1. Introduction
2. Software
R
I will start by saying that this tutorial is written assuming some level of statistical knowledge (i.e., an undergraduate course) and some familiarity with computers. For example, I will leave it to you to explore the main R command window on your own. While I will walk you through how to conduct statistical analyses in R I will generally not explain advanced concepts in detail in most instances - I will leave it to you to support you understanding of R and statistical analysis. I highly recommend Andy Field's book for this http://www.statisticshell.com/html/dsur.html. Note, if you look towards the bottom of the linked page your will find the following linked PDF which is a chapter from the book that explains the R programming environment in detail.
Most research statisticians do not use SPSS despite the large number of researchers that prefer this statistical package. Instead, statisticians prefer R, an open source statistical programming environment.
To start this series of tutorials, you will have to download and install R. R can be downloaded here:
https://www.r-project.org/
I personally think it is a lot easier to use R Studio to work with R. R Studio is a shell that visualizes a lot of things that are typically hidden in such as variables. It also provides a menu driven selection of tools that R users typically have to execute using R code. Given that this tutorial assumes you have R Studio, download and install it now:
https://www.rstudio.com/products/rstudio/#Desktop
Once R Studio is installed I would recommend creating a directory for your working R files. Do this now.
Open R Studio (note, R automatically loads once R studio is opened). Take some times and explore the menu items and the workspace.
Using Session --> Set Working Directory --> Choose Directory set the directory to your R directory. Note, you will see the command for changing the working directory in your command window after using the Session drop down menu. To do this from the command prompt you would use setwd("~/R") where whatever is in quotes is your path to your R directory.
Installing Packages
One of the reasons R is so powerful is that users can write their own "packages" which add tools to R. You can download these packages for free. I will note here that while I love R Studio I find packages are more easily installed from R itself so we will install packages from within R but use them in R studio.
Close R Studio and open R. You may get a prompt here to save your workspace, feel free to do so. This is how R Studio saves all of the material you have been working with - this is very handy when doing data analysis but sometimes you may wish to clear the workspace. We will get to this later.
At the command prompt in R, ">", type install.packages("plyr"). You will be asked to select a CRAN (host) site from which to download the package - select one. This will install the plyr package which adds some commands we will use in later tutorials. In later tutorials we will also add other packages. Do not forget to install packages from within R!
Now, reopen R Studio. At the command prompt type library("plyr"). This tells R Studio to load the plyr library for use. You will need to do this each time you use a library, although you can set R to load libraries automatically. There are reasons for not doing this - we will get to that later.
Congratulations! You are now ready to start learning how to do statistics in R.
Most research statisticians do not use SPSS despite the large number of researchers that prefer this statistical package. Instead, statisticians prefer R, an open source statistical programming environment.
To start this series of tutorials, you will have to download and install R. R can be downloaded here:
https://www.r-project.org/
I personally think it is a lot easier to use R Studio to work with R. R Studio is a shell that visualizes a lot of things that are typically hidden in such as variables. It also provides a menu driven selection of tools that R users typically have to execute using R code. Given that this tutorial assumes you have R Studio, download and install it now:
https://www.rstudio.com/products/rstudio/#Desktop
Once R Studio is installed I would recommend creating a directory for your working R files. Do this now.
Open R Studio (note, R automatically loads once R studio is opened). Take some times and explore the menu items and the workspace.
Using Session --> Set Working Directory --> Choose Directory set the directory to your R directory. Note, you will see the command for changing the working directory in your command window after using the Session drop down menu. To do this from the command prompt you would use setwd("~/R") where whatever is in quotes is your path to your R directory.
Installing Packages
One of the reasons R is so powerful is that users can write their own "packages" which add tools to R. You can download these packages for free. I will note here that while I love R Studio I find packages are more easily installed from R itself so we will install packages from within R but use them in R studio.
Close R Studio and open R. You may get a prompt here to save your workspace, feel free to do so. This is how R Studio saves all of the material you have been working with - this is very handy when doing data analysis but sometimes you may wish to clear the workspace. We will get to this later.
At the command prompt in R, ">", type install.packages("plyr"). You will be asked to select a CRAN (host) site from which to download the package - select one. This will install the plyr package which adds some commands we will use in later tutorials. In later tutorials we will also add other packages. Do not forget to install packages from within R!
Now, reopen R Studio. At the command prompt type library("plyr"). This tells R Studio to load the plyr library for use. You will need to do this each time you use a library, although you can set R to load libraries automatically. There are reasons for not doing this - we will get to that later.
Congratulations! You are now ready to start learning how to do statistics in R.
JASP
SPSS
3. Data Formats