediction with regards to chosen model evaluation parameters. The investigated techniques were Logistic Regression, Random Forest, Decision Tree, AdaBoost, XGBoost, Artificial Neural Network and Support Vector Machine. An oversampling technique called SMOTE was implemented in order to treat the imbalance between classes for the response variable. The results showed that XGBoost without implementation of SMOTE obtained the best result with respect to the chosen model evaluation metric. / Det är nödvändigt för en bank att ha en bra uppskattning på hur stor risk den bär med avseende på kunders fallissemang. Olika statistiska metoder har använts för att estimera denna risk, men med den nuvarande utvecklingen inom maskininlärningsområdet har det väckt ett intesse att utforska om maskininlärningsmetoder kan förbättra kvaliteten på riskuppskattningen. Syftet med denna avhandling är att undersöka vilken metod av de implementerade maskininlärningsmetoderna presterar bäst för modellering av fallissemangprediktion med avseende på valda modelvaldieringsparametrar. De implementerade metoderna var Logistisk Regression, Random Forest, Decision Tree, AdaBoost, XGBoost, Artificiella neurala nätverk och Stödvektormaskin. En översamplingsteknik, SMOTE, användes för att behandla obalansen i klassfördelningen för svarsvariabeln. Resultatet blev följande: XGBoost utan implementering av SMOTE visade bäst resultat med avseende på den valda metriken.

The desire to model the true gain from targeting an individual in marketing purposes has lead to the common use of uplift modeling. Uplift modeling requires the existence of a treatment group as well as a control group and the objective hence becomes estimating the difference between the success probabilities in the two groups. Efficient methods for estimating the probabilities in uplift models are statistical machine learning methods. In this project the different uplift modeling approaches Subtraction of Two Models, Modeling Uplift Directly and the Class Variable Transformation are investigated. The statistical machine learning methods applied are Random Forests and Neural Networks along with the standard method Logistic Regression. The data is collected from a well established retail company and the purpose of the project is thus to investigate which uplift modeling approach and statistical machine learning method that yields in the best performance given the data used in this project. The variable selection step was shown to be a crucial component in the modeling processes as so was the amount of control data in each data set. For the uplift to be successful, the method of choice should be either the Modeling Uplift Directly using Random Forests, or the Class Variable Transformation using Logistic Regression. Neural network - based approaches are sensitive to uneven class distributions and is hence not able to obtain stable models given the data used in this project. Furthermore, the Subtraction of Two Models did not perform well due to the fact that each model tended to focus too much on modeling the class in both data sets separately instead of modeling the difference between the class probabilities. The conclusion is hence to use an approach that models the uplift directly, and also to use a great amount of control data in each data set. / Behovet av att kunna modellera den verkliga vinsten av riktad marknadsföring har lett till den idag vanligt förekommande metoden inkrementell responsanalys. För att kunna utföra denna typ av metod krävs förekomsten av en existerande testgrupp samt kontrollgrupp och målet är således att beräkna differensen mellan de positiva utfallen i de två grupperna. Sannolikheten för de positiva utfallen för de två grupperna kan effektivt estimeras med statistiska maskininlärningsmetoder. De inkrementella responsanalysmetoderna som undersöks i detta projekt är subtraktion av två modeller, att modellera den inkrementella responsen direkt samt en klassvariabeltransformation. De statistiska maskininlärningsmetoderna som tillämpas är random forests och neurala nätverk samt standardmetoden logistisk regression. Datan är samlad från ett väletablerat detaljhandelsföretag och målet är därmed att undersöka vilken inkrementell responsanalysmetod och maskininlärningsmetod som presterar bäst givet datan i detta projekt. De mest avgörande aspekterna för att få ett bra resultat visade sig vara variabelselektionen och mängden kontrolldata i varje dataset. För att få ett lyckat resultat bör valet av maskininlärningsmetod vara random forests vilken används för att modellera den inkrementella responsen direkt, eller logistisk regression tillsammans med en klassvariabeltransformation. Neurala nätverksmetoder är känsliga för ojämna klassfördelningar och klarar därmed inte av att erhålla stabila modeller med den givna datan. Vidare presterade subtraktion av två modeller dåligt på grund av att var modell tenderade att fokusera för mycket på att modellera klassen i båda dataseten separat, istället för att modellera differensen mellan dem. Slutsatsen är således att en metod som modellerar den inkrementella responsen direkt samt en relativt stor kontrollgrupp är att föredra för att få ett stabilt resultat.

<p dir="ltr">Automaticity, an essential attribute of skill, is developed when a task is executed repeatedly with minimal attention and can have both good (e.g., productivity, skill acquisitions) and bad (e.g., accident involvement) implications on workers’ performance. However, the implications of automaticity in construction are unknown despite their significance. To address this knowledge gap, this research aimed to examine methods that are indicative of the development of automaticity on construction sites and its implications on construction safety and productivity. The objectives of the dissertation include: 1) examining the development of automaticity during the repetitive execution of a primary task of roofing construction and a concurrent secondary task (a computer-generated audio-spatial processing task) to measure attentional resources; 2) using eye-tracking metrics to distinguish between automatic and nonautomatic subjects and determine the significant factors contributing to the odds of automatic behavior; 3) determining which personal characteristics (such as personality traits and mindfulness dimensions) better explain the variability in the attention of workers while developing automaticity. To achieve this objective, 28 subjects were recruited to take part in a longitudinal study involving a total of 22 repetitive sessions of a simulated roofing task. The task involves the installation of 17 pieces of 25 ft2 shingles on a low-sloped roof model that was 8 ft wide, 8 ft long, and 4 ft high for one month in a laboratory. The collected data was analyzed using multiple statistical and data mining techniques such as repeated measures analysis of variance (RM-ANOVA), pairwise comparisons, principal component analysis (PCA), support vector machine (SVM), binary logistic regression (BLR), relative weight analyses (RWA), and advanced bootstrapping techniques to address the research questions. First, the findings showed that as the experiment progressed, there were significant improvements in the mean automatic performance measures such as the mean primary task duration, mean primary task accuracy, and mean secondary task score over the repeated measurements (p-value < 0.05). These findings were used to demonstrate that automaticity develops during repetitive construction activities. This is because these automatic performance measures provide an index for assessing feature-based changes that are synonymous with automaticity development. Second, this study successfully used supervised machine learning methods including SVM to classify subjects (with an accuracy of 76.8%) based on their eye-tracking data into automatic and nonautomatic states. Also, BLR was used to estimate the probability of exhibiting automaticity based on eye-tracking metrics and ascertain the variables significantly contributing to it. Eye-tracking variables collected towards safety harness and anchor, hammer, and work area AOIs were found to be significant predictors (p < 0.05) of the probability of exhibiting automatic behavior. Third, the results revealed that higher levels of agreeableness significantly impact increased levels of change in attention to productivity-related cues during automatic behavior. Additionally, higher levels of nonreactivity to inner experience significantly reduce the changes in attention to safety-related AOIs while developing automaticity. The findings of this study provide metrics to assess training effectiveness. The findings of this study can be used by practitioners to better understand the positive and negative consequences of developing automaticity, measure workers’ performance more accurately, assess training effectiveness, and personalize learning for workers. In long term, the findings of this study will also aid in improving human-AI teaming since the AI will be better able to understand the cognitive state of its human counterpart and can more precisely adapt to him or her.</p>

[pt] Esta dissertação apresenta uma abordagem baseada em dados para o problema de predição de desastres recorrentes em países em desenvolvimento. Métodos de aprendizado de máquina supervisionado são usados para treinar classificadores que visam prever se uma família seria afetada por ameaças climáticas recorrentes (um classificador é treinado para cada perigo natural). A abordagem desenvolvida é válida para perigos naturais recorrentes que afetam um país e permite que os gerentes de risco de desastres direcionem suas operações com mais conhecimento. Além disso, a avaliação preditiva permite que os gerentes entendam os impulsionadores dessas previsões, levando à formulação proativa de políticas e planejamento de operações para mitigar riscos e preparar comunidades para desastres recorrentes. A metodologia proposta foi aplicada ao estudo de caso do Peru, onde foram treinados classificadores para ondas de frio, inundações e deslizamentos de terra. No caso das ondas de frio, o classificador tem 73,82% de precisão. A pesquisa descobriu que famílias pobres em áreas rurais são vulneráveis a desastres relacionados a ondas de frio e precisam de intervenção humanitária proativa. Famílias vulneráveis têm infraestrutura urbana precária, incluindo trilhas, caminhos, postes de iluminação e redes de água e drenagem. O papel do seguro saúde, estado de saúde e educação é menor. Domicílios com membros doentes levam a maiores probabilidades de serem afetados por ondas de frio. Maior realização educacional do chefe da família está associada a uma menor probabilidade de ser afetado por ondas de frio. No caso das inundações, o classificador tem 82.57% de precisão. Certas condições urbanas podem tornar as famílias rurais mais suscetíveis a inundações, como acesso à água potável, postes de iluminação e redes de drenagem. Possuir um computador ou laptop diminui a probabilidade de ser afetado por inundações, enquanto possuir uma bicicleta e ser chefiado por indivíduos casados aumenta. Inundações são mais comuns em assentamentos urbanos menos desenvolvidos do que em famílias rurais isoladas. No caso dos deslizamentos de terra, o classificador tem 88.85% de precisão, e é segue uma lógica diferente do das inundações. A importância na previsão é mais uniformemente distribuída entre as características consideradas no aprendizado do classificador. Assim, o impacto de um recurso individual na previsão é pequeno. A riqueza a longo prazo parece ser mais crítica: a probabilidade de ser afetado por um deslizamento é menor para famílias com certos aparelhos e materiais domésticos de construção. Comunidades rurais são mais afetadas por deslizamentos, especialmente aquelas localizadas em altitudes mais elevadas e maiores distâncias das cidades e mercados. O impacto marginal médio da altitude é não linear. Os classificadores fornecem um método inteligente baseado em dados que economiza recursos garantindo precisão. Além disso, a pesquisa fornece diretrizes para abordar a eficiência na distribuição da ajuda, como formulações de localização da instalação e roteamento de veículos. Os resultados da pesquisa têm várias implicações gerenciais, então os autores convocam à ação gestores de risco de desastres e outros interessados relevantes. Desastres recorrentes desafiam toda a humanidade. / [en] This dissertation presents a data-driven approach to the problem of predicting recurrent disasters in developing countries. Supervised machine learning methods are used to train classifiers that aim to predict whether a household would be affected by recurrent climate threats (one classifier is trained for each natural hazard). The approach developed is valid for recurrent natural hazards affecting a country and allows disaster risk managers to target their operations with more knowledge. In addition, predictive assessment allows managers to understand the drivers of these predictions, leading to proactive policy formulation and operations planning to mitigate risks and prepare communities for recurring disasters. The proposed methodology was applied to the case study of Peru, where classifiers were trained for cold waves, floods, and landslides. In the case of cold waves, the classifier was 73.82% accurate. The research found that low-income families in rural areas are vulnerable to cold wave related disasters and need proactive humanitarian intervention. Vulnerable families have poor urban infrastructure, including footpaths, roads, lampposts, and water and drainage networks. The role of health insurance, health status, and education is minor. Households with sick members are more likely to be affected by cold waves. Higher educational attainment of the head of the household is associated with a lower probability of being affected by cold snaps.In the case of flooding, the classifier is 82.57% accurate. Certain urban conditions, such as access to drinking water, lampposts, and drainage networks, can make rural households more susceptible to flooding. Owning a computer or laptop decreases the likelihood of being affected by flooding while owning a bicycle and being headed by married individuals increases it. Flooding is more common in less developed urban settlements than isolated rural families.In the case of landslides, the classifier is 88.85% accurate and follows a different logic than that of floods. The importance of the prediction is more evenly distributed among the features considered when learning the classifier. Thus, the impact of an individual feature on the prediction is small. Long-term wealth is more critical: the probability of being affected by a landslide is lower for families with specific appliances and household building materials. Rural communities are more affected by landslides, especially those located at higher altitudes and greater distances from cities and markets. The average marginal impact of altitude is non-linear.The classifiers provide an intelligent data-driven method that saves resources by ensuring accuracy. In addition, the research provides guidelines for addressing efficiency in aid distribution, such as facility location formulations and vehicle routing.The research results have several managerial implications, so the authors call for action from disaster risk managers and other relevant stakeholders. Recurrent disasters challenge all of humanity.

When recently graduated psychologists leave the profession, it can have a negative impact on the quality and continuity of care as well as resulting in socioeconomic costs. This study set out to investigate what personal and contextual factors affect newly graduated psychologists' intention to leave the profession (ITLP) over time. Longitudinal data was collected using a survey over three waves: 2017, 2018 and 2019. The participants were newly graduated psychologists in Sweden (n=346) who had answered two consecutive surveys. Logistic regressions were made, with the dependent variable ITLP. The independent variables were: sector (public or private), occupational self-efficacy, work related psychological flexibility, role stress. emotional demands, job satisfaction, social support (from colleagues, supervisor and family), transition between studies and internship, transition between internship and employment and sickness absence. Results showed that job satisfaction, social support from supervisors and the transition between internship and employment had a significant effect on the newly graduated psychologists’ ITLP over time. Due to data limitations some hypothesized relationships might not have been detected. Further research is needed to clarify what affects psychologists’ ITLP over time. / Att psykologer väljer att lämna yrket kan påverka vårdkvalitet och kontinuitet, dessutom innebär det samhällsekonomiska kostnader. Denna studie undersöker vilka faktorer det är som påverkar huruvida psykologer har en intention att lämna yrket (ITLP) eller inte. Longitudinell data samlades in i tre omgångar: 2017, 2018 och 2019. Deltagare var nyligen examinerade psykologer i Sverige (n=346) som hade svarat på två efterföljande enkäter. Logistiska regressioner genomfördes med den beroende variabeln ITLP. De oberoende variabler var: sektor (offentlig eller privat), arbetsrelaterad self-efficacy, arbetsrelaterad psykologisk flexibilitet, rollstress, emotionella krav, arbetstillfredsställelse, socialt stöd (från kollegor, överordnad och familj), övergång mellan studier och praktisk tjänstgöring, övergång mellan praktisk tjänstgöring och arbete samt sjukfrånvaro. Resultatet visade att arbetstillfredsställelse, socialt stöd från överordnad och transitionen mellan praktisk tjänstgöring och arbete hade en signifikant effekt på ITLP över tid. Begränsningar i data kan ha gjort så att vissa av de samband som hypotiserats inte kunde identifieras. Mer framtida forskning behövs för att klargöra vilka faktorer som påverkar psykologers ITLP över tid.