Visão Geral

Após realizar este Curso R Statistical Analysis with Rlang, você será capaz de:

• A linguagem e sintaxe de programação R
• Programação orientada a objetos em R
• Como realizar uma série de análises usando R
• Como usar R para resumo gráfico
• Soluções personalizadas usando R

Objetivo

Curso R Statistical Analysis with Rlang, dará a você uma base sólida na criação de soluções de análise estatística usando a linguagem R (Rlang) e como realizar uma variedade de processos analíticos comumente usados. Você também aprenderá como produzir gráficos de qualidade para acompanhar sua pesquisa analítica.

R é uma linguagem de programação projetada expressamente para fornecer um ambiente de programação estatística que inclui amplos recursos gráficos.

Ele se tornou rapidamente o padrão de fato para analistas em muitas disciplinas.

Se você é novo em programação, mas tem uma mente analítica e cabeça para estatísticas, nós o ajudamos a aprender rapidamente os fundamentos das soluções de codificação manual usando o R Studio.

Publico Alvo

Analistas, cientistas de dados e desenvolvedores de software que desejam explorar a vasta gama de recursos analíticos e gráficos de R.

Materiais

Conteúdo Programatico

Introduction to R

1. Overview of the R environment
2. Getting help
3. Simple maths

Data in R

1. Loading and saving data
2. Types of R object
3. Making R data objects
4. Cross tabulation
5. Working with data objects

Statistical analyses using R

1. Describing data
2. Data distribution and sampling
3. Basic hypothesis testing
4. Advanced analyses – ANOVA and regression

Using R for graphical summary

1. Producing graphs using R
2. Customising graphs
3. Adding lines, points, symbols and text to graphs
4. Working with colour
5. Exporting graphs

Custom solutions using R

1. Custom functions
2. Writing and saving scripts
3. Object classes
4. Loops and conditional statements
5. Making the most of results
6. Developing custom R solutions

The following modules are suggestions for custom training programmes, which can be tailored to your team's requirements.

Framework R Course modules

You can split the R course into modules that can be taken ad hoc but with a coherent syllabus - each of the following modules can be arranged to be delivered in a day - or split over half days to fit in with your team's needs.

1. Foundation: introduction to data and graphics.
2. Statistical Hypothesis Testing: basic stats tests.
3. Advanced Graphics: professional quality graphics.
4. Unsupervised Machine Learning: cluster analysis.
5. Supervised Machine Learning: regression analysis.
6. Visual data exploration: advanced graphical methods for exploring data.
7. R Programming Tools: unlock the potential of R.
8. Using the Tidyverse: tools for data scientists.
9. RMarkdown: integrate R results and graphics into documents.

F01 BEGINNING R (FOUNDATION)

Suitable for complete beginners. A one-day foundation to using R: the statistical programming language. You’ll gain various skills, including:

1. Importing Data.
2. Handling Data.
3. Data Summary and Aggregation.
4. Visualising Data.

No previous experience of statistics, graphics or computer languages is needed.

F02 STATISTICAL HYPOTHESIS TESTING WITH R

An introduction to the basics of hypothesis testing using R. This one-day module assumes some knowledge of R but experience of statistical analysis is not necessary.

1. Data distribution.
2. Tests for differences in samples.
3. Tests for correlation.
4. Tests of association.
5. Analysis of Variance.
6. Introduction to regression.
7. Visualising and reporting results.

F03 ADVANCED GRAPHICS

This one-day module builds on the foundation and extends your skills in graphical presentation. The module focusses on the skills you need to create professional quality graphics, such as:

1. Adding text to plots.
2. Legends.
3. Adding lines and curves to plots.
4. Special characters, e.g. superscript, maths symbols.
5. Using colour.
6. Exporting graphics.

Some knowledge of the graphical functions of R is required, our foundation module would be ideal preparation.

F04 UNSUPERVISED MACHINE LEARNING

Unsupervised machine learning is a collective term for methods of data analysis that seek to find and identify clusters in your data. This one-day module will give you the skills you need to carry out a range of analytical methods including:

1. Similarity & dissimilarity.
2. Hierarchical cluster analysis.
3. K-means analysis.
4. Multivariate analysis (ordination).

Some prior knowledge of R is required but you don’t need any experience of cluster analysis or statistics.

F05 SUPERVISED MACHINE LEARNING

Supervised machine learning is a general term for methods of predictive data analysis. The most commonly used method of machine learning is regression. In this one-day module you’ll learn a range of regression modelling skills including:

1. Regression model building.
2. Curvilinear regression.
3. Best-fit lines.
4. Confidence Intervals.
5. Model building.
6. Generalised linear modelling (GLM) for non-Gaussian data.

Some prior knowledge of R is required but no especial knowledge or experience of statistics or regression are necessary.

F06 VISUAL DATA EXPLORATION

This module focusses on graphical methods of data exploration and covers some advanced graphical techniques.

1. Graphs of data distribution.
2. Graphs highlighting sample differences.
3. Graphs highlighting relationships.
4. Graphs of compositional data.
5. Multivariate plots.

Some previous knowledge of R is assumed; our foundation module would be ideal preparation.

F07 R PROGRAMMING TOOLS

This module explores the flexibility of R by exploring the programming tools that allow you to create your own custom routines.

1. R Scripts.
2. Function parameters.
3. Function results.
4. User Intervention.
5. Conditional expressions.
6. Error Trapping.
7. Argument matching.
8. Loops.
9. Custom class results.

Some previous experience of using R is needed for this module, our foundation module would be ideal preparation.

F08 USING THE TIDYVERSE

The Tidyverse is a popular suite of R packages designed to help the data scientist. This module provides an introduction and overview to the tools available in the Tidyverse including:

1. Importing data with readr.
2. Cleaning data with tidyr.
3. Manipulating data with dplyr.
4. Graphics with ggplot2.

Some previous experience of using R is essential, our foundation module would be ideal preparation.

F09 RMARKDOWN

Markdown is a popular way to encode text and graphics into HTML, PDF and other document formats. RMarkdown integrates the power and flexibility of R with Markdown. This allows you to carry out data analytics using R and integrate the results into reports and documents. This module covers a range of topics, including:

1. Markdown syntax.
2. Integrating R.
3. HTML documents.
4. Word documents.
5. PDF documents.
6. Slide presentations.

Some knowledge of using R is essential here, although you don’t need to be an advanced user to use RMarkdown. No previous experience of HTML or “regular” markdown is required.