Why Statistics is Not Data Science
Chris Malone | Tisha Hooks
|0:||STAT: Statistics is the science of data that focuses on understanding sources of variation, quantifying uncertainty, and confirming / contradicting hypotheses through inference |
|DSCI: The science of planning for, acquisition, management, analysis of, and inference from data (Source: StatSNSF Committee)|
|1:||STAT: Analysis of data within a specific context|
Can incorporate iterative process, etc
|DSCI: Computational tools required for big/wide data|
Non-traditional techniques used to analyze the data/create predictions - neural networks, machine learning, etc.
|2:||STAT: "The art and science of learning from data." Understanding real world problems through data. |
|DSCI: "The art and science of computing with data???"|
|3:||STAT: The science of collecting, describing, analyzing, and presenting data. Statistics is important for making informed decisions and effective citizenship. |
|DSCI: Study and practice of the collection, maintenance, analysis, and visualization of data (often at a large scale) using ethical, computationally supported, and statistically valid methods.|
|4:||STAT: Collection, Organization, Analysis, and Interpretation of Data|
|DSCI: Statistics with bigger, messier data|
|5:||STAT: A great chance to work with Tisha and Chris!|
The science of designing studies and analyzing associated data.
The science of asking questions and answering those questions with data.
Extracting information from data.
Data-based decision making.
|DSCI: The science of data gathering, exploration, and manipulation from unstructured or unconventional data sources.|
|6:||STAT: gathering, exploring, visualizing, analyzing, communicating what the data says, communicating the results, letting the data speak, using data to make informed decisions, |
|DSCI: big data, integration of statistics and computer scientist, computation, less inferential more prediction focused, grabbing data from multiple sources, data manipulation and cleaning|
Using data with uncertainties to answer questions about the world.
|DSCI: Wrangling real (and really messy) data from any field to address questions about the world. |
Data science is a subset of statistics?
|8:||STAT: Statistics is a science that studies variation in the world around us and uses methods and tools to describe data and make decisions.|
|DSCI: Data science is an interdisciplinary science that includes statistics, computer science, communication skills, and domain knowledge. |
|9:||STAT: creating knowledge from data using models and analysis understanding uncertainty and bias|
|DSCI: combining tools from statistics and computer science to manage and analyze complex data, with greater emphasis on upstream (i.e., before analysis) data processing|
|11:||STAT: The art and science of drawing insight from data accounting for uncertainty. Entire pipeline is considered an aspect of statistics (collection to communication). |
|DSCI: Application of computational and inferential thinking to a discipline-specific problem. Includes areas outside of statistics such as data management/storage.|
|12:||STAT: The science of drawing inferences from data|
|DSCI: Integration of statistics, computation, and data management|
|13:||STAT: Collecting, visualizing, and analyzing data to draw inferences about populations in the presence of uncertainty and communicating the results.|
|DSCI: Emerging field involving data management, computation, statistical models, visualization, interpretation, domain knowledge, communication, and decision-focused.|