So with each rendition of the American Community Survey (ACS), we get to see something called the "margin of error", or the MOE for short. The MOEs show us the 90% confidence interval we have that the ACTUAL thing we are measuring is within ONE MOE of the estimate. So for example, if the median age is 42.1 years and the MOE for median age is 1.0, then we are 90% confident that the actual median age is somewhere between 41.1 and 43.1 years of age. So how might we use the MOEs to our advantage when trying to say something about the data ? Well here's an example using the poverty rates for individuals within each municipality in Herkimer County.
The first thing you might want to know is what the overall poverty rate is for Herkimer County, and its margin of error. This first chart shows you that information based on the 2014 Five Year ACS Estimates. The estimated poverty rate for the county is 15.9%, with a margin of error of +/- 1.3%.
 |
| CLICK TO ENLARGE |
Next, we can see what each of the municipalities data looks like overlaid on this same chart.Note that the estimated number is represented by the black boxes, the margins of error on either side of the estimate by the lines.
 |
| CLICK TO ENLARGE |
So what does this tell us ?Well, let's start by looking at the communities whose MOEs and estimates fall entirely below the shaded area that represents the county's poverty range. All in all, six towns and one village fall completely below the county poverty range - the towns of Fairfield, Litchfield, Newport, Schuyler, Stark, and Webb, and the village of Poland. All of these areas have poverty rates and MOEs which qualify them as being significantly lower that that of the county.
 |
| CLICK TO ENLARGE |
On the other end of the spectrum, only one municipality has a poverty rate and MOE that place it significantly higher than the county's poverty rate - the village of Ilion.
 |
| CLICK TO ENLARGE |
All of the remaining municipalities basically have poverty rates that are not particularly different than the county as a whole. So when you use the ACS data, pay attention to the relative nature of the MOE - do they extend the 90% confidence intervals such that it lies within the range of the county as a whole? Or is it wholly below or above that range, and suggest that there is a significant difference between they two entities you are comparing?
So with each rendition of the American Community Survey (ACS), we get to see something called the "margin of error", or the MOE for short. The MOEs show us the 90% confidence interval we have that the ACTUAL thing we are measuring is within ONE MOE of the estimate. So for example, if the median age is 42.1 years and the MOE for median age is 1.0, then we are 90% confident that the actual median age is somewhere between 41.1 and 43.1 years of age. So how might we use the MOEs to our advantage when trying to say something about the data ? Well here's an example using the poverty rates for individuals within each municipality in Herkimer County.
