Skip to content

Lies, Damn Lies and Statistics

January 25, 2017

mark-twainI lied.

I said my next post would be on economics but, here is a short one about a conversation had on social media a few days ago.

Someone tried to convince me that alternative facts were OK. They used President Trump’s claim that violent crime (homicides) in 50 major cities was up 17%. I countered that, nationwide, violent crime has been going down since the early 1990s. I even provided a helpful graphic:

crime-stats

My social media interlocutor then countered that I was just choosing “alternative facts” to prove my point just like Trump was. So, I had to drill down and do some research.

Trump’s numbers were based on crime statistics evidently reported by the FBI. Indeed, the data seemed to to show that, from2014 to 2015, homicide rates in these cities went from 9.3 deaths per 100,000 to 10.8 deaths per 100,000 (numbers are from Politifact who checked the data).

10.8-9.3=1.5.

1.5/9.3=0.16 or 16%.

Not far from his claim of 17%.

BUT…

This claim falls short in a number of ways from a scientific perspective.

It is a one year jump.

And since the homicide rate is relatively low, it does not take much of an increase to register as a large percentage increase.

And a simple one year uptick could just be random variation around an average that is pretty low by historical standards rather than the beginnings of a long term trend that has been going down for a couple of decades.

So, this is the danger in not fully interrogating the numbers politicians spout. Trump did not lie. But when you approach the claim like a scientist the truth reveals itself.

Trump used a very short time frame of data to make a disingenuous and manipulative claim to frighten people into thinking that the streets of America are running with criminals gunning down innocents. And he is the strong, law-andorder candidate who is going to fix it. It was disingenuous…manipulative…calculating …purely for political gain… and…successful.

But, is this how we want our leaders to treat data? Hopefully, after spelling this out, the social media interlocutor is a little less in favor of “alternative facts”. But I don’t think I can delude myself into think that is true.

And, next year, when it takes a 1.5 deaths per 100,000 downtick, he can say that he brought the homicide rate down. To historic lows.

 

Advertisements

Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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 )

Google+ photo

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

Connecting to %s

The Insect Ecology Lab

at the University of Dayton (Dr. Chelse Prather & students)

ecoqui

Quantitative Genetics and more

Arthropod Ecology

Writings about arthropod ecology, arachnids & academia at McGill University

Random Walks

Mr. Chase blogs about math

Dynamic Ecology

Multa novit vulpes

Small Pond Science

Research, teaching, and mentorship in the sciences

%d bloggers like this: