Data analysis for vaccine awareness week

I have combined the following data into one data matrix:
2009 Vaccination data table (subset of most often given vaccines reflecting the trend) ;
– American Human Development Index by State from American Human development Project;

Classification of Blue and Red states;

First, I have applied PCA to just vaccination rates data, where states partisan classification was used for classes.
No correlation between vaccination rates and partisan class was observed.

Second, Principal Component Analysis was applied to all data (vaccination rates and human development index) with autoscaling.

PC1 captures 39% of variance in the data and separates samples by those having high rank (cumulative index), high Education, Income and Health index from those having low Rank. Mostly blue states and some red states (AK, ND, NE, UT, KS) have highest rank. Vaccination rates do not contribute into PC1 (close to 0) indicating that there is no direct correlation between human development index and vaccination.

PC 2 separates states by vaccination rates. Those on top have higher vaccination rates that those on the bottom of a biplot. There is week correlation (captured in ~16% of variance in the data) between vaccination rates and education and income index and rank.

4 groups of states are classified by PCA:
1. Red states having quite good vaccination rates and very bed HD index.
2. Mostly blue states and some red states having best vaccination rates and best HD index.
3. Purple states having worst vaccination rates and worst HD index.
4. Mixed states – some blue, some red and Co with very bed vaccination rates but high Health Index.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: