Spurious Correlations

According to a Christian Apologist, there is…

"…increasing life expectancy the more often one attends religious service. A 20 year old who attends a religious service more than once a week has an 8 year greater life expectancy than one who never attends religious services.  

Obviously much needs to be sifted from such and variables considered, but I would proffer that it is a pretty dramatic difference! 

God does indeed sometimes say "yes" to our prayers for healing and longer life!"

Now… I am willing to believe that a religious lifestyle could increase life expectancy. Unfortunately, the Christian Apologist hasn't provided any evidence and is making a massive assumption based on correlation rather than causation.  I'm guessing his statistics come from the USA.

There is an interesting psychological overview of the subject here.  A brief extract…

When we compare people living in the same country, religious people enjoy a health advantage if they are part of a large majority, as is true of the U.S. That advantage disappears if religious people are in the minority.

Why? One plausible reason that non religious people in the U.S. have worse health is that they are largely excluded from participation in politics and find that they have less of a role to play in their local communities because religious people consider them unworthy. One key reason for this is that churches play a central role in organizing charities and civic organizations.

In predominantly secular countries, community involvement is very high so that atheists are much more active in their communities than they would be in a comparatively religious country such as the U.S. Instead of feeling like second class citizens, the non religious are fully integrated in their communities with all of the health advantages this brings. So what had looked like advantages of religion could be simply an advantage of being in the mainstream.

But what about the assumption of causation that the Christian Apologist has made?  Here are some incredibly compelling correlations from the excellent http://tylervigen.com website. I think everyone would agree that assuming causation (rather than determining a causation) can be misleading…

US spending on science, space, and technology correlates with Suicides by hanging, strangulation and suffocation

1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009
Spending (Millions of today's dollars) (US OMB)	18,079	18,594	19,753	20,734	20,831	23,029	23,597	23,584	25,525	27,731	29,449
Deaths (US) (CDC)	5,427	5,688	6,198	6,462	6,635	7,336	7,248	7,491	8,161	8,578	9,000
Correlation: 0.992082

 Number people who drowned by falling into a swimming-pool correlates with Number of films Niclas Cage appeared in

	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009
Deaths (US) (CDC)	109	102	102	98	85	95	96	98	123	94	102
Films (IMDB)	2	2	2	3	1	1	2	3	4	1	4
Correlation: 0.666004

People who drowned after falling out of a fishing boat correlates with Marriage rate in Kentucky

	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010
Deaths (US) (CDC)	19	16	9	12	15	10	11	7	2	5	1	1
Marriages per 1000 people (US Census)	10.9	9.8	9	9	9.1	8.8	8.7	8.4	7.8	7.9	7.6	7.4
Correlation: 0.952407

Divorce rate in Maine correlates with Per capita consumption of margarine (US)

	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009
Divorces per 1000 people (US Census)	5	4.7	4.6	4.4	4.3	4.1	4.2	4.2	4.2	4.1
Pounds of margarine (USDA)	8.2	7	6.5	5.3	5.2	4	4.6	4.5	4.2	3.7
Correlation: 0.992558