XLSTAT se integra a la familia Lumivero. Conoce más

# Cursos y Webinares

Addinsoft organiza sesiones públicas (interempresas) y privadas (intraempresas) para todos los niveles. Puede inscribirse en uno de nuestros cursos programados o ponerse en contacto con nosotros para solicitar un curso de formación personalizado. Todos nuestros cursos están disponibles en aulas virtuales.

## ANOVA and Regression models with XLSTAT

You would like to understand the difference between analysis of variance and regression ? During this training, you will perform these analyses in Excel with XLSTAT using concrete examples.

3 días
21H

SEE BROCHURE

### Documentos

This course places a strong emphasis on ANOVA and regression modeling and is addressed to anyone interested in mastering these two fundamental statistical methods. The ANOVA component of the course will focus on: simple ANOVA, multifactor, balanced ANOVA, repeated measures ANOVA. The regression part will be mainly devoted to simple regression followed by an introduction to multiple regression. The course is suitable for people who are looking to understand how ANOVA and regression works, apply these tools to their own data and interpret XLSTAT outputs. The course will spend ⅔ of the time on ANOVA and ⅓ on regression.

Main topics covered in this training:

• One-way ANOVA
• Pairwise multiple comparison tests
• Analysis of variance with crossed factors
• Repeated measures analysis of variance (balanced designs)
• Simple linear regression

Required experience:

Trainees must have a good knowledge of basic statistical tools: descriptive statistic, hypotheses testing, confidence intervals, p-value, alpha risk, etc.

Syllabus:

### Review of basic statistical tools

• Writing conventions on samples (x̄, s, …) and populations (µ, σ, …)
• Confidence intervals
• Hypothesis testing
• The p-value

### Implementation and interpretation of a one-way factor ANOVA

• The context for using the simple ANOVA
• Differences with the Student Test
• Independent and paired data
• Assumptions of ANOVA
• Variance decomposition
• Interpretation of the ANOVA table
• Experimental error
• Significance of effects
• The importance of degrees of freedom for the error term
• Multiple comparisons of the means
• Post-hoc tests (Tukey, Bonferroni, Newman-Keuls, ...)
• Common mistakes to avoid in ANOVA

### Implementation and interpretation of a two-way and multi-factor ANOVA

• Context for using a two-factor ANOVA
• The concept of interaction terms
• Assumptions for implementing a two-factor ANOVA on balanced and unbalanced designs
• Decomposing the variance
• Interpreting the ANOVA table (sum of squares, effects, interactions, ...)
• Multiple pairwise comparisons of means (Tukey, Bonferroni, Dunnett,…)
• Graphical output of the model

### The different experimental designs and associated models

• Presentation of the linear model
• The different types of factors
• The different types of models:
• Models with and without interactions
• Crossed and nested models
• Repeated measures
• The importance and pertinence of experimental designs

### Implementation and interpretation of a simple linear regression

• General principals of regression:
• Differences between ANOVA and Regression
• Objectives and assumptions
• Basic principles of regression modeling
• The different models of regression: simple and multiple linear model
• Model quality: error of estimation, coefficient of determination
• Residual analysis:
• Residual computations
• Homogeneity
• Suspect values
• Graphical analysis
• Using the model:
• Prediction of individual values
• Confidence intervals of the predictions
• Graphical representation of the results
• Common mistakes to avoid in regression
• Introduction to multiple regression