- statslausanne - lists.sib.swiss

Next statistics forum: 14 November, "Hunting for rare genetic determinants of psychiatric traits", Sina Rüeger
by Frédéric Schütz 12 Nov '13

12 Nov '13

Dear all, The next seminar in our series of statistics talks for people interested in quantitative methods in biology and medicine will take place on *Thursday 14 November 2013 at 14h00* (not 11:00!) in the Salle Delachaux (Biopôle 2, premier étage, Route de la Corniche 10, Lausanne, M2: Vennes). The speaker will be *Sina Rüeger* (UNIL) who will speak about "Hunting for rare genetic determinants of psychiatric traits" Abstract: Only little is known about the genetic architecture of psychological disorders (e.g. bipolar disorder, major depression disorder, or cocaine dependence); they are assumed to be highly complex and heterogenous traits. Very few common variants have been identified, thus it is also assumed that rare variants may play an important role. To understand the role of rare variants in psychological disorders and the relation between phenotypes we analysed the sequencing data (including rare variants) using the psychiatric arm of the Colaus study cohort. The talk will focus on difficulties arising from rare variant associations, i.e. the standard methods are not necessarily adequate in this setting. Different “variant burden tests”, designed to analyse rare variants, will be presented; regression based collapsing methods and kernel association tests (SKAT). If time permits, I will also present a strategy of how to combine multiple phenotypes to improve statistical power (some psychiatric traits might be highly correlated, and thus are assumed to have similar genetic risk factors). Hope to see you there! Frédéric (for the organizers: Jérôme Goudet, Valentin Rousson, Frédéric Schütz)

1 0

"On the consequences of dichotomization on correlations and odds-ratios", Keith Baggerly on 12 November 2013
by Frédéric Schütz 04 Nov '13

04 Nov '13

Dear all, next week, the SIB will host Keith Baggerly from the MD Anderson Cancer Center (USA), who will speak about "When is Reproducibility an Ethical Issue? Genomics, Personalized Medicine, and Human Error" The presentation will take place on *Tuesday 12 November October 2013 at 14h00* in the Auditoire B of the Génopode building (Dorigny campus of the University of Lausanne). While this presentation does not happen at the usual time for our "statistics forum", it is likely to be of interest to most statisticians around. Keith's name is associated with the terms "forensic bioinformatics" and "reproducible research", and he was one of the main actors in the "great Duke cancer disaster" saga (see http://www.nytimes.com/2011/07/08/health/research/08genes.html?_r=1& for more information). If you are looking for a more scientific reading, his paper published in the "Annals of Applied Statistics" (http://projecteuclid.org/DPubS?service=UI&version=1.0&verb=Display&handle=e…) is particularly interesting. The abstract follows: Modern high-throughput biological assays let us ask detailed questions about how diseases operate, and promise to let us personalize therapy. Careful data processing is essential, because our intuition about what the answers “should” look like is very poor when we have to juggle thousands of things at once. When documentation of such processing is absent, we must apply “forensic bioinformatics” to work from the raw data and reported results to infer what the methods must have been. We will present several case studies where simple errors may have put patients at risk. This work has been covered both in the scientific press and on the front page of the New York Times, and has prompted several journals to revisit the types of information that must accompany publications. We discuss steps we take to avoid such errors, and lessons that can be applied to large data sets more broadly. Hope to see you there! Frédéric -- Frédéric Schütz, PhD Frederic.Schutz(a)isb-sib.ch Bioinformatics Core Facility (Delorenzi group) Swiss Institute of Bioinformatics http://www.isb-sib.ch/ University of Lausanne http://www.unil.ch/ Batiment Genopode Quartier Sorge Phone: +41 21 692 40 94 CH-1015 Lausanne Fax: +41 21 692 40 65

1 1

Next statistics forum: "On the consequences of dichotomization on correlations and odds-ratios", Valentin Rousson on 24 October 2013
by Frederic Schutz 17 Oct '13

17 Oct '13

Dear all, The next seminar in our series of statistics talks for people interested in quantitative methods in biology and medicine will take place on *Thursday 24 October 2013 at 11h00* in the Salle Delachaux (Biopôle 2, premier étage, Route de la Corniche 10, Lausanne, M2: Vennes). The speaker will be Valentin Rousson from IUMSP/CHUV, who will speak about "On the consequences of dichotomization on correlations and odds-ratios" Abstract: It is well known that dichotomizing continuous data has the effect to decrease statistical power when the goal is to test for a statistical association between two variables. Modern researchers however are not only focusing on statistical significance, but also on an estimation of the "effect size" (i.e. the strength of association between the variables) to judge whether a significant association is also clinically relevant. In this talk, we are interested in the consequences of dichotomizing continuous data on the value of an effect size in some classical settings. It turns out that the conclusions will not be the same whether using a correlation or an odds-ratio to summarize the strength of association between the variables: whereas the value of a correlation is typically decreased by a factor sqrt(pi/2) after each dichotomization, the value of an odds-ratio is at the same time raised to the power sqrt(2). From a descriptive statistical point of view, it is thus not clear whether dichotomizing continuous data leads to a decrease or to an increase of the effect size, as illustrated using a data set to investigate the relationship between motor and intellectual functions in children and adolescents. Hope to see you there! Frédéric (for the organizers: Jérôme Goudet, Valentin Rousson, Frédéric Schütz) -- Frédéric Schütz, PhD Frederic.Schutz(a)isb-sib.ch Bioinformatics Core Facility (Delorenzi group) Swiss Institute of Bioinformatics http://www.isb-sib.ch/ University of Lausanne http://www.unil.ch/ Batiment Genopode Quartier Sorge Phone: +41 21 692 40 94 CH-1015 Lausanne Fax: +41 21 692 40 65

1 0

Next statistics forum on June 13, 2013 at 11:00
by Rousson Valentin 10 Jun '13

10 Jun '13

Dear all, The next seminar in our series of statistics talks for people interested in quantitative methods in biology and medicine will take place on Thursday 13 June 2013 at 11h00 in the Salle Delachaux (Biopôle 2, premier étage, Route de la Corniche 10, Lausanne, M2: Vennes). The speaker will be Michael Amiguet from the IUMSP and University Hospital Lausanne, who will talk about "Weighted Likelihood Negative Binomial Regression" The abstract is enclosed. Hope to see you there ! Valentin (for the organizers: Jérôme Goudet, Valentin Rousson, Frédéric Schütz) _______________________________________________ statslausanne mailing list statslausanne(a)lists.isb-sib.ch http://lists.isb-sib.ch/mailman/listinfo/statslausanne

1 0

seminar on Bayesian trials
by Rousson Valentin 03 Jun '13

03 Jun '13

Dear all, You might be interested (and are very welcome!) to come in the following seminar given by Dr. Simon Wandel (Cogitars GbbH) visiting the IUMSP on this Thursday 6 june 2013 at 14h00 in the Salle Delachaux (Biopôle 2, premier étage, Route de la Corniche 10, Lausanne, M2: Vennes). Title: Fully Bayesian trials: an appetizer Abstract: In the past ten years, the potential of fully Bayesian trials has been recognized by leading Pharmaceutical companies1, regulatory bodies (such as FDA2) and other institutions concerned with all types of research. However, there is still very limited understanding of the clear advantages which Bayesian trials have to offer. This is especially true for situations where traditional concepts such as power do not provide an adequate approach to study design.This talk will start with a short introduction to Bayesian thinking3 followed by real-world examples of fully Bayesian trials. An emphasis will be put on cases where Bayesian trials release their full potential: dealing with parameter uncertainty4, evidence synthesis5, and prediction. In order to actively engage the audience, a real world problem will be posed and discussed at the end of the talk. References 1. Kakizume, T. Novartis: Challenging to Accelerate Oncology New Drug Development. http://atdd- frm.umin.jp/slide/11/kakizume.pdf accessed on April 11, 2013. 2. FDA - CDRH. Guidance for Industry and FDA Staff Guidance for the Use of Bayesian Statistics in Medical Device Clinical Trials. http://www.fda.gov/downloads/MedicalDevices/DeviceRegulationandGuidance/Gui… accessed on April 25, 2013. 3. Spiegelhalter, DJ, Abrams, K and Myles, J. Bayesian Approaches to Clinical Trials and Health-Care Evaluation. Wiley. 4. Joseph, L, Gyorkos, T and Coupal, L. Bayesian Estimation of Disease Prevalence and the Parameters of Diagnostic Tests in the Absence of a Gld Standard. AJE 141, 1991. 5. Schmidli H, Wandel S, Neuenschwander B. The network meta-analytic -predictive approach to non-inferiority trials. Stat Meth in Med Res, 2011. ---------------------------------------------------- Valentin Rousson Unité de Statistique Institut Universitaire de Médecine Sociale et Préventive Centre Hospitalier Universitaire et Université de Lausanne Biopôle 2 Route de la Corniche 10 CH-1010 Lausanne Tél : ++41 (021) 314 73 28 Fax : ++41 (021) 314 73 73 Email: Valentin.Rousson(a)chuv.ch<mailto:Valentin.Rousson@chuv.ch>

1 0

Next statistics forum on Mai 16, 2013 at 11:00
by Rousson Valentin 08 May '13

08 May '13

Dear all, The next seminar in our series of statistics talks for people interested in quantitative methods in biology and medicine will take place on Thursday 16 Mai 2013 at 11h00 in the Salle Delachaux (Biopôle 2, premier étage, Route de la Corniche 10, Lausanne, M2: Vennes). The speaker will be Martina Rothenbühler from the Swiss Household Panel, FORS, University of Lausanne, who will talk about "Methodological challenges of a longitudinal survey" Abstract: The Swiss Household Panel (SHP) is a longitudinal survey with annual repetition. Its principal objective is to analyse social change, in particular the dynamics of the living conditions of the population in Switzerland. Household panels face several challenges related to their longitudinal nature. One of them is the complex weighting system that needs to be adapted to new entries such as children and cohabitants. Another issue in longitudinal surveys is attrition, that is the loss of panel members from one wave to the next. In my presentation I will introduce these two aspects and discuss the measures and techniques applied within the SHP to cope with them. I will also present some ongoing research related to attrition and future developments of the weighting scheme. Hope to see you there ! Valentin (for the organizers: Jérôme Goudet, Valentin Rousson, Frédéric Schütz) ---------------------------------------------------- Unité de Statistique Institut Universitaire de Médecine Sociale et Préventive Centre Hospitalier Universitaire et Université de Lausanne Biopôle 2 Route de la Corniche 10 CH-1010 Lausanne Tél : ++41 (021) 314 73 28 Fax : ++41 (021) 314 73 73 Email: Valentin.Rousson(a)chuv.ch<mailto:Valentin.Rousson@chuv.ch>

1 0

short course on "CONTEMPORARY METHODS OF MORTALITY ANALYSIS"
by Rousson Valentin 02 Apr '13

02 Apr '13

Dear list members, A short course entitled "CONTEMPORARY METHODS OF MORTALITY ANALYSIS" taught by Prof. Leonid Gavrilov and Prof. Natalia Gavrilova from the Center of Aging, NORC at the University of Chicago, will be held on June 19, 20, 21 2013 at the Institute for Social and Preventive Medicine from the University Hospital Lausanne. The course is free of charge but the number of participants is limited to 30. The participants have to register at Catherine.Turrian(a)chuv.ch<mailto:Catherine.Turrian@chuv.ch> before May 31, 2013 providing their name, professional affiliation and e-mail address. A confirmation of registration will be sent. DATE : JUNE 19-20-21, 2013 Location : IUMSP, Biopôle 2, rte de la Corniche 10, CH-1010 Lausanne, niveau -1 Duration: two and half days Wednesday June 19 14:00 – 17:00 Thursday June 20 09:00 – 12:00 and 14:00 – 17:00 Friday June 21 09:00 – 12:00 and 14:00 – 17:00 Description: The course will focus on contemporary statistical methods to study recent historical trends of human mortality and longevity (with implications for forecasting). It considers new approaches to mortality projections and population forecasts, including data analysis at advanced ages. The course starts with basic methods of construction and analysis of period and cohort life tables and explaining common mortality indicators used in demography and survival analysis (e.g., explaining the difference between the hazard rate and the probability of death). The course describes existing mortality laws observed for humans and other animals (the Gompertz-Makeham law, the compensation law of mortality, and the late-life mortality deceleration) and it provides explanation of mortality laws in terms of mathematical reliability theory of aging. Methods of mortality measurement and modeling at advanced ages (including data quality control measures) are described using examples from human and animal mortality data. Various parametric and semi-parametric approaches to mortality forecasting are also presented (Lee-Carter model, model based on principal component analysis of mortality trends). Specifically, a modified method of mortality shifting is illustrated using mortality data of Sweden and other developed countries. This approach involves identifying the best time interval for measuring the rate of mortality decline and its use for mortality extrapolation. Applying cohort-component method of population projections under different scenarios of life extension is also described. New studies and findings on predictors of exceptional human longevity are presented. Finally, methods for calculating healthy life expectancy and health-related indicators are discussed. Participants of this course are encouraged to bring with them laptops with Excel and Stata software for practical exercises on statistical methods and models described in this course. ---------------------------------------------------- Valentin Rousson Unité de Statistique Institut Universitaire de Médecine Sociale et Préventive Centre Hospitalier Universitaire et Université de Lausanne Biopôle 2 Route de la Corniche 10 CH-1010 Lausanne Tél : ++41 (021) 314 73 28 Fax : ++41 (021) 314 73 73 Email: Valentin.Rousson(a)chuv.ch<mailto:Valentin.Rousson@chuv.ch>

1 0

Next statistics forum: "Statistical analysis when data are functions", David Kraus, 21 March 2013
by Frederic Schutz 18 Mar '13

18 Mar '13

Dear all, The next seminar in our series of statistics talks for people interested in quantitative methods in biology and medicine will take place on Thursday 21 March 2013 at 11h00 in the Salle Delachaux (Biopôle 2, premier étage, Route de la Corniche 10, Lausanne, M2: Vennes). The speaker will be David Kraus from the IUMSP and University Hospital Lausanne, who will talk about "Statistical analysis when data are functions" Abstract: Functional data analysis (i.e., statistical analysis of collections of functions) deals with situations where individual observations (data units) are whole functions or curves, representing for example the temporal evolution of a process or the geometric structure of an object. We review some basic properties and methods for analysing functional data and illustrate their use on a blood pressure monitoring data set. We discuss practical issues that arise in the analysis of these data and lead to the development of new methods. Hope to see you there ! Frédéric (for the organizers: Jérôme Goudet, Valentin Rousson, Frédéric Schütz)

1 0

Next statistics forum: "Correlation", Yadolah Dodge on Thursday 29 November 2012
by Frederic Schutz 23 Nov '12

23 Nov '12

Dear all, The next seminar in our series of statistics talks for people interested in quantitative methods in biology and medicine will take place on Thursday 29 November at 11h00 in the Salle Delachaux (Biopôle 2, premier étage, Route de la Corniche 10, Lausanne, M2: Vennes). The speaker will be Yadolah Dodge from the University of Neuchâtel, who will talk about "Correlation" --- Abstract: The word correlation is a wonderful example of a word that started out as a general term and proved to be so useful in various fields of study that it developed more specialized senses over time. In the 19th century, scholars of various disciplines adopted the term correlation to their specific areas of interest. After examining forearm and height measurements, Galton introduced the concept of correlation in 1888. In statistics, the Pearson product-moment correlation coefficient or Pearson's r is a measure of the linear dependence between two variables X and Y. It is widely used in the sciences as a measure of the strength of linear dependence between two variables. In this talk we introduce different formulas for the correlation coefficient for different applications. In particular, we discuss the third and the fourth power of r for determining the direction of dependency in linear regression. Keywords. Causality. Correlation coefficient. Linear regression. Response variable. Kurtosis coefficient. Coefficient of variation. Skewness coefficient. References: Dodge, Y. and Yadegari, I. (2013). Correlation and its Applications. To appear. --- You can find more information about the forum on our web page at http://moodle.unil.ch/course/view.php?id=2729 Hope to see you there ! Frédéric (for the organizers: Jérôme Goudet, Valentin Rousson, Frédéric Schütz)

1 0

Next statistics forum: Helena Marti Soler, Thursday 1st November 2012
by Frederic Schutz 29 Oct '12

29 Oct '12

Dear all, The next seminar in our series of statistics talks for people interested in quantitative methods in biology and medicine will take place on Thursday 1st November at 11h00 in the Salle Delachaux (Biopôle 2, premier étage, Route de la Corniche 10, Lausanne, M2: Vennes). The speaker will be Helena Marti Soler from the IUMSP, who will talk (in French) about "Modélisation des données d’enquêtes cas-cohorte par imputation multiple : Application en épidémiologie cardio-vasculaire". Please see the abstract attached (in PDF). You can find more information about the forum on our web page at http://moodle.unil.ch/course/view.php?id=2729 Hope to see you there ! Frédéric (for the organizers: Jérôme Goudet, Valentin Rousson, Frédéric Schütz)

1 0