Community, Demography

Trego and the American Community Survey

Montana’s American Community Survey is composed from the final interviews conducted with 10,138 households in the state.  Since Montana has 519,935 households, the chance of any household being in the final interview is 10,138 out of 519,935 = 0.0195, right around 2% of the population is included in the survey.  Since Tregp shows 295 households, we can guess that our community data is assembled from somewhere around 6 completed interviews.

This table about sample sizes is from kenpro.org

As you will note, a population of 250 calls for 152 samples, and that the break is in the lower right corner – while a sample of 382 covers a population of 75,000, 384 is good for a million.  I’m not going into details about sampling – this is a blog, not a stats class. If enough people ask for the stats instruction, I’ll do another article.  Suffice to say, we can expect the numbers on the ACS to be pretty vague in small communities. So let’s look at the ACS data: data.census.gov

The top of the page shows:

Total Population                                           515

Median Household Income                          $36,458

Bachelor’s Degree or Higher                       26.1%

Employment Rate                                        40.2%

Total Housing Units                                      283

Without Health Care Coverage                   9.0%

Total Households                                         249

As we go further down the page, we start to encounter the variance – the range the number represents.  That 515 population is taken from the decennial census not the ACS. 

Median Age:    60.5 +/- 3.2 years 

16.8% of Trego folks speak a language other than English at home – plus or minus 15.4% so that’s somewhere between 6 and 166.  Probably not a particularly useful piece of information.

That Median Household Income turns out to be plus or minus $8,980: the number can be as much as 24.6% off either way.  It can be as low as $27,478 or as high as $45,438.  As we move into the full chart on that number, we see that the number of households lists the margin of error as plus or minus 67.  Could be as low as 182 or as high as 316. 

That 26.1% of Trego residents with a bachelor’s degree or more has a 12% margin of error – it could be as low as 14.1% or as high as 38.1%,  It shows 8.1% of our residents holding graduate or professional degrees, but doesn’t give a margin of error there.

The school board will be pleased to know that 97.8% (plus or minus 6.6%) of our kids are enrolled in Kindergarten to 12th grade.  Might even surprise the County Superintendent.  Pretty sure some kids out there are home-schooled.

That 40.2% employment rate (+/- 12.9%) looks low – but I guess it fits right in with a median age over 60 and 31.1% (+/-9.4%) disability. 

And finally, there are 48 women 15 to 50 years old – but the margin of error is 38, so it translates to somewhere between 10 and 86.

The ACS data is good – but the sample for Trego was small, and not checking the limitations lets us make blunders.

Community, Demography

When the official data isn’t good data

As I was retiring, the American Community Survey(ACS) was replacing the long-form Census questionnaire.  There is merit to the argument that a survey can provide data that is as good as a form that one out of six people fill out – both are, after all, actually surveys.  Still, as a rural sociologist whose primary duties were rural demography, I wasn’t comfortable with the American Community Survey results – the sampling size was too small.

Now, I can access data that compiles five years worth of estimates – so here is some data on Rexford, Eureka, Fortine and Trego, by zip code, in two separate five-year conglomerates:

2012-2016Rexford
59930
Eureka
59917
Fortine
59918
Trego
59934
Total Population5664,425584562
5 to 9212823452
10 to 14353052249
Median (Average) Age58.043.650.749.2
Per capita income$22,377$18,799$21,203$25,999
2015-2019Rexford
59930
Eureka
59917
Fortine
59918
Trego
59934
Total Population6584,769747476
5 to 953212
10 to 14502163520
Median (Average) Age56.046.847.260.4
Per capita income$13,438$22,867$28,753$26,671

The American Community Survey is a well-conducted survey.  The data is correct, in both cases, within the limits of the survey.  The small samples, however, can create some large swings and make the data less useful.  I have been looking forward to reviewing the Trego data since I was selected to return the ACS survey.  Trego’s median age went up 11 years.  The population dropped by 15%.  The youth population plunged.  Meanwhile Fortine incomes increased by 36%, as Rexford plunged into the depths of poverty.  All the survey data is correct – but sampling bias, due to the small number of participants, has given us data we can’t use.

I still prefer the old, time-consuming long form results over the ACS.