SPSSStatistics

The R ecosystem has become widely popular lately in enterprise statistical analysis because it's free and has a low barrier to entry for all

The wide use of R in enterprise Big Data has gained a lot of traction in the last couple of years, for so many great reasons

Because of the ease of adoption, enterprise software vendors are embracing R for analytics

Early adopters want low cost/ big results that ultimately drive where to invest for future gains

Open: R’s open-source provenance ensures that whenever a new analytical approach is developed, it is released to the entire R community almost immediately once it has been submitted and tested through the R project.

R is not just a stats package, it’s a language, designed to be used the way problems are thought about

Mature: R has been on the market for more than two decades, is field-proven in many enterprise applications, and is an integral component of many commercial solutions such as IBM SPSS Statistics.

@TrippBraden They do, some times they move too quickly though, jumping in is fine, some times not with both feet first is safer though ;-)

R has become the preferred computing environment for a large part of the statistical community

Popular: R has become very popular with statisticians and data miners for developing statistical software and is widely used for advanced data analysis.

Comprehensive: R provides a wide variety of advanced statistical and graphical techniques.

R brings a programmatic way to approach statistics w/ a different level of investment.

Inexpensive: R is available as Free Software under the terms of the Free Software Foundation GNU General Public License.

Deployable: R runs on Windows and MacOS, a wide variety of UNIX platforms and similar systems (including FreeBSD and Linux).

@jameskobielus Like so many tools we're now putting to good and powerful use, R has been a stable secure scaleable tool for so much longer than most people realise

Intuitive: R is object-oriented language that is easy for the average statistical analyst to learn and master.

Composable: R facilitates development and composition of statistical models as components of larger analytic workflows.

@jameskobielus R does have some great commercial support as well and that's part of what is making it so popular, esp. platforms like Data Science Experience from IBM.

Embeddable: R is easier to embed into applications than other statistical languages.

Extensible: R packages can be easily extended in the statistical analysis tool of your choice.

R is great because it offers the opportunity to create packages that is easy to distribute and access within the community

@jameskobielus I love that it takes me less than a few hours to get almost anyone up and running with R to set them on the right path to learning or doing real analytics

Check out my recent blog on the power of R in stat analysis; http://www.ibmbigdat...

@8pathsolutions Also great that it's supported on so many platforms natively, cross platform support is pure gold

Check out the recent whitepaper on the power of R with SPSS Statistics: http://ibm.co/2f0cqs...

@tcrawford I also love that so many of us share code and models others and ourselves can build on and share development investment and effort / time

@jameskobielus Good Pt: There's a good fit for R and good fit for products like SPSS.

I like a R a lot better now than 10 years ago - not only are more people using it, #rstudio makes it much easier to look at R code

@dez_blanchfield That's for sure. R has joined Spark and Hadoop as core to the new open-source stack for programming data-driven applications.

@jameskobielus Open platform support is such a large part of the success of tools like R and many others

@8pathsolutions I have plans to teach my kids some basics over this coming xmas break in fact to help them in high school and homework !!

@jameskobielus Really enjoyed it, your regular blogs are always a good source of info ;-)

@dez_blanchfield Very true! Cross platform support is becoming important - I run linux, windows and mac daily

@8pathsolutions I love that I can jump from Windows, to Mac, and Linux and back, at any time, and share with cloud drives or source code version control tools ;-)

Start with some refresher courses in basic mathematics before anything else

Become familiar with probability theory & it’s use

Learn about classical statistics / hypothesis testing

Learn anova, analysis of variance, regression and the general linear model

Learn factor analysis and other multivariate methods

Core: linear algebra, basic statistics, linear and logistic regression, data mining, predictive modeling, cluster analysis, association rules, market basket analysis, decision trees, time-series analysis, forecasting...

Learn about Bayesian analysis and learn how to put it to use

...machine learning, Bayesian and Monte Carlo Statistics, matrix operations, sampling, text analytics, summarization, classification, primary components analysis, experimental design, unsupervised learning constrained optimization.

Learn & practice everything you can in data-mining

Data visualization. Feature engineering.

I have to say that I personally recommend folk avoid a lot of pain building their own tools and just sign up to Data Science Experience and Data Watson Platform ;-)

At least one subject domain focus grounded in academic training. Perhaps a "computational" field such as econometrics.

Get your hands on SPSS Predictive Analytics and play / learn / read ;-)

Blog I posted a few years ago on the topic of data science curricula: http://www.ibmbigdat...

Get hands on with deep learning / machine learning, all things Cognitive Computing is the next big wave, folks need to sit up and pay attention to this one, it's going to be HUGE !!

Free courses on bigdatauniversity.co...: https://bigdataunive...

in the MIDS program at datascience@berkeley, but I'm biased, I teach statistics for data science there :)

@dez_blanchfield Speaking of: get a free trial of #SPSSStatistics: http://ibm.co/2hvlR0...

@8pathsolutions You can be biased, I only wish I could spend some time there taking your course ;-)

@jameskobielus The examples on DSX are a great starting place too, and shared cards from others sharing their work..

I studied traditional mathematics, economics and statistics courses because #DataScience didn't exist when I was in school - I think I turned out just fine