Specification and testing of multiplicative time-varying GARCH models with applications

In this article, we develop a specification technique for building multiplicative time-varying GARCH models of Amado and Teräsvirta (2008, 2013). The variance is decomposed into an unconditional and a conditional component such that the unconditional variance component is allowed to evolve smoothly over time. This nonstationary component is defined as a linear combination of logistic transition functions with time as the transition variable. The appropriate number of transition functions is determined by a sequence of specification tests. For that purpose, a coherent modelling strategy based on statistical inference is presented. It is heavily dependent on Lagrange multiplier type misspecification tests. The tests are easily implemented as they are entirely based on auxiliary regressions. Finite-sample properties of the strategy and tests are examined by simulation. The modelling strategy is illustrated in practice with two real examples: an empirical application to daily exchange rate returns and another one to daily coffee futures returns.

Evaluating sampling strategies and logistic regression methods for modelling complex land cover changes

The role of land cover change as a significant component of global change has become increasingly recognized in recent decades. Large databases measuring land cover change, and the data which can potentially be used to explain the observed changes, are also becoming more commonly available. When developing statistical models to investigate observed changes, it is important to be aware that the chosen sampling strategy and modelling techniques can influence results. We present a comparison of three sampling strategies and two forms of grouped logistic regression models (multinomial and ordinal) in the investigation of patterns of successional change after agricultural land abandonment in Switzerland. Results indicated that both ordinal and nominal transitional change occurs in the landscape and that the use of different sampling regimes and modelling techniques as investigative tools yield different results. Synthesis and applications. Our multimodel inference identified successfully a set of consistently selected indicators of land cover change, which can be used to predict further change, including annual average temperature, the number of already overgrown neighbouring areas of land and distance to historically destructive avalanche sites. This allows for more reliable decision making and planning with respect to landscape management. Although both model approaches gave similar results, ordinal regression yielded more parsimonious models that identified the important predictors of land cover change more efficiently. Thus, this approach is favourable where land cover change pattern can be interpreted as an ordinal process. Otherwise, multinomial logistic regression is a viable alternative.

State-dependent threshold STAR models

In this paper we consider extensions of smooth transition autoregressive (STAR) models to situations where the threshold is a time-varying function of variables that affect the separation of regimes of the time series under consideration. Our specification is motivated by the observation that unusually high/low values for an economic variable may sometimes be best thought of in relative terms. State-dependent logistic STAR and contemporaneous-threshold STAR models are introduced and discussed. These models are also used to investigate the dynamics of U.S. short-term interest rates, where the threshold is allowed to be a function of past output growth and inflation.

Predictive models of syncope causes in an outpatient clinic

The investigation of unexplained syncope remains a challenging clinical problem. In the present study we sought to evaluate the diagnostic value of a standardized work-up focusing on non invasive tests in patients with unexplained syncope referred to a syncope clinic, and whether certain combinations of clinical parameters are characteristic of rhythmic and reflex causes of syncope. METHODS AND RESULTS: 317 consecutive patients underwent a standardized work-up including a 12-lead ECG, physical examination, detailed history with screening for syncope-related symptoms using a structured questionnaire followed by carotid sinus massage (CSM), and head-up tilt test. Invasive testings including an electrophysiological study and implantation of a loop recorder were only performed in those with structural heart disease or traumatic syncope. Our work-up identified an etiology in 81% of the patients. Importantly, three quarters of the causes were established non invasively combining head-up tilt test, CSM and hyperventilation testing. Invasive tests yielded an additional 7% of diagnoses. Logistic analysis identified age and number of significant prodromes as the only predictive factors of rhythmic syncope. The same two factors, in addition to the duration of the ECG P-wave, were also predictive of vasovagal and psychogenic syncope. These factors, optimally combined in predictive models, showed a high negative and a modest positive predictive value. CONCLUSION: A standardized work-up focusing on non invasive tests allows to establish more than three quarters of syncope causes. Predictive models based on simple clinical parameters may help to distinguish between rhythmic and other causes of syncope

Do pseudo-absence selection strategies influence species distribution models and their predictions? An information-theoretic approach based on simulated data

Background Multiple logistic regression is precluded from many practical applications in ecology that aim to predict the geographic distributions of species because it requires absence data, which are rarely available or are unreliable. In order to use multiple logistic regression, many studies have simulated "pseudo-absences" through a number of strategies, but it is unknown how the choice of strategy influences models and their geographic predictions of species. In this paper we evaluate the effect of several prevailing pseudo-absence strategies on the predictions of the geographic distribution of a virtual species whose "true" distribution and relationship to three environmental predictors was predefined. We evaluated the effect of using a) real absences b) pseudo-absences selected randomly from the background and c) two-step approaches: pseudo-absences selected from low suitability areas predicted by either Ecological Niche Factor Analysis: (ENFA) or BIOCLIM. We compared how the choice of pseudo-absence strategy affected model fit, predictive power, and information-theoretic model selection results. Results Models built with true absences had the best predictive power, best discriminatory power, and the "true" model (the one that contained the correct predictors) was supported by the data according to AIC, as expected. Models based on random pseudo-absences had among the lowest fit, but yielded the second highest AUC value (0.97), and the "true" model was also supported by the data. Models based on two-step approaches had intermediate fit, the lowest predictive power, and the "true" model was not supported by the data. Conclusion If ecologists wish to build parsimonious GLM models that will allow them to make robust predictions, a reasonable approach is to use a large number of randomly selected pseudo-absences, and perform model selection based on an information theoretic approach. However, the resulting models can be expected to have limited fit.

Establishment of models to study mouse and human retinogenesis "in vitro" : isolation and characterization of retinal stem cells

SUMMARY IN FRENCH Les cellules souches sont des cellules indifférenciées capables a) de proliférer, b) de s'auto¬renouveller, c) de produire des cellules différenciées, postmitotiques et fonctionnelles (multipotencialité), et d) de régénérer le tissu après des lésions. Par exemple, les cellules de souches hematopoiétiques, situées dans la moelle osseuse, peuvent s'amplifier, se diviser et produire diverses cellules différenciées au cours de la vie, les cellules souches restant dans la moelle osseuse et consentant leur propriété. Les cellules souches intestinales, situées dans la crypte des microvillosités peuvent également régénérer tout l'intestin au cours de la vie. La rétine se compose de six classes de neurones et d'un type de cellule gliale. Tous ces types de cellules sont produits par un progéniteur rétinien. Le pic de production des photorécepteurs se situe autour des premiers jours postnatals chez la souris. A cette période la rétine contient les cellules hautement prolifératives. Dans cette étude, nous avons voulu analyser le phénotype de ces cellules et leur potentiel en tant que cellules souches ou progénitrices. Nous nous sommes également concentrés sur l'effet de certains facteurs épigéniques sur leur destin cellulaire. Nous avons observé que toutes les cellules prolifératives isolées à partir de neurorétines postnatales de souris expriment le marqueur de glie radiaire RC2, ainsi que des facteurs de transcription habituellement trouvés dans la glie radiaire (Mash1, Pax6), et répondent aux critères des cellules souches : une capacité élevée d'expansion, un état indifférencié, la multipotencialité (démontrée par analyse clonale). Nous avons étudié la différentiation des cellules dans différents milieux de culture. En l'absence de sérum, l'EGF induit l'expression de la β-tubulin-III, un marqueur neuronal, et l'acquisition d'une morphologie neuronale, ceci dans 15% des cellules présentes. Nous avons également analysé la prolifération de cellules. Seulement 20% des cellules incorporent le bromodéoxyuridine (BrdU) qui est un marqueur de division cellulaire. Ceci démontre que l'EGF induit la formation des neurones sans une progression massive du cycle cellulaire. Par ailleurs, une stimulation de 2h d'EGF est suffisante pour induire la différentiation neuronale. Certains des neurones formés sont des cellules ganglionnaires rétiniennes (GR), comme l'indique l'expression de marqueurs de cellules ganglionnaires (Ath5, Brn3b et mélanopsine), et dans de rare cas d'autres neurones rétiniens ont été observés (photorécepteurs (PR) et cellules bipolaires). Nous avons confirmé que les cellules souches rétiniennes tardives n'étaient pas restreintes au cours du temps et qu'elles conservent leur multipotencialité en étant capables de générer des neurones dits précoces (GR) ou tardifs (PR). Nos résultats prouvent que l'EGF est non seulement un facteur contrôlant le développement glial, comme précédemment démontré, mais également un facteur efficace de différentiation pour les neurones rétiniens, du moins in vitro. D'autre part, nous avons voulu établir si l'oeil adulte humain contient des cellules souches rétiniennes (CSRs). L'oeil de certains poissons ou amphibiens continue de croître pendant l'âge adulte du fait de l'activité persistante des cellules souches rétiniennes. Chez les poissons, le CSRs se situe dans la marge ciliaire (CM) à la périphérie de la rétine. Bien que l'oeil des mammifères ne se développe plus pendant la vie d'adulte, plusieurs groupes ont prouvé que l'oeil de mammifères adultes contient des cellules souches rétiniennes également dans la marge ciliaire plus précisément dans l'épithélium pigmenté et non dans la neurorétine. Ces CSRs répondent à certains critères des cellules souches. Nous avons identifié et caractérisé les cellules souches rétiniennes résidant dans l'oeil adulte humain. Nous avons prouvé qu'elles partagent les mêmes propriétés que leurs homologues chez les rongeurs c.-à-d. auto-renouvellement, amplification, et différenciation en neurones rétiniens in vitro et in vivo (démontré par immunocoloration et microarray). D'autre part, ces cellules peuvent être considérablement amplifiées, tout en conservant leur potentiel de cellules souches, comme indiqué par l'analyse de leur profil d'expression génique (microarray). Elles expriment également des gènes communs à diverses cellules souches: nucleostemin, nestin, Brni1, Notch2, ABCG2, c-kit et son ligand, aussi bien que cyclin D3 qui agit en aval de c-kit. Nous avons pu montré que Bmi1et Oct4 sont nécessaires pour la prolifération des CSRs confortant leur propriété de cellules souches. Nos données indiquent que la neurorétine postnatale chez la souris et l'épithélium pigmenté de la marge ciliaire chez l'humain adulte contiennent les cellules souches rétiniennes. En outre, nous avons développé un système qui permet d'amplifier et de cultiver facilement les CSRs. Ce modèle permet de disséquer les mécanismes impliqués lors de la retinogenèse. Par exemple, ce système peut être employé pour l'étude des substances ou des facteurs impliqués, par exemple, dans la survie ou dans la génération des cellules rétiniennes. Il peut également aider à disséquer la fonction de gènes ou les facteurs impliqués dans la restriction ou la spécification du destin cellulaire. En outre, dans les pays occidentaux, la rétinite pigmentaire (RP) touche 1 individu sur 3500 et la dégénérescence maculaire liée à l'âge (DMLA) affecte 1 % à 3% de la population âgée de plus de 60 ans. La génération in vitro de cellules rétiniennes est aussi un outil prometteur pour fournir une source illimitée de cellules pour l'étude de transplantation cellulaire pour la rétine. SUMMARY IN ENGLISH Stem cells are defined as undifferentiated cells capable of a) proliferation, b) self maintenance (self-renewability), c) production of many differentiated functional postmitotic cells (multipotency), and d) regenerating tissue after injury. For instance, hematopoietic stem cells, located in bone marrow, can expand, divide and generate differentiated cells into the diverse lineages throughout life, the stem cells conserving their status. In the villi crypt, the intestinal stem cells are also able to regenerate the intestine during their life time. The retina is composed of six classes of neurons and one glial cell. All these cell types are produced by the retinal progenitor cell. The peak of photoreceptor production is reached around the first postnatal days in rodents. Thus, at this stage the retina contains highly proliferative cells. In our research, we analyzed the phenotype of these cells and their potential as possible progenitor or stem cells. We also focused on the effect of epigenic factor(s) and cell fate determination. All the proliferating cells isolated from mice postnatal neuroretina harbored the radial glia marker RC2, expressed transcription factors usually found in radial glia (Mash 1, Pax6), and met the criteria of stem cells: high capacity of expansion, maintenance of an undifferentiated state, and multipotency demonstrated by clonal analysis. We analyzed the differentiation seven days after the transfer of the cells in different culture media. In the absence of serum, EGF led to the expression of the neuronal marker β-tubulin-III, and the acquisition of neuronal morphology in 15% of the cells. Analysis of cell proliferation by bromodeoxyuridine incorporation revealed that EGF mainly induced the formation of neurons without stimulating massively cell cycle progression. Moreover, a pulse of 2h EGF stimulation was sufficient to induce neuronal differentiation. Some neurons were committed to the retinal ganglion cell (RGC) phenotype, as revealed by the expression of retinal ganglion markers (Ath5, Brn3b and melanopsin), and in few cases to other retinal phenotypes (photoreceptors (PRs) and bipolar cells). We confirmed that the late RSCs were not restricted over-time and conserved multipotentcy characteristics by generating retinal phenotypes that usually appear at early (RGC) or late (PRs) developmental stages. Our results show that EGF is not only a factor controlling glial development, as previously shown, but also a potent differentiation factor for retinal neurons, at least in vitro. On the other hand, we wanted to find out if the adult human eye contains retina stem cells. The eye of some fishes and amphibians continues to grow during adulthood due to the persistent activity of retinal stem cells (RSCs). In fish, the RSCs are located in the ciliary margin zone (CMZ) at the periphery of the retina. Although, the adult mammalian eye does not grow during adult life, several groups have shown that the adult mouse eye contains retinal stem cells in the homologous zone (i.e. the ciliary margin), in the pigmented epithelium and not in the neuroretina. These RSCs meet some criteria of stem cells. We identified and characterized the human retinal stem cells. We showed that they posses the same features as their rodent counterpart i.e. they self-renew, expand and differentiate into retinal neurons in vitro and in vivo (indicated by immunostaining and microarray analysis). Moreover, they can be greatly expanded while conserving their sternness potential as revealed by the gene expression profile analysis (microarray approach). They also expressed genes common to various stem cells: nucleostemin, nestin, Bmil , Notch2, ABCG2, c-kit and its ligand, as well as cyclin D3 which acts downstream of c-kit. Furthermore, Bmil and Oct-4 were required for RSC proliferation reinforcing their stem cell identity. Our data indicate that the mice postnatal neuroretina and the adult pigmented epithelium of adult human ciliary margin contain retinal stem cells. We developed a system to easily expand and culture RSCs that can be used to investigate the retinogenesis. For example, it can help to screen drugs or factors involved, for instance, in the survival or generation of retinal cells. This could help to dissect genes or factors involved in the restriction or specification of retinal cell fate. In Western countries, retinitis pigmentosa (RP) affects 1 out of 3'500 individuals and age-related macula degeneration (AMD) strikes 1 % to 3% of the population over 60. In vitro generation of retinal cells is thus a promising tool to provide an unlimited cell source for cellular transplantation studies in the retina.

Effects of sample size on the performance of species distribution models

A wide range of modelling algorithms is used by ecologists, conservation practitioners, and others to predict species ranges from point locality data. Unfortunately, the amount of data available is limited for many taxa and regions, making it essential to quantify the sensitivity of these algorithms to sample size. This is the first study to address this need by rigorously evaluating a broad suite of algorithms with independent presence-absence data from multiple species and regions. We evaluated predictions from 12 algorithms for 46 species (from six different regions of the world) at three sample sizes (100, 30, and 10 records). We used data from natural history collections to run the models, and evaluated the quality of model predictions with area under the receiver operating characteristic curve (AUC). With decreasing sample size, model accuracy decreased and variability increased across species and between models. Novel modelling methods that incorporate both interactions between predictor variables and complex response shapes (i.e. GBM, MARS-INT, BRUTO) performed better than most methods at large sample sizes but not at the smallest sample sizes. Other algorithms were much less sensitive to sample size, including an algorithm based on maximum entropy (MAXENT) that had among the best predictive power across all sample sizes. Relative to other algorithms, a distance metric algorithm (DOMAIN) and a genetic algorithm (OM-GARP) had intermediate performance at the largest sample size and among the best performance at the lowest sample size. No algorithm predicted consistently well with small sample size (n < 30) and this should encourage highly conservative use of predictions based on small sample size and restrict their use to exploratory modelling.

The five and seven factors personality models: differences and similitude between the TCI-R, NEO-FFI-R and ZKPQ-50-CC

The present study tests the relationships between the three frequently used personality models evaluated by the Temperament Character Inventory-Revised (TCI-R), Neuroticism Extraversion Openness Five Factor Inventory – Revised (NEO-FFI-R) and Zuckerman-Kuhlman Personality Questionnaire-50- Cross-Cultural (ZKPQ-50-CC). The results were obtained with a sample of 928 volunteer subjects from the general population aged between 17 and 28 years old. Frequency distributions and alpha reliabilities with the three instruments were acceptable. Correlational and factorial analyses showed that several scales in the three instruments share an appreciable amount of common variance. Five factors emerged from principal components analysis. The first factor was integrated by A (Agreeableness), Co (Cooperativeness) and Agg-Host (Aggressiveness-Hostility), with secondary loadings in C (Conscientiousness) and SD (Self-directiveness) from other factors. The second factor was composed by N (Neuroticism), N-Anx (Neuroticism-Anxiety), HA (Harm Avoidance) and SD (Self-directiveness). The third factor was integrated by Sy (Sociability), E (Extraversion), RD (Reward Dependence), ImpSS (Impulsive Sensation Seeking) and NS (novelty Seeking). The fourth factor was integrated by Ps (Persistence), Act (Activity), and C, whereas the fifth and last factor was composed by O (Openness) and ST (Self- Transcendence). Confirmatory factor analyses indicate that the scales in each model are highly interrelated and define the specified latent dimension well. Similarities and differences between these three instruments are further discussed.

Factors Affecting the Forecasting Accuracy of Diffusion Models

Tutkielman tavoitteena oli tarkastella innovaatioiden leviämismallien ennustetarkkuuteen vaikuttavia tekijöitä. Tutkielmassa ennustettiin logistisella mallilla matkapuhelinliittymien leviämistä kolmessa Euroopan maassa: Suomessa, Ranskassa ja Kreikassa. Teoriaosa keskittyi innovaatioiden leviämisen ennustamiseen leviämismallien avulla. Erityisesti painotettiin mallien ennustuskykyä ja niiden käytettävyyttä eri tilanteissa. Empiirisessä osassa keskityttiin ennustamiseen logistisella leviämismallilla, joka kalibroitiin eri tavoin koostetuilla aikasarjoilla. Näin tehtyjä ennusteita tarkasteltiin tiedon kokoamistasojen vaikutusten selvittämiseksi. Tutkimusasetelma oli empiirinen, mikä sisälsi logistisen leviämismallin ennustetarkkuuden tutkimista otosdatan kokoamistasoa muunnellen. Leviämismalliin syötettävä data voidaan kerätä kuukausittain ja operaattorikohtaisesti vaikuttamatta ennustetarkkuuteen. Dataan on sisällytettävä leviämiskäyrän käännöskohta, eli pitkän aikavälin huippukysyntäpiste.

Logistic regression to estimate the welfare of broiler breeders in relation to environmental and behavioral variables

The increasing demand of consumer markets for the welfare of birds in poultry house has motivated many scientific researches to monitor and classify the welfare according to the production environment. Given the complexity between the birds and the environment of the aviary, the correct interpretation of the conduct becomes an important way to estimate the welfare of these birds. This study obtained multiple logistic regression models with capacity of estimating the welfare of broiler breeders in relation to the environment of the aviaries and behaviors expressed by the birds. In the experiment, were observed several behaviors expressed by breeders housed in a climatic chamber under controlled temperatures and three different ammonia concentrations from the air monitored daily. From the analysis of the data it was obtained two logistic regression models, of which the first model uses a value of ammonia concentration measured by unit and the second model uses a binary value to classify the ammonia concentration that is assigned by a person through his olfactory perception. The analysis showed that both models classified the broiler breeder's welfare successfully.

Determinants of credit risk in secured loans – Evidence from the auto loan industry

The purpose of this study is to examine attributes which have explanation power to the probability of default or serious overdue in secured auto loans. Another goal is to find out differences between defaulted loans and loans which have had payment difficulties but survived without defaulting. 19 independent variables used in this study reflect information available at the time of credit decision. These variables were tested with logistic regression and backward elimination procedure. The data includes 8931 auto loans from a Finnish finance company. 1118 of the contracts were taken by company customers and 7813 by private customers. 130 of the loans defaulted and 584 had serious payment problems but did not default. The maturities of those loans were from one month to 60 months and they have ended during year 2011. The LTV (loan-to-value) variable was ranked as the most significant explainer because of its strong positive relationship with probability of payment difficulties. Another important explainer in this study was the credit rating variable which got a negative relationship with payment problems. Also maturity and car age performed well having both a positive relationship with the probability of payment problems. When compared default and serious overdue situations, the most significant differences were found in the roles of LTV, Maturity and Gender variables.

Parameter identification in time series models

Time series analysis can be categorized into three different approaches: classical, Box-Jenkins, and State space. Classical approach makes a basement for the analysis and Box-Jenkins approach is an improvement of the classical approach and deals with stationary time series. State space approach allows time variant factors and covers up a broader area of time series analysis. This thesis focuses on parameter identifiablity of different parameter estimation methods such as LSQ, Yule-Walker, MLE which are used in the above time series analysis approaches. Also the Kalman filter method and smoothing techniques are integrated with the state space approach and MLE method to estimate parameters allowing them to change over time. Parameter estimation is carried out by repeating estimation and integrating with MCMC and inspect how well different estimation methods can identify the optimal model parameters. Identification is performed in probabilistic and general senses and compare the results in order to study and represent identifiability more informative way.

Artificial neural network models for predicting 1-year mortality in elderly patients with intertrochanteric fractures in China

The mortality rate of older patients with intertrochanteric fractures has been increasing with the aging of populations in China. The purpose of this study was: 1) to develop an artificial neural network (ANN) using clinical information to predict the 1-year mortality of elderly patients with intertrochanteric fractures, and 2) to compare the ANN's predictive ability with that of logistic regression models. The ANN model was tested against actual outcomes of an intertrochanteric femoral fracture database in China. The ANN model was generated with eight clinical inputs and a single output. ANN's performance was compared with a logistic regression model created with the same inputs in terms of accuracy, sensitivity, specificity, and discriminability. The study population was composed of 2150 patients (679 males and 1471 females): 1432 in the training group and 718 new patients in the testing group. The ANN model that had eight neurons in the hidden layer had the highest accuracies among the four ANN models: 92.46 and 85.79% in both training and testing datasets, respectively. The areas under the receiver operating characteristic curves of the automatically selected ANN model for both datasets were 0.901 (95%CI=0.814-0.988) and 0.869 (95%CI=0.748-0.990), higher than the 0.745 (95%CI=0.612-0.879) and 0.728 (95%CI=0.595-0.862) of the logistic regression model. The ANN model can be used for predicting 1-year mortality in elderly patients with intertrochanteric fractures. It outperformed a logistic regression on multiple performance measures when given the same variables.

Modélisation de l'interprétation des pianistes & applications d'auto-encodeurs sur des modèles temporels

Ce mémoire traite d'abord du problème de la modélisation de l'interprétation des pianistes à l'aide de l'apprentissage machine. Il s'occupe ensuite de présenter de nouveaux modèles temporels qui utilisent des auto-encodeurs pour améliorer l'apprentissage de séquences. Dans un premier temps, nous présentons le travail préalablement fait dans le domaine de la modélisation de l'expressivité musicale, notamment les modèles statistiques du professeur Widmer. Nous parlons ensuite de notre ensemble de données, unique au monde, qu'il a été nécessaire de créer pour accomplir notre tâche. Cet ensemble est composé de 13 pianistes différents enregistrés sur le fameux piano Bösendorfer 290SE. Enfin, nous expliquons en détail les résultats de l'apprentissage de réseaux de neurones et de réseaux de neurones récurrents. Ceux-ci sont appliqués sur les données mentionnées pour apprendre les variations expressives propres à un style de musique. Dans un deuxième temps, ce mémoire aborde la découverte de modèles statistiques expérimentaux qui impliquent l'utilisation d'auto-encodeurs sur des réseaux de neurones récurrents. Pour pouvoir tester la limite de leur capacité d'apprentissage, nous utilisons deux ensembles de données artificielles développées à l'Université de Toronto.

L'association entre l'utilisation du transport actif et l'état de santé auto-rapporté chez des adultes montréalais

Introduction : Une majorité de Canadiens adopte un mode de vie sédentaire qui est un facteur de risque important pour différents problèmes de santé. Dernièrement, des interventions en santé publique ciblent le transport actif pour augmenter la pratique d’activité physique. Objectif : L’objectif de cette étude est de quantifier la direction et la taille de l’association entre l’état de santé rapporté par des adultes montréalais et leur utilisation de la marche et du vélo utilitaires. Méthode : L’échantillon comprend 4503 résidents de l’Île de Montréal, âgés de 18 ans et plus, ayant répondu à un sondage téléphonique sur la pratique de l’activité physique et du transport actif. Des analyses de régression logistique multiples ont été appliquées pour examiner l’association entre l’état de santé auto-rapporté et la pratique du vélo (N=4386) et entre l’état de santé auto-rapporté et la pratique de la marche utilitaire (N=4350). Résultats : Les gens ayant une santé perçue comme bonne et moyenne/mauvaise ont une probabilité plus faible de pratiquer la marche utilitaire (OR = 0,740; p < 0,05 et OR = 0,552; p < 0,01) que ceux rapportant une excellente santé, alors que cette association n’est pas significative pour la pratique du vélo utilitaire dans notre étude. Conclusion : Bien que les résultats obtenus ne soient pas tous statistiquement significatifs, la probabilité d’utiliser le transport actif semble plus faible chez les adultes indiquant un moins bon état de santé par rapport aux adultes indiquant que leur état de santé est excellent.