histogram

The Problem with Linear Regression for Count Data: Predicting Length of Stay in Hospital

This year’s flu strain is very vigorous. The number of people checking in at hospitals is rapidly increasing. Hospitals are desperate to know if they have enough beds to handle those who need their help.

You have been asked to analyze a previous year’s hospitalization length of stay by people with the flu who had been admitted to the hospital. The predictors in your data set are age group, gender and race of those admitted. You also have an indicator that signifies whether the hospital was privately or publicly run.

What R Commander Can do in R Without Coding–More Than You Would Think

by Karen Grace-Martin 4 Comments

I received a question recently about R Commander, a free R package. R Commander is the powerhouse of our upcoming workshop R for SPSS Users.

R Commander overlays a menu-based interface to R, so just like SPSS or JMP, you can run analyses using menus. Nice, huh?

The question was whether R Commander does everything R does, or just a small subset.

Unfortunately, R Commander can’t do everything R does. Not even close.

But it does a lot. More than just the basics.

So I thought I would show you some of the things R Commander can do entirely through menus–no programming required, just so you can see just how unbelievably useful it is.

Data Sets and Variables

Import data sets from other software:

SPSS
Stata
Excel
Minitab
Text
SAS Xport

Define Numerical Variables as categorical and label the values

Open the data sets that come with R packages

Merge Data Sets

Edit and show the data in a data spreadsheet

Personally, I think that if this was all R Commander did, it would be incredibly useful. These are the types of things I just cannot remember all the commands for, since I just don’t use R often enough.

Data Analysis

Yes, R Commander does many of the simple statistical tests you’d expect:

Chi-square tests
Paired and Independent Samples t-tests
Tests of Proportions
Common nonparametrics, like Friedman, Wilcoxon, and Kruskal-Wallis tests
One-way ANOVA and simple linear regression

What is surprising though, is how many higher-level statistics and models it runs:

Hierarchical and K-Means Cluster analysis (with 7 linkage methods and 4 options of distance measures)
Principal Components and Factor Analysis
Linear Regression (with model selection, influence statistics, and multicollinearity diagnostic options, among others)
Logistic regression for binary, ordinal, and multinomial responses
Generalized linear models, including Gamma and Poisson models

In other words–you can use R Commander to run in R most of the analyses that most researchers need.

Graphs

A sample of the types of graphs R Commander creates in R without you having to write any code:

QQ Plots
Scatter plots
Histograms
Box Plots
Bar Charts

The nice part is that it does not only do simple versions of these plots. You can, for example, add regression lines to a scatter plot or run histograms by a grouping factor.

R is Not So Hard! A Tutorial, Part 12: Creating Histograms & Setting Bin Widths

by guest 2 Comments

by David Lillis, Ph.D.

This is Part 12 in my R Tutorial Series: R is Not so Hard. Go back to Part 11 or start with Part 1.

I’m sure you’ve heard that R creates beautiful graphics.

It’s true, and it doesn’t have to be hard to do so. Let’s start with a simple histogram using the hist() command, which is easy to use, but actually quite sophisticated.

First, we set up a vector of numbers and then we create a histogram.

B <- c(2, 4, 5, 7, 12, 14, 16)
hist(B)

That was easy, but you need more from your histogram. [Read more…] about R is Not So Hard! A Tutorial, Part 12: Creating Histograms & Setting Bin Widths