Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Christophe Lalanne.
Biostatistics and Computer-based Analysis of Health Data using SAS | 2017
Christophe Lalanne; Mounir Mesbah
In this final chapter, we will essentially introduce two new statistical procedures: PROC LIFETEST and PROC PHREG. These two procedures enable the analysis of survival data.
Biostatistics and Computer-based Analysis of Health Data using SAS | 2017
Christophe Lalanne; Mounir Mesbah
In this chapter, we will look at the main commands capable of summarizing, in a quantitative or graphical manner, the distribution of a numeric or categorical variable.
Biostatistics and Computer-based Analysis of Health Data using SAS | 2017
Christophe Lalanne; Mounir Mesbah
In this chapter, we are going to present in more detail the statistical procedures seen in the previous chapter: PROC FREQ and PROC TTEST. We will see how they enable us to compare theoretical means or probability of events (theoretical proportions). We will also see how to use the PROC FREQ procedure to estimate odds ratios and other relative risks in a contingency table. Finally, we will address the PROC ANOVA and PROC GLM procedures to carry out multifactor analysis of variance, as well as PROC NPAR1WAY to perform non-parametric tests.
Biostatistics and Computer-based Analysis of Health Data using SAS | 2017
Christophe Lalanne; Mounir Mesbah
In this chapter, we are essentially going to present two new statistical procedures: PROC CORR and PROC REG.
Biostatistics and Computer-Based Analysis of Health Data Using Stata | 2017
Christophe Lalanne; Mounir Mesbah
This chapter focuses on measures of association between two categorical variables (χ 2 or Fisher test for a contingency table, and the calculation of the odds ratio (OR)) or between a numeric variable and a classification factor. In the latter case, we will consider the case of two independent (or not) samples, as well as parametric (Students t -test) and non-parametric (Wilcoxon test) models for two or more samples situations (analysis of variance (ANOVA) and Kruskal–Wallis ANOVA). The Bonferroni correction method for multiple comparisons of treatment and the linear trend test for the ANOVA will also be discussed. The case of two-factor ANOVA is presented succinctly, restricted to the major commands allowing for the construction of the ANOVA table and an interaction graph to be plotted.
Biostatistics and Computer-Based Analysis of Health Data Using Stata | 2017
Christophe Lalanne; Mounir Mesbah
After having reviewed the principal measures of risk in epidemiologic and diagnostic studies, we will focus on modeling a binary variable according to numerical or binary explanatory variables based on the logistic regression model.
Biostatistics and Computer-based Analysis of Health Data using R | 2016
Christophe Lalanne; Mounir Mesbah
This chapter revisits the measures of association typically found in epidemiology or clinical research studies and the concepts discussed partly. It will cover the risk measures such as the odds ratio in prospective studies or the sensitivity/specificity measures of a diagnostic test. The simple logistic regression model in which we consider a single explanatory variable, numerical or qualitative, is presented in detail: estimation of the parameters of the model, in the case of individual or grouped data, pointwise and interval prediction. Finally, the construction of an ROC curve completes this chapter addressing the case where the response variable is a binary variable.
Biostatistics and Computer-based Analysis of Health Data using R | 2016
Christophe Lalanne; Mounir Mesbah
R is more than a simple software program for statistics; it is a language for the manipulation of statistical data. This partly explains its difficult non user-friendly approach for users accustomed to drop-down menus such as those offered by SPSS (although SPSS also offers a basic macro language). This chapter allows the reader to discover the elements of the language and to become familiarized with the mechanisms by which to represent statistical data in R. In the illustrations that follow, the R commands are prefixed with the symbol >, which designates the R console prompt. It is, therefore, unnecessary to copy this symbol to test the proposed instructions.
Biostatistics and Computer-based Analysis of Health Data using R | 2016
Christophe Lalanne; Mounir Mesbah
In this chapter, we will pay particular attention to quantification, in terms of direction and amplitude, and to testing the degree of association between two variables whether symmetrical or not. In the first instance, we will discuss the comparison of mean values, mainly focusing on two samples, whether independent or not, where a variable acts as the response variable and the other as an explanatory variable. The student’s t-test will be used, as well as its non-parametric alternative (Wilcoxon–Mann–Whitney test) for two samples. In a second phase, we focus on two-way contingency tables (independent samples) as well as conventional measures of association (chi-squared test) or those more specific to epidemiology (odds ratio, relative risk), including the case of non-independent samples (McNemar’s test). In these situations, the variables can play a symmetrical role (or in the case of relative risk). Before describing these testing procedures, the R commands that can be used to summarize a data structure consisting of two variables will also be discussed.
Biostatistics and Computer-based Analysis of Health Data using R | 2016
Christophe Lalanne; Mounir Mesbah
In this chapter, we will focus on monotonic or linear association measures between two numeric variables (pointwise or interval estimation, correlation coefficient test) and on the associated exploratory graphical representations (scatter diagram and Loess curve). The linear regression model is then developed in the case of an explanatory variable (simple linear regression); particularly the estimation of the regression line coefficients and the construction of the associated null hypothesis tests, the table of the variance analysis associated with the regression model, as well as pointwise and interval prediction. The verification of the application conditions and the model diagnosis by analysis of the residuals are also considered.