What’s the difference between data analysis, data analytics, statistics, applied Mathematics, and data science? Eli5
In: 0
Data analysis – checking patterns in lego blocks
Data analytics – the tools used for checking patterns (and presenting them), like Pandas, Tableau
Data science – the art of using the patterns in lego blocks to make better decisions
(Someone correct if I’m wrong on some parts)
> data analysis
Very general term that can refer to any process of analysing or interpreting data.
> data analytics
Business buzzword.
> statistics
The entire academic field that studies data and probability. Alternatively, multiple pieces of data (e.g. “employment statistics” means “some data on employment”).
> applied Mathematics
A fairly vague term encompassing the parts of maths that are closer to direct applications, such as fluid mechanics, mathematical physics, mathematical biology, and financial mathematics. Nobody really agrees exactly what falls under this, but it’s usually seen as distinct from statistics, which usually isn’t regarded as part of mathematics.
> data science
Programming buzzword.
Data Analysis: A really broad term that encompasses many other things, including most of Data Science.
Data Analytics: Analytics is a term that encompasses a set of tools and measurements, usually for measuring things like user engagement (how long does the user stay on this page? What do they usually click first? etc.)
Statistics: A field that is separate from, but mostly based on mathematics. Encompasses techniques for describing data (descriptive) and making predictions based on data (predictive)
Applied Mathematics: A sub-field of mathematics that is focused on using mathematics to solve tangible problems from other fields (e.g. physics, engineering, statistics). The majority of the field is differential equations, linear algebra, and probability.
Data science: Basically modern day statisticians. The main difference being that we’re being absolutely flooded with massive amounts of data constantly, so their job is to not only do statistics (and machine learning) with data, but also to build and integrate data pipelines (all the stuff that captures, transforms, and stores the data). Classical statisticians were a lot more worried about collecting good data efficiently, since collecting data was a manual process.
Latest Answers