I started using R because I needed more functionality than Excel. I didn't want to pay for Prism or SPSS. I decided the best way forward was to learn how to use R.
My key aim was to learn some advanced visualisation skills. I have been a fan of flowingdata.com for many years. I bought Nathan Yau's book, Visualise This as a new year gift for 2014. It showed me how to use R to make heat maps, nicely stacked bar charts and interesting charts.
Then, I found R-Studio and I can honestly say that I haven't look back. R, within R-Studio, is my goto program for data analysis and visualisation. I published my first paper using R to analyse proteomic data last year and I will publish more in the future.
Here are some of the key advantages of using R for academic research:
R can do analysis and visualisations that Excel and Prism can’t.
These include generating lots of pairwise graphs to detect correlations, overplotting scatter plots, performing cluster analysis and heat maps.
R can record your workflow and then you can share it.
R is more difficult because it uses command line to perform data analysis. However, this is also one of the key advantages. Because it uses command line, it also records a history of what you have done and allows you to write scripts. These scripts can be shared, easily reproduced and automated.
R is free!
R is open source. It costs nothing to buy or update. I really like this.
There are free programs that interact with R that make it easier to use.
I use R-Studio. These programs allow you to work with R in a slightly easier way. Again these are free and they are cross platform. They look the same on a PC or a Mac.
There is lots of free help!
There is a large community that provides advice and help about R. Put a search into your web browser and you come across lots of people who have experienced similar problems. With a bit of work, you can apply these to your data.
I used my three favourite recently to find the code to draw a figure legend: