### When do people worry about hurricanes?

I recently read an article in the December issue of *Significance* titled, “Does Christmas
really come earlier every year?” by Nathan Cunningham of the University
College of Dublin. His premise was that,
by using cluster analysis of Google Trends data, we can see how people have
begun thinking about the holidays earlier and earlier each year. It’s a good read: http://www.statslife.org.uk/significance/1892. I should note that Nathan graciously
answered my emails asking for clarification and saw real value in this
technique for emergency management work.

**hurricane**”.

### Google Trends

Google Trends (http://www.google.com/trends/) allows you to view the volume of searches on particular terms. The units are percentage of total Google searches. For example, the week that Hurricane Katrina made landfall, “hurricane” scored almost 100; almost all searches were hurricane related. If you sign-on with your Google ID, you can also download the data to CSV. Cunningham used Google Trends to analyze search volumes on holiday-related terms (“Christmas”, “Santa Claus”, etc). Here I’ve compared the search terms “hurricane” and “tornado”. You can see that there is a somewhat repetitive pattern of increase mid-year. I wanted to explore this pattern.### Cluster Analysis

### Further Investigation

**cluster analysis**can illustrate the behavior of data that have more than one pattern. This could find application in data that vary from Region to Region or JFO to JFO, or changes with disaster type.

**Google Trends**data, it is easy to see that the data returned also lend themselves to

**Time Series Analysis.**

###
**R Code used in this example**

**## Crow's nest Clustering example – Tim Allen**

**# Adapted from http://www.statslife.org.uk/significance/1892**

**# Nathan Cunningham - Does Christmas really come earlier every year?**

**# Significance Magazine 11 November 2014**

**
#
Allow multiple plots (2 rows x 6 columns)
par(mfrow
#
You have to install and load the mclust package
library(mclust)
#
Calculate clusters for each year
# 1) load this
year's data in a matrix
observations
# 2) find
clusters based on models' BIC
fit
# 3) Plot the
clusters and print the model summary
plot(fit, what
print(summary(fit))
}
**

**=**c(2,6))

**for**(yr

**in**2007:2013) {

**<- span="">**as.matrix(subset(gtrends, year

**==**yr, select

**=**c("week","hurricane")))

**<- span="">**Mclust(observations, 2)

**=**"classification", xlab

**=**yr)

### Acknowledgement

### My sincere appreciation to Nathan Cunningham of the University College of Dublin for his kind help in preparation of this article. Please read his article, "Does Christmas really come earlier every year?"