Authors' Quotes
“As the United States continues to struggle with containing COVID-19, one challenge is the continued lack of data from widespread testing that is so critical for tracking disease incidence and prevalence. Another challenge, arguably more serious, is the politicization of a public health crisis, which has led some to distrust basic scientific facts and data. Our book is about the application of statistics and data to detect and mitigate disease outbreaks. It is about how science can be used to successfully solve complex problems like this coronavirus pandemic. In our complex and interconnected world, we need good science supported by trustworthy data now more than ever.” - Ron Fricker, Monitoring the Health of Populations by Tracking Disease Outbreaks
"Computational reproducibility and literate programming are hallmarks of trustworthy data analysis. R Markdown is a powerful tool to combine code and narrative into a rigorous, well-documented file, book, blog, or more. As the R Markdown ecosystem has grown, even the most experienced users may struggle to keep up with all of the latest tips and tricks for efficient programming, elegant formatting, and effective customization. This cookbook demonstrates how to fine-tune R Markdown for your data analysis needs through succinct but tangible real-world examples." - Yihui Xie, R Markdown Cookbook
“Statistics the only means we have to make sense of randomness in our world, extracting patterns and important information from indiscriminate data. As statisticians and data scientists it is our obligation to present and analyse the data as clearly as possible, so that any systematic evidence becomes obvious and irrefutable.” - Dirk Kroese, Data Science and Machine Learning
“COVID-19 has shown us that it’s more critical than ever for governments to make wise use of data, tools and evidence to make useful decisions. That requires that the analysis can be trusted and verified, while at the same time protecting individual privacy. Our book provides a framework to help decision-makers and scientists make those tradeoffs”. - Julia Lane, Big Data and Social Science
“The perspective of social scientists is critical to understanding some of the most pressing contemporary issues on the intersection of government, society and
technology. Resources such as “R for Political Data Science” can help social science scholars, students and practitioners to acquire an understanding of data science from a practical standpoint, giving new edges to their analyses and boosting novel interdisciplinary collaborations.” - Francisco Urdinez and Andrés Cruz, R for Political Data Science
“The very nature of social events often remains opaque, despite all the news reports, graphs and data tables we might be presented with. These sources of information represent only a summary of some imperfect data, perhaps reflecting many different but equally reasonable views about what the events are, where they occur, whom they impact and how they operate. Understanding social events through data starts by asking questions about the evidence we have and its limitations. Those questions might include where the data is from and how it has been collected." - André Python, Debunking Seven Terrorism Myths Using Statistics
“Trustable data can only come from transparent data. Collection methods and instruments,
data assumptions, pre-processing, etc all affect the data. That is why, whether those data concern a pandemic, a business, or an election, knowing how they came to be is a prerequisite to understanding what they mean.” - Ole Forsberg, Understanding Elections through Statistics
“The range of possible questions that may be answered by Data Science is going to grow, thanks to the availability of large sets of data and to the increasing computational power. As a matter of fact, from a methodological point of view, the huge amount of raw data available on the actions and strategies in basketball, combined with the absence of a sound theory explaining the relationships between the many involved variables, make these questions challenging for Data Scientists." - Paola Zuccolotto and Marica Manisera, Basketball Data Science
“Trustworthy statistical results have to report accurately the phenomena under study, accounting for their meaning in an understandable way. This is not easy when facing the question “what is important in life” posed in a survey. Without a doubt, free-text answers have to be collected. To deal with this type of data, tools working out the results with objectivity have to be developed. Presenting these tools, both the statistical methods and the package that implements them, is the subject m book. The methodology also makes it possible tosimultaneously deal with answers in different languages, without any translation. This opens innovative opportunities to compare perceptions and aspirations around the world in a trustable and credible way. “ - Mónica Becue-Bertaut, Textual Data Science with R