If you converse with any veteran data scientist, you might find yourself bemused with all the data-related or statistical terms that you would come across. Statistics is just the beginning of a voyage if you are planning to get ahead with a career in data science. Dealing with complex data is close to impossible if you are not familiar with the core concepts and terms in statistics. If you are comfortable with number-crunching, statistics is a piece of cake. On the other hand, if statistical results are computed electronically, you might sigh a breath of relief while manipulating large and crucial data.
If you want to master programming with statistics, there are plenty of software options available for you, such as R, Scala, Python and several other open source as well as licensed tools. However, SAS, developed by North Carolina State University, (later incorporated as SAS Institute), is leading the analytics market (almost 70% companies use SAS for analytics). SAS is a popular tool to help with data analytics and business intelligence.
Worry not — as this article will present the best resources available online (and for free!) to analyse statistical data through coding or programming by SAS. These resources will definitely sharpen your programming skill along with providing statistical knowledge in depth.
The pioneers of SAS have come up with a great offering when it comes to learning SAS. The software itself has over 200 components which deliver service for various business domains ranging from Operations Research to Clinical Data Integration. The training section in the website offers free tutorials in the form of videos to facilitate easy learning. The topics include right from setting up the software, teaching basics of SAS programming, to advanced SAS programming such as SAS SQL, SAS Studio, SAS GRAPH, among others. It also provides classroom training, e-training along with an official certification for a prescribed fee in the form of training courses.
2. SAS Tutorials from Kent State University (Website)
This open-access online tutorial brought out by Kent State University is the best bet for any student or learner to learn SAS from basics. The tutorial begins by familiarising the learner with SAS environment, rules for programming and SAS dataset libraries for creating and storing data. It discusses various mathematical and statistical functions which can be implemented using SAS in the successive sections of the tutorial. Apart from this, inferential statistics is also mentioned in detail. Learners can also work on the datasets provided in the tutorial.
3 . ListenData (Website)
This is an interactive website dedicated solely to data analytics platform. It offers SAS tutorials along with many other useful information such as preparing for interviews and SAS jobs resumes. The learner can proceed at his or her own pace with the tutorials. Statistical Analysis with SAS focuses on essential topics such as descriptive and inferential statistics, linear and logistic regression, time series analysis, variable selection and reduction, cluster analysis and predictive modelling with SAS, and many more. The section starts from SAS basics and proceeds to advanced sections such as Proc SQL and SAS Macros.
4. Discovering Data Science with SAS by SAS Institute (e-book)
This free e-book is a slight digression from all the resources listed above. Developed by a team of data scientists at SAS, it focuses mainly on data science areas such as data visualisation, data quality, DS2 language and neural networks using SAS. In addition to these topics, Big Data is also discussed to differentiate its context to data science. The case studies presented at the end of the book serve useful insights. The book is available for free in a PDF from the official SAS website.
5. SAS Manual for Introduction to the Practice of Statistics by Michael Evans (e-book)
University of Toronto, Canada, has introduced a handbook to specifically focus on the usage of statistical concepts in SAS. The main topics covered under statistics are probability, data distribution, inferential statistics and regression. The learner gets an idea to implement his statistical knowledge to his or her SAS programming. This book is a great help for someone who has trouble finding the right code etiquettes for SAS programming. This book is available for free here.
There are innumerable learning resources to grasp the concepts of SAS Programming, but validity of information should always be checked, for it may lead to incorrect or improper coding standards in practice. Also, industries demand have leaned on R, Python and Big Data suite for data analysis these days. But nonetheless SAS will always be there to take on analytics and business intelligence solutions.
Try deep learning using MATLAB