Thursday, October 31, 2013

Multiple Comparisons, Margins of Error, and the Affordable Care Act Census Data

In my last post I looked at changes in the census rates in 51 states (50 plus DC) since parts of the act have come into effect.  I found 14 with a significant change from 2010 to 2011 (the most recent years available since the ACA was passed).  Each individual state was classified as changed if the difference in their rates were outside of the 95% probability margin of error (MOE) for both years.  That means that we are 95% certain that the actual rate is between an upper and lower limit.

For example Texas had a MOE of +/- 0.2%, that means it's estimated rate for 2010 of 26.3% is between 26.5% and 26.1% with 95% probability while it's estimated rate for 2011 of 25.7%  is between 25.9% and 25.5% with 95% probability.  Because the intervals for both years do not overlap, we can be confident that the change in the rate is real across the years.


Contrary to his claims, the results suggest that Ted Cruz's Texas so far has had a real but small decrease in the uninsured rate since the ACA or Obamacare has been enacted. In the graph above, California and Vermont have had significant decreases while Missouri was the only one that increased.  Massachusetts and Pennsylvania stayed the same.  The other states are summarized in my previous post.  

Statistician critics may argue that repeating 51 comparisons inflates the chance that at least one state has been significantly different by pure chance.  The 95% confidence interval means that there is a 5% chance or 0.05 probability that each individual comparison is significant by pure chance.  Repeated 51 times means that the expected number of chance differences is 51(0.05)=2.55.  Because there were 14 significant differences which is well above the expected number of chance differences.     I can be confident that almost all of changes in the rates are real.

Looking at the county level rates for Pennsylvania there were zero significant changes either positive or negative out of the 67 counties.  Counties with small populations have very large MOEs however.

**Related Posts**

The Affordable Care Act (ACA) Having Little Effect on PA's Uninsured Rate So Far (Repost with PUSH)



Sunday, October 27, 2013

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

In my post on Pennsylvania's uninsured, I wrote that the Affordable Care Act (ACA) was having little effect in Pennsylvania's rate of uninsured.  I wrote in another post that I received skeptical comments on my first post. I said in that post that I would look at changes in the rates in other states.  I couldn't then because the government shutdown also shutdown the US Census Bureau site.  The Advisory Board has come out with an image that can be updated on how many sign up for the state exchanges which are different from the federal.

Now that the shutdown is over I can look at the Census Data for the Small Area Health Insurance Estimates (SAHIE) for states from 2008 thru 2011.  To determine which states had a significant decline in the uninsured rate from 2010 to 2011 (the period where portions of the ACA have taken effect such as the one allowing parents to keep their kids on their insurance until age 26), I marked a state as declined if it had a rate that declined outside its margin of error (MOE).  There were 14 states with a significant change in their rates and 37 (including DC) that either stayed the same or increased.   States with larger populations have smaller margins of error.  

Five of the states are summarized in the graph above, California, Massachusetts (which has it's version of the ACA), Pennsylvania, Texas (with the largest rate in the US), and Vermont (which is the first in the US to pass a single payer plan).  California, Texas, and Vermont had significant decreases in the rates while Pennsylvania and Massachusetts remained within the margin of error (MOE) for both years.  Missouri was the only state that showed a significant increase from 15.3% to 16.0% which was outside the MOE of 0.3%.

ACA Decrease in uninsured * Medicaid Expansion Crosstabulation

Medicaid Expansion
Total
not participating or considering not participating
participating or leaning
expanding through alternate means or considering
ACA Change in uninsured
No
16
15
6
37
yes
6
8
0
14
Total
22
23
6
51

I tried to see if there was any association between decreases in the rates and other state level variables but there was none.  The table above shows that there is no relationship between a significant decrease in the rate and whether or not the state is participating in Medicaid Expansion (p=0.254).  PA Gov. Corbett has proposed a draconian version of Medicaid expansion which Lloyd Stires has written extensively about.   Below is a table showing where each state stands on the ACA decrease and Medicaid expansion.  I added this clip from The Daily Show to give somewhat amusing background on Medicaid expansion.




State
ACA Decrease in uninsured
Medicaid Expansion
1
Alabama
No
not participating or considering not participating
2
Alaska
No
not participating or considering not participating
3
Arizona
No
expanding through alternate means or considering
4
Arkansas
No
expanding through alternate means or considering
5
California
yes
participating or leaning
6
Colorado
No
participating or leaning
7
Connecticut
No
participating or leaning
8
Delaware
No
participating or leaning
9
District of Columbia
No
participating or leaning
10
Florida
No
not participating or considering not participating
11
Georgia
No
not participating or considering not participating
12
Hawaii
No
participating or leaning
13
Idaho
yes
not participating or considering not participating
14
Illinois
yes
participating or leaning
15
Indiana
No
expanding through alternate means or considering
16
Iowa
No
expanding through alternate means or considering
17
Kansas
yes
not participating or considering not participating
18
Kentucky
No
participating or leaning
19
Louisiana
No
not participating or considering not participating
20
Maine
No
not participating or considering not participating
21
Maryland
yes
participating or leaning
22
Massachusetts
No
participating or leaning
23
Michigan
yes
participating or leaning
24
Minnesota
No
participating or leaning
25
Mississippi
No
not participating or considering not participating
26
Missouri
yes (increase)
not participating or considering not participating
27
Montana
No
not participating or considering not participating
28
Nebraska
No
not participating or considering not participating
29
Nevada
yes
participating or leaning
30
New Hampshire
No
not participating or considering not participating
31
New Jersey
No
participating or leaning
32
New Mexico
No
participating or leaning
33
New York
yes
participating or leaning
34
North Carolina
No
not participating or considering not participating
35
North Dakota
No
participating or leaning
36
Ohio
No
participating or leaning
37
Oklahoma
No
expanding through alternate means or considering
38
Oregon
yes
participating or leaning
39
Pennsylvania
No
expanding through alternate means or considering
40
Rhode Island
No
participating or leaning
41
South Carolina
yes
not participating or considering not participating
42
South Dakota
No
not participating or considering not participating
43
Tennessee
No
not participating or considering not participating
44
Texas
yes
not participating or considering not participating
45
Utah
No
not participating or considering not participating
46
Vermont
yes
participating or leaning
47
Virginia
No
not participating or considering not participating
48
Washington
No
participating or leaning
49
West Virginia
No
participating or leaning
50
Wisconsin
yes
not participating or considering not participating
51
Wyoming
No
not participating or considering not participating

**Related Posts**


National, State, and County Uninsured Estimates