Training Catalog

• Understanding the contribution of NVivo for analyzing qualitative data
• Using the NVivo interface
• Importing and organizing data in an NVivo project
• Coding data
• Understanding the most advanced features of the software (queries, visualizations, intercoder reliability…)

Day 1

1. Introduction to NVivo
2. Discovering the NVivo user interface
3. Creating and importing data in NVivo*
4. Organizing data through memo links and annotations*
5. Organizing data using file classifications*
6. Organizing data using cases and case classifications*
7. Coding data (coding, uncoding, coding stripes, organizing codes hierarchically, codebook)*

Day 2

1. Coding relations and sentiments
2. Working with non-textual data (pdfs, audio, video, pictures, surveys)
3. Team work
4. Visuals (exploration tools and maps)
5. Queries (word frequency, text search, coding, matrixes and crosstabs, coding comparison)

* Users can use their own data during these sequences.

• Mastery of the basic functions in order to be autonomous with Stata on the following subjects: Descriptive statistics, graphs and first estimates.

4 modules of 3.5 hours each

Stata Deb1 : Meeting the software 

• Presentation of the software environment
• How to set up a Stata session to be efficient
• The general syntax of a Stata command
• How to use the help to become autonomous
• Commented example of a Stata session to understand its possibilities
• Importing data, describing them and visualizing them: a first approach
• A first exercise

Stata Deb2: Working with your data 

• Exploring a data file: the if, by and in conditional
• Manipulating variables: creation, recoding, labels and many other tricks
• Handling data: sorting, deleting, merging, changing format and producing aggregated data
• An exercise to test yourself

Stata Deb3: Descriptive Statistics, Tables and Charts 

• Descriptive statistics
• Synthetic statistical tables
• Univariate analysis
• An introduction to analysis of variance
• Graphs with Stata
• A synthetic exercise

Stata Deb4: An introduction to regression

• Linear regression: estimation, post-estimation, diagnostics and tests
• Logistic regression: estimation, post-estimation, diagnostics and tests
• Discovering programming: loops
• Synthetic exercise (continued)

Learn how to create and analyse Factorial Design of Experiments with Design Expert.

Please contact us if you would prefer to have this training course held in English.

• Discover the R language and software and learn the first basics of this language

R1: First steps in R

• Introduction
• Entering a command in the console
• Writing a clean, structured and commented script
• Create, modify, view and delete an object
• Manipulating different data types and data structures
• The R objects: vectors, factors, arrays, lists, data frames, functions

R2: Import, control and export data arrays

• View and edit working directory
• Import data contained in a .csv file
• Check the types of its variables and modify them if needed
• Categorical variables: factors
• Controlling for missing data
• Exporting a data table to a .csv file

R3: Numerical valuation of data

• Manipulating your dataset (selecting variables, rows …)
• Numerical valuation: getting to know the dataset, summarizing and quantifying the information
• Descriptive statistics, counts, pivot tables
• Data aggregation (statistics by group of observations)

R4: Graphical valuation of data

• Creating basic graphs: histogram, scatterplot, box plot, bar chart, pie chart
• Changing the various basic chart options (color, title, point and line type, size, …)
• Add elements to a chart (points, lines, segments, legends, …)
• Save a graph

• Master more complex machine learning models, in particular ensemble methods based on bagging and boosting techniques, to use and optimize penalty models (lasso and elasticnet), to understand the bootstrap resampling technique for estimation and cross-validation, to know how to implement collaborative filtering techniques.
• At the end of this training, the participant will have a global vision of the different multivariate modeling techniques.

Day 1

• Advanced data mining:
  o DBSCAN, unsupervised data clustering algorithm
  o Manifold Learning

DAY 2

• Gaussian Mixture Modelling (GMM)
• Optimizing penalty models with Lasso and elasticnet (regression, PLS)
• Support Vector Machine (SVM)

DAY 3

• Random Forest and Gradient Boosting Machines
• Bootstraping estimation and cross-validation
• Collaborative filtering and recommendation system

• Understand the basics of machine learning and machine learning on structured data, apply standard dimension reduction and clustering methods, know how to implement a regression model by controlling overfitting and validating model predictions, understand the basics of text mining.
• At the end of this training, the participant will be able to determine the type of techniques to apply based on the questions asked and perform elaborate pre-processing to implement predictive models.

DAY 1

• Introduction to unsupervised methods:
  • Principal component analysis (PCA)
  • Automatic classification (k-means)
  • Association rules (apriori, eclat)
• Introduction to supervised methods:
  • Linear and logistic regression models with regularization (ridge regression)
  • Decision trees (regression and classification)

DAY 2

• Standard methods for implementing predictive models:
  • Feature engineering: learning to reduce the complexity of a problem,
  • Variable selection,
  • Cross-validation,
  • Calibration of a predictive model
  • Text mining and web scraping

• Understand the role of NVivo in the qualitative analysis process.
• Understand and master the NVivo environment.
  • Source management
  • Case management
  • Source coding
  • Crossing matrices
  • Documenting your analysis; memos, annotations and links to.

First half-day

1. Qualitative analysis with NVivo and getting started with the software (1h)

• Reminder of the basic principles of qualitative analysis
• The place of Computer-Assisted Qualitative Data Analysis Software in the research process
• NVIVO’s interface and perspective

2. Preparing a project (1h)

• Preparation of the data, organisation of the software and data importation (textual data in word and pdf – working with images)
• The NVivo mind map: brainstorming as a starting point for coding
• Practical exercises

3. Deductive and inductive coding (2h)

• Practical exercises on textual and image databases
• The different coding logics.
• The relations

Module 1: The special case of audio and video data and transcription (2h)

• The different types of transcription
• Exchange between participants on their good practices
• Tools for efficient transcription
• Demonstration of NVivo transcription
• Importing transcriptions made outside NVIVO

Module 2: Automatic queries (2h)

• Automatic coding of emotions and themes
• Automatic coding based on document structure – working with semi-structured and structured interviews

Module 3: Working with surveys and data tables (2h)

• Importing Excel files

Module 4: Documenting your analyses, your work + Cross-referencing matrices (2h)

• Memos and annotations
• See-also links
• Matrix coding query to explore the links between ideas

Exchange with participants about their NVivo practices and refresh their knowledge

From participant data:
Mastering the NVivo environment.
– Data management
– Case management
– Source coding
– Queries and matrices
– Documenting your analysis; memos, annotations and see-also links.
– Visualisation and export
– Importing and using data from social networks and from internet
– Collaborative work and encoder comparison.

First half-day: Review of the basic principles of qualitative analysis with NVivo (3h)

Exchange with participants on their practices and needs + Refresher course if necessary
The aim of this module is to standardise knowledge of the software and qualitative analysis.
Each participant will be able to present his or her research and questions in preparation for the training

Module 1: Generating and using cases through queries (2h)

• Cases, classifications, attributes and attribute values – what differences in NVivo?
• Importing classifications sheets from Excel
• Organisation of cases and nesting of the different levels

Module 2: Automatic queries and collaborative work (2h)

• Automatic coding of emotions and themes
• Automatic coding based on document structure – working with semi-structured and structured interviews
• Working with several people on an NVivo project
• Encoder comparison

Module 3: Queries: Deepening the understanding of your corpus and its coding (2h)

• Frequency queries and word clouds
• Word search, synapsis and hierarchical top-down classification.
• Matrix coding: exploratory approaches and word overlap
• Crosstab: cross-referencing nodes and features
• Coding queries: answering a research question in a few clicks

Module 4: Documenting analysis, work and visualisations (2h)

• Memos and annotations
• See-also links
• Framework matrices
• Comparison diagrams, clusters, project and concept maps.

Module 5: Working with web data (2h)

• Importing data from Twitter, Facebook and YouTube
• Importing data from websites
• Social network analysis with NVivo

Module 6: Literature review with NVivo (2h)

• Importing scientific documents from (Endnote, Zotéro, Refworks, Mendeley or Citavi)
• Thematic coding of scientific documents

• Deepen the tools to represent and manipulate complex data, effectively use the pandas library, import data sources (CSV, JSON, XML, SQL), perform a simple or multiple linear regression model with the statmodels library, perfect your knowledge of matplotlib and know how to use seaborn or plotly..
• At the end of this training, the participant should be able to import or even merge structured or unstructured data sources, apply advanced processing on quantitative and qualitative data and build elaborate static or dynamic graphs.

DAY 1

• Advanced Data Processing:
  • The numpy library :
    • advanced functions (views, slices)
    • the interface with scipy
  • The pandas library:
    • The import of external data sources,
    • The aggregation of data,
    • The reshaping,
    • Indexing,
    • The merging of data sources
  • The statmodels library:
    • Single and multiple regression,
    • The testing of regression coefficients,
    • The diagnosis of the model,
    • Point and interval prediction
• The processing of strings, regex
• Date processing and time series management

DAY 2

• The generators, itertools, lazy evaluation
• The database interface (SQL, NoSQL)
• The Seaborn package:Advanced graphing features (trellis graphs, statistical distributions, heatmap)
• Interactive graphics with the Bokeh and Plotly packages.

• Understand how data is represented, know how to manipulate simple data structures, master the basics of the numpy and scipy libraries for numerical computation and basic statistical functions, learn the basics of graphical visualization with matplotlib.
• At the end of this training, the participant should be able to write simple analysis scripts working either with artificial data or with data sources that do not require major pre-processing. He/she will know how to implement the main statistical tests for the comparison of two samples and perform basic exploratory graphs.

Day 1

• The working environment: Python 2 and 3.x
• The presentation of the different consoles and debugging in Python:
  • Anaconda
  • Jupyter
  • Spyder
• Data types: lists, dictionaries
• Control structures
• The functions, methods and packages

DAY 2

• Data handling and cleaning:
  • numpy: Basic objects and manipulation of 2-dimensional arrays (array and numeric calculation functions, random number generators)
  • scipy: Basic functionality (scientific functions and basic statistical tests)
  • The probability distributions and univariate statistics.
    • matplotlib: basic features: scatterplot, box plot, histogram
  • Simple scripting

Learn more about the tools used to represent and manipulate complex data, discover the dplyr and data.table packages to optimise data processing, import data sources (CSV, JSON, XML, SQL), create a simple or multiple linear regression model using the {stats} package, improve your knowledge of graphs and know how to use ggplot2 or plotly.

DAY 1

• Importing external data sources with the{base}, {foreign} and {haven} packages

• The tools for optimizing data processing, {data.table} and {dplyr}:
  • Advanced data frame manipulation,
  • Data aggregation,
  • The reshaping,
  • Indexing,
  • The merging of data sources

• The realization of a simple or multiple linear regression model with the {stats} package:
  • The simple and multiple regression,
  • The testing of regression coefficients,
  • The diagnosis of the model,
  • Point and interval prediction

DAY 2

• The processing of strings, regex
• The processing of dates and time series management
• The functional approach and lazy evaluation
• The database interface (SQL, NoSQL)
• The advanced graphical features with the {ggplot2} package:
  • Trellis charts,
  • Statistical distributions,
  • Data presentation with heatmap
• Building elaborate interactive static or dynamic graphs with the {ggvis} and {plotly} packages

• Understand how data is represented, know how to manipulate simple data structures, master basic functions in the {base} and {stats} packages for numerical computation and basic statistical functions, learn the basics of graphical visualization with the basic graphics package {graphics}.
• At the end of this training, the participant should be able to write simple analysis scripts working with either artificial data or data sources that do not require major pre-processing. He/she will know how to implement the main statistical tests for comparing two samples and perform basic exploratory graphs.

DAY 1

• The work environment:
  • Introduction to R 3.x
  • Introduction to RStudio
• The different basic data types (vector, list, data frame), control structures, simple functions
• The basic control structures of R
• The important functions and packages for data manipulation

DAY 2

• The basic features:
  • Simple numeric functions,
  • The random number generators
• The probability distributions and univariate statistics
• Scientific functions {stats} and basic statistical tests
  • Elementary statistical graphical management: scatterplot, box plot, histogram)
• The writing of simple programming scripts with R

Discover all the possibilities offered by PRISM to get the graph you want, automated plotting of fit curves included.

Please contact us if you would like to have this training course held in English.

• Improve your knowledge of the software and discover advanced functions of Stata
  • Declare data in different formats
  • Advanced estimation
  • Programming.

4 modules of 3.5 hours each

Stata Av1 : Advanced data management

• Treatment of alphanumeric variables
• Merging and aggregating data
• Processing of date variables and time series operators
• Advanced management of graphs

Stata Av2 : Programming with Stata

• Local and global macros
• Loops, sums and counters, temporary variables
• Programming to reproduce
• Application examples

Stata Av3: Estimation methods, tests and predictions

• Linear regression with categorical variables and interactions
• Presenting results in a synthetic table and exporting them
• Specification tests and diagnostics
• Extension to other estimation methods

Stata Av4: Introduction to panel data estimation

• Structure and visualize data
• Fixed effects model
• Random effects models
• Some extensions

• Learn to account for different sources of endogeneity in a regression model

3.5 hour module

1. The different sources of endogeneity and the consequences for the properties of estimators
2. Estimation methods
3. Synthetic ordering that allows for these different sources to be considered in a single model
4. Practical exercise

• How to master Lasso (least absolute shrinkage and selection operator) methods with Stata for prediction and/or inference on causal parameters. This regression method (typically used in high-dimensional problems) consists of penalizing the absolute size of the regression coefficients.

Please contact us if you would like to have this training course held in English.

Processing and Analyzing Time Series with Stata.

Please contact us if you would like to have this training course held in English & for the whole program.

Know how to process time series with R.

Please contact us if you would prefer to have this training course held in English.

• Become familiar with three main components of Stata: data management, data analysis, and data visualization.
• Upon completion of the course, you will be able to use Stata efficiently for data management, basic analyses and graphics.
• You will be able to create reproducible analysis, for better collaborative works and simplified follow-up analyses

Fundamentals of Using Stata (1h30 – Day1)

• Keeping organized
• Knowing how Stata treats data
• Using dialog boxes efficiently
• Using the Command window
• Saving time and effort while working
• A sample Stata Session
• Getting Help

Basic Data Management in Stata (3h30 – Day1 and Day2)

• Reading Data in Stata
  o Using and Saving Stata data files
  o Reading in datasets of various standard formats, such as those from spreadsheets or databases
• Labeling data, variables and values and setting up encoded variables
• Creating and Recoding variables in an efficient fashion
• Generating statistics within groups, and working across variables

Intermediate Data Management in Stata (2h – Day2)

• Combining datasets by adding observations and by adding variables
• Reshaping data from wide to long
• Reshaping data from long to wide
• Collapsing data across observations

Workflow (1h30 – Day3)

• Using menus and the Command window to work quickly
• Setting up Stata for your profile
• Keeping complete records of what is done inside Stata: saving dofile
• Creating reproducible analyses, which are completely documented
• Finding, installing, and removing community-contributed extensions to Stata
• Customizing how Stata starts up and where it looks for files

Analysis (3h30 – Day3 and Day 4)

• Using basic statistical commands
• Reusing results of Stata commands
• Using common postestimation commands
• Working with interactions and factor variables

Graphics (2h – Day 4)

• Introduction to graphics
• Overview of graph two-way plots
• Building up complex graphs
• Using the Graph Editor

Addressing the Agile mindset and concepts.

1. Why move to Agile ?
2. Introduction to Agile
3. The vocabulary of Agile
4. The principles of Scrum

Understand the Design Thinking process in order to use it to innovate and solve complex problems.

1. Discover: discover the challenge
2. Define: define precisely the problem to be solved
3. Develop: imagine the most relevant solution
4. Deliver: build the solution and collect feedbacks according to an iterative approach

• Understand high-throughput genomic sequencing
• Be able to choose the appropriate technology for your project
• Know the bioinformatics tools used
• Know the possible statistical analyses

Please contact us if you would like to have this training course held in English.

Discover all the possibilities offered by PRISM to get the graph you want, automated plotting of fit curves included.

Please contact us if you would like to have this training course held in English.

Knowing how to manipulate data and extract information from it with R.

Please contact us if you would like to have this training course held in English.

Understand the data science ecosystem and know the tools related to the realization of a data science project.

DAY 1

• The unix environment, interacting with a shell, open source tools (sed, awk, grep, jq, csvkit, etc.), R and Python, SQL and NoSQL
• Revision control and collaborative work with Git
• The methodology for managing a data science project
• Software engineering fundamentals and best practices

DAY 2

• Information gathering and processing (experimental designs and clinical trials, surveys and polls, web data, open data)
• Distributed architecture and database, map-reduce, big data, Apache Spark

• Discover the R language and software and learn the first basics of this language

R1: First steps in R

• Introduction
• Entering a command in the console
• Writing a clean, structured and commented script
• Create, modify, view and delete an object
• Manipulating different data types and data structures
• The R objects: vectors, factors, arrays, lists, data frames, functions

R2: Import, control and export data arrays

• View and edit working directory
• Import data contained in a .csv file
• Check the types of its variables and modify them if needed
• Categorical variables: factors
• Controlling for missing data
• Exporting a data table to a .csv file

R3: Numerical valuation of data

• Manipulating your dataset (selecting variables, rows …)
• Numerical valuation: getting to know the dataset, summarizing and quantifying the information
• Descriptive statistics, counts, pivot tables
• Data aggregation (statistics by group of observations)

R4: Graphical valuation of data

• Creating basic graphs: histogram, scatterplot, box plot, bar chart, pie chart
• Changing the various basic chart options (color, title, point and line type, size, …)
• Add elements to a chart (points, lines, segments, legends, …)
• Save a graph

• Master more complex machine learning models, in particular ensemble methods based on bagging and boosting techniques, to use and optimize penalty models (lasso and elasticnet), to understand the bootstrap resampling technique for estimation and cross-validation, to know how to implement collaborative filtering techniques.
• At the end of this training, the participant will have a global vision of the different multivariate modeling techniques.

Day 1

• Advanced data mining:
  o DBSCAN, unsupervised data clustering algorithm
  o Manifold Learning

DAY 2

• Gaussian Mixture Modelling (GMM)
• Optimizing penalty models with Lasso and elasticnet (regression, PLS)
• Support Vector Machine (SVM)

DAY 3

• Random Forest and Gradient Boosting Machines
• Bootstraping estimation and cross-validation
• Collaborative filtering and recommendation system

• Understand the basics of machine learning and machine learning on structured data, apply standard dimension reduction and clustering methods, know how to implement a regression model by controlling overfitting and validating model predictions, understand the basics of text mining.
• At the end of this training, the participant will be able to determine the type of techniques to apply based on the questions asked and perform elaborate pre-processing to implement predictive models.

DAY 1

• Introduction to unsupervised methods:
  • Principal component analysis (PCA)
  • Automatic classification (k-means)
  • Association rules (apriori, eclat)
• Introduction to supervised methods:
  • Linear and logistic regression models with regularization (ridge regression)
  • Decision trees (regression and classification)

DAY 2

• Standard methods for implementing predictive models:
  • Feature engineering: learning to reduce the complexity of a problem,
  • Variable selection,
  • Cross-validation,
  • Calibration of a predictive model
  • Text mining and web scraping

• Deepen the tools to represent and manipulate complex data, effectively use the pandas library, import data sources (CSV, JSON, XML, SQL), perform a simple or multiple linear regression model with the statmodels library, perfect your knowledge of matplotlib and know how to use seaborn or plotly..
• At the end of this training, the participant should be able to import or even merge structured or unstructured data sources, apply advanced processing on quantitative and qualitative data and build elaborate static or dynamic graphs.

DAY 1

• Advanced Data Processing:
  • The numpy library :
    • advanced functions (views, slices)
    • the interface with scipy
  • The pandas library:
    • The import of external data sources,
    • The aggregation of data,
    • The reshaping,
    • Indexing,
    • The merging of data sources
  • The statmodels library:
    • Single and multiple regression,
    • The testing of regression coefficients,
    • The diagnosis of the model,
    • Point and interval prediction
• The processing of strings, regex
• Date processing and time series management

DAY 2

• The generators, itertools, lazy evaluation
• The database interface (SQL, NoSQL)
• The Seaborn package:Advanced graphing features (trellis graphs, statistical distributions, heatmap)
• Interactive graphics with the Bokeh and Plotly packages.

• Understand how data is represented, know how to manipulate simple data structures, master the basics of the numpy and scipy libraries for numerical computation and basic statistical functions, learn the basics of graphical visualization with matplotlib.
• At the end of this training, the participant should be able to write simple analysis scripts working either with artificial data or with data sources that do not require major pre-processing. He/she will know how to implement the main statistical tests for the comparison of two samples and perform basic exploratory graphs.

Day 1

• The working environment: Python 2 and 3.x
• The presentation of the different consoles and debugging in Python:
  • Anaconda
  • Jupyter
  • Spyder
• Data types: lists, dictionaries
• Control structures
• The functions, methods and packages

DAY 2

• Data handling and cleaning:
  • numpy: Basic objects and manipulation of 2-dimensional arrays (array and numeric calculation functions, random number generators)
  • scipy: Basic functionality (scientific functions and basic statistical tests)
  • The probability distributions and univariate statistics.
    • matplotlib: basic features: scatterplot, box plot, histogram
  • Simple scripting

Learn more about the tools used to represent and manipulate complex data, discover the dplyr and data.table packages to optimise data processing, import data sources (CSV, JSON, XML, SQL), create a simple or multiple linear regression model using the {stats} package, improve your knowledge of graphs and know how to use ggplot2 or plotly.

DAY 1

• Importing external data sources with the{base}, {foreign} and {haven} packages

• The tools for optimizing data processing, {data.table} and {dplyr}:
  • Advanced data frame manipulation,
  • Data aggregation,
  • The reshaping,
  • Indexing,
  • The merging of data sources

• The realization of a simple or multiple linear regression model with the {stats} package:
  • The simple and multiple regression,
  • The testing of regression coefficients,
  • The diagnosis of the model,
  • Point and interval prediction

DAY 2

• The processing of strings, regex
• The processing of dates and time series management
• The functional approach and lazy evaluation
• The database interface (SQL, NoSQL)
• The advanced graphical features with the {ggplot2} package:
  • Trellis charts,
  • Statistical distributions,
  • Data presentation with heatmap
• Building elaborate interactive static or dynamic graphs with the {ggvis} and {plotly} packages

• Understand how data is represented, know how to manipulate simple data structures, master basic functions in the {base} and {stats} packages for numerical computation and basic statistical functions, learn the basics of graphical visualization with the basic graphics package {graphics}.
• At the end of this training, the participant should be able to write simple analysis scripts working with either artificial data or data sources that do not require major pre-processing. He/she will know how to implement the main statistical tests for comparing two samples and perform basic exploratory graphs.

DAY 1

• The work environment:
  • Introduction to R 3.x
  • Introduction to RStudio
• The different basic data types (vector, list, data frame), control structures, simple functions
• The basic control structures of R
• The important functions and packages for data manipulation

DAY 2

• The basic features:
  • Simple numeric functions,
  • The random number generators
• The probability distributions and univariate statistics
• Scientific functions {stats} and basic statistical tests
  • Elementary statistical graphical management: scatterplot, box plot, histogram)
• The writing of simple programming scripts with R

• Learn to account for different sources of endogeneity in a regression model

3.5 hour module

1. The different sources of endogeneity and the consequences for the properties of estimators
2. Estimation methods
3. Synthetic ordering that allows for these different sources to be considered in a single model
4. Practical exercise

Processing and Analyzing Time Series with Stata.

Please contact us if you would like to have this training course held in English & for the whole program.

Know how to process time series with R.

Please contact us if you would prefer to have this training course held in English.

• Become familiar with three main components of Stata: data management, data analysis, and data visualization.
• Upon completion of the course, you will be able to use Stata efficiently for data management, basic analyses and graphics.
• You will be able to create reproducible analysis, for better collaborative works and simplified follow-up analyses

Fundamentals of Using Stata (1h30 – Day1)

• Keeping organized
• Knowing how Stata treats data
• Using dialog boxes efficiently
• Using the Command window
• Saving time and effort while working
• A sample Stata Session
• Getting Help

Basic Data Management in Stata (3h30 – Day1 and Day2)

• Reading Data in Stata
  o Using and Saving Stata data files
  o Reading in datasets of various standard formats, such as those from spreadsheets or databases
• Labeling data, variables and values and setting up encoded variables
• Creating and Recoding variables in an efficient fashion
• Generating statistics within groups, and working across variables

Intermediate Data Management in Stata (2h – Day2)

• Combining datasets by adding observations and by adding variables
• Reshaping data from wide to long
• Reshaping data from long to wide
• Collapsing data across observations

Workflow (1h30 – Day3)

• Using menus and the Command window to work quickly
• Setting up Stata for your profile
• Keeping complete records of what is done inside Stata: saving dofile
• Creating reproducible analyses, which are completely documented
• Finding, installing, and removing community-contributed extensions to Stata
• Customizing how Stata starts up and where it looks for files

Analysis (3h30 – Day3 and Day 4)

• Using basic statistical commands
• Reusing results of Stata commands
• Using common postestimation commands
• Working with interactions and factor variables

Graphics (2h – Day 4)

• Introduction to graphics
• Overview of graph two-way plots
• Building up complex graphs
• Using the Graph Editor

• Mastery of the basic functions in order to be autonomous with Stata on the following subjects: Descriptive statistics, graphs and first estimates.

4 modules of 3.5 hours each

Stata Deb1 : Meeting the software 

• Presentation of the software environment
• How to set up a Stata session to be efficient
• The general syntax of a Stata command
• How to use the help to become autonomous
• Commented example of a Stata session to understand its possibilities
• Importing data, describing them and visualizing them: a first approach
• A first exercise

Stata Deb2: Working with your data 

• Exploring a data file: the if, by and in conditional
• Manipulating variables: creation, recoding, labels and many other tricks
• Handling data: sorting, deleting, merging, changing format and producing aggregated data
• An exercise to test yourself

Stata Deb3: Descriptive Statistics, Tables and Charts 

• Descriptive statistics
• Synthetic statistical tables
• Univariate analysis
• An introduction to analysis of variance
• Graphs with Stata
• A synthetic exercise

Stata Deb4: An introduction to regression

• Linear regression: estimation, post-estimation, diagnostics and tests
• Logistic regression: estimation, post-estimation, diagnostics and tests
• Discovering programming: loops
• Synthetic exercise (continued)

Processing and Analyzing Time Series with Stata.

Please contact us if you would like to have this training course held in English & for the whole program.

Understand the data science ecosystem and know the tools related to the realization of a data science project.

DAY 1

• The unix environment, interacting with a shell, open source tools (sed, awk, grep, jq, csvkit, etc.), R and Python, SQL and NoSQL
• Revision control and collaborative work with Git
• The methodology for managing a data science project
• Software engineering fundamentals and best practices

DAY 2

• Information gathering and processing (experimental designs and clinical trials, surveys and polls, web data, open data)
• Distributed architecture and database, map-reduce, big data, Apache Spark

Learn how to create and analyse Factorial Design of Experiments with Design Expert.

Please contact us if you would prefer to have this training course held in English.

Addressing the Agile mindset and concepts.

1. Why move to Agile ?
2. Introduction to Agile
3. The vocabulary of Agile
4. The principles of Scrum

Learn how to create and analyse Factorial Design of Experiments with Design Expert.

Please contact us if you would prefer to have this training course held in English.

• Understand high-throughput genomic sequencing
• Be able to choose the appropriate technology for your project
• Know the bioinformatics tools used
• Know the possible statistical analyses

Please contact us if you would like to have this training course held in English.

Understand the Design Thinking process in order to use it to innovate and solve complex problems.

1. Discover: discover the challenge
2. Define: define precisely the problem to be solved
3. Develop: imagine the most relevant solution
4. Deliver: build the solution and collect feedbacks according to an iterative approach

Knowing how to manipulate data and extract information from it with R.

Please contact us if you would like to have this training course held in English.

Understand the data science ecosystem and know the tools related to the realization of a data science project.

DAY 1

• The unix environment, interacting with a shell, open source tools (sed, awk, grep, jq, csvkit, etc.), R and Python, SQL and NoSQL
• Revision control and collaborative work with Git
• The methodology for managing a data science project
• Software engineering fundamentals and best practices

DAY 2

• Information gathering and processing (experimental designs and clinical trials, surveys and polls, web data, open data)
• Distributed architecture and database, map-reduce, big data, Apache Spark

• Discover the R language and software and learn the first basics of this language

R1: First steps in R

• Introduction
• Entering a command in the console
• Writing a clean, structured and commented script
• Create, modify, view and delete an object
• Manipulating different data types and data structures
• The R objects: vectors, factors, arrays, lists, data frames, functions

R2: Import, control and export data arrays

• View and edit working directory
• Import data contained in a .csv file
• Check the types of its variables and modify them if needed
• Categorical variables: factors
• Controlling for missing data
• Exporting a data table to a .csv file

R3: Numerical valuation of data

• Manipulating your dataset (selecting variables, rows …)
• Numerical valuation: getting to know the dataset, summarizing and quantifying the information
• Descriptive statistics, counts, pivot tables
• Data aggregation (statistics by group of observations)

R4: Graphical valuation of data

• Creating basic graphs: histogram, scatterplot, box plot, bar chart, pie chart
• Changing the various basic chart options (color, title, point and line type, size, …)
• Add elements to a chart (points, lines, segments, legends, …)
• Save a graph

• Master more complex machine learning models, in particular ensemble methods based on bagging and boosting techniques, to use and optimize penalty models (lasso and elasticnet), to understand the bootstrap resampling technique for estimation and cross-validation, to know how to implement collaborative filtering techniques.
• At the end of this training, the participant will have a global vision of the different multivariate modeling techniques.

Day 1

• Advanced data mining:
  o DBSCAN, unsupervised data clustering algorithm
  o Manifold Learning

DAY 2

• Gaussian Mixture Modelling (GMM)
• Optimizing penalty models with Lasso and elasticnet (regression, PLS)
• Support Vector Machine (SVM)

DAY 3

• Random Forest and Gradient Boosting Machines
• Bootstraping estimation and cross-validation
• Collaborative filtering and recommendation system

• Understand the basics of machine learning and machine learning on structured data, apply standard dimension reduction and clustering methods, know how to implement a regression model by controlling overfitting and validating model predictions, understand the basics of text mining.
• At the end of this training, the participant will be able to determine the type of techniques to apply based on the questions asked and perform elaborate pre-processing to implement predictive models.

DAY 1

• Introduction to unsupervised methods:
  • Principal component analysis (PCA)
  • Automatic classification (k-means)
  • Association rules (apriori, eclat)
• Introduction to supervised methods:
  • Linear and logistic regression models with regularization (ridge regression)
  • Decision trees (regression and classification)

DAY 2

• Standard methods for implementing predictive models:
  • Feature engineering: learning to reduce the complexity of a problem,
  • Variable selection,
  • Cross-validation,
  • Calibration of a predictive model
  • Text mining and web scraping

• Deepen the tools to represent and manipulate complex data, effectively use the pandas library, import data sources (CSV, JSON, XML, SQL), perform a simple or multiple linear regression model with the statmodels library, perfect your knowledge of matplotlib and know how to use seaborn or plotly..
• At the end of this training, the participant should be able to import or even merge structured or unstructured data sources, apply advanced processing on quantitative and qualitative data and build elaborate static or dynamic graphs.

DAY 1

• Advanced Data Processing:
  • The numpy library :
    • advanced functions (views, slices)
    • the interface with scipy
  • The pandas library:
    • The import of external data sources,
    • The aggregation of data,
    • The reshaping,
    • Indexing,
    • The merging of data sources
  • The statmodels library:
    • Single and multiple regression,
    • The testing of regression coefficients,
    • The diagnosis of the model,
    • Point and interval prediction
• The processing of strings, regex
• Date processing and time series management

DAY 2

• The generators, itertools, lazy evaluation
• The database interface (SQL, NoSQL)
• The Seaborn package:Advanced graphing features (trellis graphs, statistical distributions, heatmap)
• Interactive graphics with the Bokeh and Plotly packages.

• Understand how data is represented, know how to manipulate simple data structures, master the basics of the numpy and scipy libraries for numerical computation and basic statistical functions, learn the basics of graphical visualization with matplotlib.
• At the end of this training, the participant should be able to write simple analysis scripts working either with artificial data or with data sources that do not require major pre-processing. He/she will know how to implement the main statistical tests for the comparison of two samples and perform basic exploratory graphs.

Day 1

• The working environment: Python 2 and 3.x
• The presentation of the different consoles and debugging in Python:
  • Anaconda
  • Jupyter
  • Spyder
• Data types: lists, dictionaries
• Control structures
• The functions, methods and packages

DAY 2

• Data handling and cleaning:
  • numpy: Basic objects and manipulation of 2-dimensional arrays (array and numeric calculation functions, random number generators)
  • scipy: Basic functionality (scientific functions and basic statistical tests)
  • The probability distributions and univariate statistics.
    • matplotlib: basic features: scatterplot, box plot, histogram
  • Simple scripting

Learn more about the tools used to represent and manipulate complex data, discover the dplyr and data.table packages to optimise data processing, import data sources (CSV, JSON, XML, SQL), create a simple or multiple linear regression model using the {stats} package, improve your knowledge of graphs and know how to use ggplot2 or plotly.

DAY 1

• Importing external data sources with the{base}, {foreign} and {haven} packages

• The tools for optimizing data processing, {data.table} and {dplyr}:
  • Advanced data frame manipulation,
  • Data aggregation,
  • The reshaping,
  • Indexing,
  • The merging of data sources

• The realization of a simple or multiple linear regression model with the {stats} package:
  • The simple and multiple regression,
  • The testing of regression coefficients,
  • The diagnosis of the model,
  • Point and interval prediction

DAY 2

• The processing of strings, regex
• The processing of dates and time series management
• The functional approach and lazy evaluation
• The database interface (SQL, NoSQL)
• The advanced graphical features with the {ggplot2} package:
  • Trellis charts,
  • Statistical distributions,
  • Data presentation with heatmap
• Building elaborate interactive static or dynamic graphs with the {ggvis} and {plotly} packages

• Understand how data is represented, know how to manipulate simple data structures, master basic functions in the {base} and {stats} packages for numerical computation and basic statistical functions, learn the basics of graphical visualization with the basic graphics package {graphics}.
• At the end of this training, the participant should be able to write simple analysis scripts working with either artificial data or data sources that do not require major pre-processing. He/she will know how to implement the main statistical tests for comparing two samples and perform basic exploratory graphs.

DAY 1

• The work environment:
  • Introduction to R 3.x
  • Introduction to RStudio
• The different basic data types (vector, list, data frame), control structures, simple functions
• The basic control structures of R
• The important functions and packages for data manipulation

DAY 2

• The basic features:
  • Simple numeric functions,
  • The random number generators
• The probability distributions and univariate statistics
• Scientific functions {stats} and basic statistical tests
  • Elementary statistical graphical management: scatterplot, box plot, histogram)
• The writing of simple programming scripts with R

Know how to process time series with R.

Please contact us if you would prefer to have this training course held in English.

• Creating your Citavi project
• Organize and manage your references with Citavi
• Feed its database with new references through different exports: DOI, PDF, websites, etc.
• Cite its bibliographic references with Citavi and publish documents with Word, articles containing bibliographic references
• Exchanging and sharing references and citations from consulted sources

1. Introduction to Citavi: Theoretical Presentation (30 min.)
2. First Steps with Citavi: Discovering the interface and working on a project (creating, opening, saving), Teamwork with Citavi: applied exercises (1h30)
3. Managing the project: Adding references (manually, automatically), searching and inserting references (from Citavi, from the Internet, with the Picker): practical exercises with importing different document formats; browsing the Internet for new documents (1h30)
4. Organizing and planning: Structuring and sorting references (classification, filter, table), searching the project (in references and full text), editing references (fields, linked documents, keywords, evaluation), planning work (tasks). Presentation and practical exercises, case studies (1h)
5. Organizing the elements of knowledge: Using the Knowledge Organizer, Working on PDF (annotations), Adding personal reflections to the project (Thoughts), Linking an article with its review. Practical exercises (1h30)
6. Using the project: Using citation styles, exporting references (via clipboard, text file, spreadsheet, email), Creating a project bibliography, Writing documents with Word. Theoretical presentation and practical applications (1h)

• Creating your bibliographic database
• Organize and manage your references with EndNote
• Feed your database with new references through various exports: DOI, PDF, websites,…
• Cite your bibliographic references with EndNote and publish documents with Microsoft Word, articles containing bibliographic references
• Exchange and share your references

Please contact us if you would like to have this training course held in English.

• Succeed in the implementation of scientific, technical and technological monitoring for a project.
• Know the watch cycle and organize your monitoring plan.
• Organize the different stages of the monitoring concretely

Please contact us if you would like to have this training course held in English.

This course is designed for scientific researchers and anyone working in scientific communication. It will provide trainees with the means and journalistic techniques, both written and oral, to simplify their complex messages with the help of metaphors that are easier to understand and prevents from using the dry language of experts.

In a nutshell: how to formulate dynamic headlines, how to synthesize and simplify these messages, and how to popularize them so that they can be understood by the greatest number of people.

• Be able to speak in English with confidence in front of a scientific audience
• Know how to use your body (breathing, stance, posture, gestures) to pace your speech
• Know how to project yourself into the space and attract the attention of the audience by giving authority to your speech
  Identify one’s weak and strong points with the help of other participants
• Know how to summarize information to make it more dynamic
• Know how to use your presentation as a springboard to express yourself, not a crutch
• Prepare an argument to back up your speech and answer questions quickly
• Be more fluid in English and handle questions.
Scientific communication and writing Short courses On-site courses Face-to-face English

• Succeed in the implementation of scientific, technical and technological monitoring for a project.
• Know the watch cycle and organize your monitoring plan.
• Organize the different stages of the monitoring concretely

Please contact us if you would like to have this training course held in English.

Understand and know how to use the Anglo-Saxon approach to writing scientific articles. Apply what you learn in the field to your own work. Understand the importance of the reader and therefore of the clarity and precision of your message. Understand that you need to think in the language in which you are writing to make it more comprehensible. Know how to make better use of grammar and syntax in your writing to make it clearer. Master the structure of the article and therefore structure your speech better. Have a framework and a toolbox that can be reused for other articles.

Knowing how to manipulate data and extract information from it with R.

Please contact us if you would like to have this training course held in English.

• Mastery of the basic functions in order to be autonomous with Stata on the following subjects: Descriptive statistics, graphs and first estimates.

4 modules of 3.5 hours each

Stata Deb1 : Meeting the software 

• Presentation of the software environment
• How to set up a Stata session to be efficient
• The general syntax of a Stata command
• How to use the help to become autonomous
• Commented example of a Stata session to understand its possibilities
• Importing data, describing them and visualizing them: a first approach
• A first exercise

Stata Deb2: Working with your data 

• Exploring a data file: the if, by and in conditional
• Manipulating variables: creation, recoding, labels and many other tricks
• Handling data: sorting, deleting, merging, changing format and producing aggregated data
• An exercise to test yourself

Stata Deb3: Descriptive Statistics, Tables and Charts 

• Descriptive statistics
• Synthetic statistical tables
• Univariate analysis
• An introduction to analysis of variance
• Graphs with Stata
• A synthetic exercise

Stata Deb4: An introduction to regression

• Linear regression: estimation, post-estimation, diagnostics and tests
• Logistic regression: estimation, post-estimation, diagnostics and tests
• Discovering programming: loops
• Synthetic exercise (continued)

Learn how to create and analyse Factorial Design of Experiments with Design Expert.

Please contact us if you would prefer to have this training course held in English.

• Improve your knowledge of the software and discover advanced functions of Stata
  • Declare data in different formats
  • Advanced estimation
  • Programming.

4 modules of 3.5 hours each

Stata Av1 : Advanced data management

• Treatment of alphanumeric variables
• Merging and aggregating data
• Processing of date variables and time series operators
• Advanced management of graphs

Stata Av2 : Programming with Stata

• Local and global macros
• Loops, sums and counters, temporary variables
• Programming to reproduce
• Application examples

Stata Av3: Estimation methods, tests and predictions

• Linear regression with categorical variables and interactions
• Presenting results in a synthetic table and exporting them
• Specification tests and diagnostics
• Extension to other estimation methods

Stata Av4: Introduction to panel data estimation

• Structure and visualize data
• Fixed effects model
• Random effects models
• Some extensions

• Learn to account for different sources of endogeneity in a regression model

3.5 hour module

1. The different sources of endogeneity and the consequences for the properties of estimators
2. Estimation methods
3. Synthetic ordering that allows for these different sources to be considered in a single model
4. Practical exercise

• How to master Lasso (least absolute shrinkage and selection operator) methods with Stata for prediction and/or inference on causal parameters. This regression method (typically used in high-dimensional problems) consists of penalizing the absolute size of the regression coefficients.

Please contact us if you would like to have this training course held in English.

Processing and Analyzing Time Series with Stata.

Please contact us if you would like to have this training course held in English & for the whole program.

• Become familiar with three main components of Stata: data management, data analysis, and data visualization.
• Upon completion of the course, you will be able to use Stata efficiently for data management, basic analyses and graphics.
• You will be able to create reproducible analysis, for better collaborative works and simplified follow-up analyses

Fundamentals of Using Stata (1h30 – Day1)

• Keeping organized
• Knowing how Stata treats data
• Using dialog boxes efficiently
• Using the Command window
• Saving time and effort while working
• A sample Stata Session
• Getting Help

Basic Data Management in Stata (3h30 – Day1 and Day2)

• Reading Data in Stata
  o Using and Saving Stata data files
  o Reading in datasets of various standard formats, such as those from spreadsheets or databases
• Labeling data, variables and values and setting up encoded variables
• Creating and Recoding variables in an efficient fashion
• Generating statistics within groups, and working across variables

Intermediate Data Management in Stata (2h – Day2)

• Combining datasets by adding observations and by adding variables
• Reshaping data from wide to long
• Reshaping data from long to wide
• Collapsing data across observations

Workflow (1h30 – Day3)

• Using menus and the Command window to work quickly
• Setting up Stata for your profile
• Keeping complete records of what is done inside Stata: saving dofile
• Creating reproducible analyses, which are completely documented
• Finding, installing, and removing community-contributed extensions to Stata
• Customizing how Stata starts up and where it looks for files

Analysis (3h30 – Day3 and Day 4)

• Using basic statistical commands
• Reusing results of Stata commands
• Using common postestimation commands
• Working with interactions and factor variables

Graphics (2h – Day 4)

• Introduction to graphics
• Overview of graph two-way plots
• Building up complex graphs
• Using the Graph Editor