Thursday, April 17, 2014

Quarterly Trends in the Uninsured and the ACA (Cross Post with PUSH)

The Gallup Organization has produced quarterly national estimates of the uninsured rate to assess the impact of the Affordable Care Act (aka Obamacare).  It suggests that the rate is at the lowest since the fourth quarter of 2008, before the recession began in earnest.  

The graph below, not surprisingly, shows that the rates are lower for the states that are expanding Medicaid.  The rates are also decreasing at a faster rate for Medicaid expanding states (15.4% in Q4 2013 to 12.45% in Q1 2014) compared to those who are not (19.6% in Q4 2013 to 18.1% in Q1 2014)

MotherJones has printed this table with projections for future costs and coverage under the ACA.  These projections are always based on assumptions which may or may not be reasonable.

A harder thing to measure is the number of underinsured under the ACA relative to the time before the law was passed.  The way in which the word underinsured is defined makes all the difference.  It is much easier just to ask survey respondents whether they have insurance or not that to ask them extensive questions about the type of coverage they have and whether it is adequate for their medical needs.

I have reported extensively on Census Bureau Small Area Health Insurance Estimates (SAHIE)  because they provide a more local picture of trends in the uninsured.  When they are discordant with uninsured rates, the rates of medical bankruptcies could suggest troubles with underinsurance.  Getting access to these statistics is difficult however.  PNHP has conducted a study on 2007 data found 62.1% of all bankruptcies were the result of medical expenses but new studies will need to be done to assess the impact of the ACA.  States with improved uninsured rates but little change in the number of medical bankruptcies could have issues with underinsurance.

**Related Posts**

The Affordable Care Act Having an Impact in Some States but not Pennsylvania

 

National, State, & County Uninsured Estimates

 

The Affordable Care Act (ACA) having little effect on PA's Uninsured Rate So Far

Friday, April 11, 2014

College Sports, Corruption, and Unions

Recently there has been a move by student athletes at Northwestern University to unionize.  They argue that they are really employees of the university who bring in billions of dollars for it in television revenues, alumni donations and gate receipts. While there is certainly a lot of merit to the argument, it still leaves in place the paradox of the student athlete in big time college sports.  New Late show host Stephen Colbert has a good discussion on this issue with former college player and union rep Ramogi Huma.  Jon Stewart also rightly skewered the NCAA for it's hypocrisy on college sports.
 




The comment I have is that the issue of corruption in big time college sports may not be adequately addressed.  The players are supposedly there to get an education but many are really there chasing dreams of playing in the NBA and NFL.  The NCAA has instituted SAT and GPA guidelines for athletes but many get around them with few skills.  Corruption is likely to occur when there are paradoxes between stated intentions and real intentions combined with lots of money.  Unionizing would help with the players situations but not with this paradox.

Major League Baseball and the National Hockey League have farm club systems where players are often taken right out of high school and given a salary to develop their skills in hopes of making it to the top tier.  There is also college baseball and hockey which does not get the same television exposure as football and basketball but I seldom hear the same stories of corruption in the former sports compared to the latter ones.  At least the farm club system is honest and removes the pretenses.  In the long run the NFL and NBA would be better off creating their own farm club system and letting them unionize.  If the players at colleges deserve to be unionized, so do other student employees.  Some graduate students now live on food stamps.

**Related Posts**

Say it ain't so JoePa!

 

Pitt & PSU going private: Shifting the Tax Burden to College Families & A Bigger Story Than the Pitt Bomb Threats & Joe Paterno

 

Concussions

 

Super Bowl XLV: A Battle of Champions Who Couldn't Compete Now Without a Salary Cap 

 

Lance Armstrong's Doping Claim: A Probabilistic Calculation

   

Sunday, March 30, 2014

Former College Classmate on CNN International on Turkey

Emel Ertas was an IUP (Indiana University of Pennsylvania) classmate of mine.  She was interviewed on her opinions on the upcoming elections in Turkey.  Their politics sounds about as divided as it is in the United States.

Going back to the days of the Alexander the Great, Turkey (then called Asia Minor) has always been at the crossroads between secular Europe and the more traditional Middle East.  The founder of modern Turkey, Mustafa Kemal Ataturk, worked hard to secularize it after being defeated in World War I.  The reforms he introduced included changing their writing to the Latin alphabet from Arabic script, granting rights to women, and providing education to the masses.  Just like in the US however, these struggles between the old and the new can remain after many reforms are enacted.  

Colbert gives a good summary.  Secularists in Turkey see Ataturk as their Lincoln.

**Related Posts**

Measuring Democracy in the World?

Change at My Alma Mater, IUP (Indiana University of Pennsylvania). Undergrads Getting Squeezed

 

The Worden Report: Protests in Wisconsin and Bahrain: Similar or Different?

 

What is Sanity?

 

Thursday, March 27, 2014

Mother Jones Saw My Method?


MotherJones magazine produced graphs published by Mitchel Hernlan similar to the ones I produced in my last posts.  The graph above has individual ratings of their health (from the national BRFSS survey) on the y axis and a measure of liberalism for each state on the left.  It seems to show that the more liberal states have better perceptions of their own health.  The results seem to be consistent with other measures of health such as life expectancy which was presented in the graph below from my last post.

As readers of this blog may notice, one glaring omission from the graph at the top is the District of Columbia.  (Another omission is a best fit regression line to show the trend.) This District is not technically a state but it does have three electoral votes for Presidential Elections which it has had since 1964.  It would score high on the measure of liberalism as it has never given it's electoral votes to a Republican while having poor health outcomes as described in the previous post.  While scoring high on liberalism is also has a high concentration of hate groups which are followed by the Southern Poverty Law Center.  

I did send my posts on hate groups to Mother Jones magazine, the Southern Poverty Law Center, and other publications.  I like to think that the similarities between the two graphs shown here suggest that it had an influence on their writing.  The fact that their article does not include DC suggest that they were not influential in the field of Political Epidemiology. There is still a need to be cautious about inferring a cause and effect relationship from correlational data and it takes time to sort the potential confounding variables out.  Some disseminating authors to the masses may not believe that they are prepared to deal with anomalies.


**Update**

One Statistician that the mainstream listens to is Nate Silver who is now feuding with Nobel Prize winning Economist Paul Krugman.  Below is a two part interview Silver gave on The Daily Show last night.  His new fivethirtyeight.com sounds like this site.  Maybe I should send my posts to him.  I have 3.5 years post for him on which to draw.




**Related Posts**

A Video By Dancing Statistics and an Announcement on Bloglovin

 

A Statistical Profile of the Uninsured in Washington, DC, New Mexico, and Texas

 

The Audacious Epigone

 

How do the States Stack Up on Infant Mortality? (Cross Post with PUSH)

 

Friday, March 21, 2014

Correlation with the Number of Hate Groups per Million, Poor Health Suggests More Hate

This is a follow up on the last post on the number of hate groups (such as the Ku Klux Klan and the Westboro Baptist Church) in each state that are being watched by the Southern Poverty Law Center.  Some may not agree with the inclusion of African American separatists like the Nation of Islam.  If these groups are excluded from the national total (115 out of 939). Computing the population adjusted rate per million gives a rate of 2.62 groups per million for the US.

The state with the highest previous rate of 23.72 groups per million was the District of Columbia.  One possible criticism is that they have a large African American population and that they are not technically a state.  If the four black separatist groups in DC are excluded from their total of 15, it still has a rate of 17.40 groups per million which is well above the national rate.  I decided to look at which other state level variables are correlated with the rate of hate groups in each state.

I combined this data set with a state level health and income data set and several of them are significantly correlated with the health measures.  The strongest of these effects was the one between infant mortality and hate groups per million accounting for 40.9% of the variability.  In the chart on the left, DC is an outlier on both variables. 

The correlation was rerun with DC excluded.  The relationship was still significant but with 12.3% of the variability accounted.  This indicates that the relationship is weaker with DC excluded but still present.


The relationship between hate groups and state level life expectancy was also significant with 29.4% of the variability accounted in a negative relationship where as the number of hate groups increases, the state's life expectancy decreases.  Like the previous graph, DC is an outlier on hate groups per million.  When DC is removed from the graph, 30.2% of the variability is accounted for in a relationship that is still negative.  This suggests that  DC has high influence but is not poorly fit to the data.

There was no significant correlation between state level per capita income and the rate of hate groups.  Other health related outcomes were significantly associated.  These individual correlations are not described in detail here for space considerations.

There is a more advanced method that can identify clusters of highly correlated variables.  It is called factor analysis.  There were two factors extracted which account for 68.8 % of the variability.  They are presented in the table below.


Rotated Factor Matrixa

Factor
Health
(46% of var explained)
Income
(22% of var explained)
Infant Mortality 2007 Deaths/1000
.909

Life Expectancy
-.817
-.462
% Low Birthweight Babies
.735
.245
Hate Groups per million
.709

Percent under age 65 in 200% of Poverty
.411
.862
Income
.140
-.727
Percent Uninsured in Demographic Group for All Income Levels
.140
.644
Expanding medicaid

-.314
Extraction Method: Principal Axis Factoring.
 Rotation Method: Varimax with Kaiser Normalization.a
a. Rotation converged in 3 iterations.

The first factor extracted has the health related variables loading on it and accounts for 46% of the total variance.  Infant mortality, life expectancy, % low birth weight babies, and the rate of hate groups load most strongly on this factor.  Percent within 200% of poverty, income, and % uninsured load most strongly on the second extracted factor (called an income factor) while accounting for 22% of the variability.  

The hate group rate does not load on the income factor but it does on the health suggesting an association with health related outcomes.  One must always be careful about inferring a cause and effect relationship based on correlational data. When DC was removed, the factor analysis did not run.

**Update**

Mark Potok of the Southern Poverty Law Center discusses the rise in hate groups and the prominence of Overland, Kansas shooter Frazier Glenn Miller.  Missouri, where Miller was living, had a rate of 3.82 hate groups per million and has life expectancy of 76.8 years with a ranking of 38th .  Kansas had a rate of 1.73 hate groups per million with a life expectancy rating of  and a ranking of 27th.

**Related Posts**

 

A Wave of Hate Groups in California? No in Washington, DC

 

How do the States Stack Up on Infant Mortality? (Cross Post with PUSH)


A Statistical Profile of the Uninsured in Washington, DC, New Mexico, and Texas

 

Wednesday, March 5, 2014

A Wave of Hate Groups in California? No in Washington, DC

The Southern Poverty Law Center has issued a report listing the total number of hate groups per state which they track.  The categories followed include, the Ku Klux Klan, Neo Nazi, White Nationalist, Racist Skinhead, Christian Identity, Neo-Confederate, Black Separatist, and General Hate.
California is shown to have the most hate groups followed by Florida and Texas.  All states except Hawaii have at least one.  These are also the first, second, and fourth most populous states in the US.  There is a highly significant correlation between the number of groups and the population in that state (r=0.885, p<.001) as seen in the above graph. 

When the number of hate groups in each state is adjusted for the states' population (by dividing the # of groups by the population and multiplying by one million), a different picture emerges.  The US average is 2.99 groups per million persons.  The rankings for the states plus DC are listed below.  Florida is almost exactly at the national average at 3.00 while Texas and California are below with 2.15 and 2.02 groups per million respectively.  A cubic plot was added to the graph below  and was significantly different from zero (r=.281, p=.045).
The states with the top number of groups per million have one outlier, Washington, DC.  With 15 groups for its 632,323 citizens, there are 23.72 groups per million which is almost three times higher than the next highest state, Arkansas.  It could be argued that the district is not really a State and is more of a city.  By comparison New York City has 22 hate groups for it's 8,336,697 citizens giving it a rate of 2.64.  Nearby Baltimore, MD has 7 groups for it's 621,342 citizens giving it a rate of 11.27.  My hometown, Pittsburgh, PA has 2 groups for it's 306,211 citizens giving it a rate of 6.53.  Of DC's 15 groups, four are Black Separatist (including the Nation of Islam), 3 each of White Nationalist (with names like the Center for Economic Studies), Anti-LGBT, and; General Hate, and one each of Anti Immigrant and Anti-Muslim. 


The extreme value for DC is similar to it's being an outlier for income and life expectancy.  In my most read post, I showed that it has the highest per capita income but the lowest life expectancy (2009 data).  The life expectancy of DC has since improved from 51st to 46th while the income ranking has fallen from 1st to a tie for 4th which would still make it an outlier.  I am not a sociologist so I'm not going to speculate as to the reasons for DC's high rate beyond what the data says.

The states that follow DC can be seen in the table below.  28 states are above the national average.  These are mostly in the south, west and midwest.  Vermont (at 6.39) and New Hampshire (at 5.30) are the only eastern states above the national average. My home state, Pennsylvania is slightly ahead of the national average at 3.21.



Rank
state
pop2012
Hate groups
Groups per million
1
District of Columbia
632323
15
23.72
2
Arkansas
2949131
24
8.14
3
Montana
1005141
8
7.96
4
Mississippi
2984926
22
7.37
5
Vermont
626011
4
6.39
6
Tennessee
6456243
37
5.73
7
Idaho
1595728
9
5.64
8
West Virginia
1855413
10
5.39
9
New Hampshire
1320718
7
5.30
10
Georgia
9919945
50
5.04
11
New Jersey
8864590
44
4.96
12
Nebraska
1855525
9
4.85
13
Alabama
4822023
22
4.56
14
Oklahoma
3814820
17
4.46
15
Delaware
917092
4
4.36
16
Louisiana
4601893
20
4.35
17
South Carolina
4723723
20
4.23
18
Indiana
6537334
26
3.98
19
Missouri
6021988
23
3.82
20
South Dakota
833354
3
3.60
21
Wyoming
576412
2
3.47
22
Kentucky
4380415
15
3.42
23
North Carolina
9752073
33
3.38
24
Colorado
5187582
17
3.28
25
Pennsylvania
12763536
41
3.21
26
Virginia
8185867
26
3.18
27
Arizona
6553255
20
3.05
28
Florida
19317568
58
3.00
29
Nevada
2758931
8
2.90
30
New Mexico
2085538
6
2.88
31
Rhode Island
1050292
3
2.86
32
Ohio
11544225
31
2.69
33
Maryland
5884563
15
2.55
34
Oregon
3899353
9
2.31
35
Texas
26059203
57
2.19
36
New York
19570261
42
2.15
37
Utah
2855287
6
2.10
38
California
38041430
77
2.02
39
Michigan
9883360
18
1.82
40
Massachusetts
6646144
12
1.81
41
Illinois
12875255
23
1.79
42
Wisconsin
5726398
10
1.75
43
Kansas
2885905
5
1.73
44
Iowa
3074186
5
1.63
45
Maine
1329192
2
1.50
46
Minnesota
5379139
8
1.49
47
Washington
6897012
10
1.45
48
North Dakota
699628
1
1.43
49
Connecticut
3590347
5
1.39
50
Alaska
731449
1
1.37
51
Hawaii
1392313
0
.00
Total
N
51
51
50
51
a. Limited to first 100 cases.

**Update** 

It's not just in the US where mapping applications are used to track racial incidents.  It's also done in Japan as seen in the video below.



**Related Posts**

Income and Life Expectancy. What does it Tell Us About US?

 

How do the States Stack Up on Infant Mortality? (Cross Post with PUSH)


A Statistical Profile of the Uninsured in Washington, DC, New Mexico, and Texas

 

A Geographical Represenation of the Mode and Ethnicity