If one survey option receives the most votes (18%), can the item with the least votes (2%) be declared the least favorite?

The media can have difficulty interpreting survey results. Here is one recent example involving a YouGov survey that asked about the most attractive regional accents in the United States:

Internet-based data analytics and market research firm YouGov released a study earlier this month that asked 1,216 Americans over the age of 18 about their accent preferences. The firm provided nine options, ranging from regions to well-known dialects in cities. Among other questions, YouGov asked, “Which American region/city do you think has the most attractive accent?”

The winner was clear. The Southeastern accent, bless its heart, took the winning spot, with the dialect receiving 18 percent of the vote from the study’s participants. Texas wasn’t too far behind, nabbing the second-most attractive accent at 12 percent of the vote…

The least attractive? Chicago rolls in dead last, with just 2 percent of “da” vote.

John Kass did not like the results and consulted a linguist:

I called on an expert: the eminent theoretical linguist Jerry Sadock, professor emeritus of linguistics from the University of Chicago…

“The YouGov survey that CBS based this slander on does not support the conclusion. The survey asked only what the most attractive dialect was, the winner being — get this — Texan,” Sadock wrote in an email.

“Louie Gohmert? Really? The fact that very few respondents found the Chicago accent the most attractive, does not mean that it is the least attractive,” said Sadock. “I prefer to think that would have been rated as the second most attractive accent, if the survey had asked for rankings.”

In the original YouGov survey, respondents were asked: “Which American region/city do you think has the most attractive accent?” Respondents could select one option. The Chicago accent did receive the least number of selections.

However, Sadock has a point. Respondents could only select one option. If they had the opportunity to rank them, would the Chicago accent move up as a non-favorite but still-liked accent? It could happen.

Additionally, the responses were fairly diverse across the respondents. The original “winner” Southeastern accent was only selected by 18% of those surveyed. This means that over 80% of the respondents did not select the leading response. Is it fair to call this the favorite accent of Americans when fewer than one-fifth of respondents selected it?

Communicating the nuances of survey results can be difficult. Yet, journalists and other should resist the urge to immediately identify “favorites” and “losers” in such situations where the data does not show an overwhelming favorite respondents did not have the opportunity to rate all of the possible responses.

Five variables to determine “The Best Cities for Living the American Dream”

SmartAsset released their 2018 rankings for “The Best Cities for Living the American Dream.” Here are the top cities and the factors they used to develop the rankings:

Best Cities for Living the American Dream

Diversity score. To create this statistic, we looked at the population percentage of different racial and ethnic groups in each city. A lower number represents more diversity. Data comes from the U.S. Census Bureau’s 2016 1-year American Community Survey.

Economic mobility. This metric looks at generational change in economic position for families. A higher number shows greater mobility. Data comes from The Equality of Opportunity Project.

Homeownership rate. This is the percent of households who own their home. Data comes from the Census Bureau’s 2016 1-year American Community Survey.

Home value. This is the median home value in every city. For this study, a lower home value is considered better as we use it as a measure of affordability. Data comes from the Census Bureau’s 1-year American Community Survey.

Unemployment rate. This is the unemployment rate by county. Data comes from the Bureau of Labor Statistics and is for January 2018.

Several quick thoughts:

  1. The five measures seem to make sense. You could quibble with different aspects, such as measuring the unemployment rate at the county level rather than the city or metropolitan region.
  2. What would make sense to add to this list of five measures? There is no measure of educational achievement on this list and it might be interesting to consider the foreign-born population in each place (particularly since the foreign-born population is at a high in American history). Do lower taxes matter?
  3. The list is skewed away from two areas: (a) the East and West coasts and (b) the biggest American cities. I would imagine the coastal cities have difficulty with home values. However, it is less obvious to me why the biggest cities, particularly those in the South and Midwest, do not make the top of these rankings.
  4. How many Americans would give up where they currently live to move to one of these places that supposedly offers a better chance at finding the American Dream? Some experts suggest Americans should simply go where there are opportunities, whether these are jobs, cheaper housing, or less taxes. Yet, it is not necessarily easy to just pick and go, particularly to places like these that might not be very well known. (And, it could also be the case that a large influx of people to each of these top-ranked locations would influence these places.)

Niche names Naperville 2nd best place to live

This is not an uncommon accolade for Naperville: Niche recently named the suburb the second best place to live in the country.

Niche looked at 228 cities and more than 15,000 towns and based rankings on crime rate, public schools, cost of living, job opportunities and local amenities…

Niche also took into account reviews from residents in the various cities and towns. Out of the 397 reviews, 111 people gave Naperville an “excellent” rating, 187 said it is “very good,” 91 called the city “average,” six said it is a “poor” place to live and two said it is “terrible.”

Naperville got an A+ for both its public schools and being a good city for families, an A in diversity, an A- in housing and a B+ in both nightlife and crime and safety.

Niche ranked Ann Arbor, Mich., the best city to live in America. Rounding out the top five cities to live in America are Arlington, Va.; Columbia, Md. and Berkeley, Calif.

Several quick thoughts:

  1. In Money‘s 2016 rankings of the best places to live, Naperville was #10.
  2. Including reviews from local residents is an interesting twist. Why did a few respondents give Naperville a poor rating? Weather and a few other issues. And the two terrible ratings are both related to the state of Illinois.
  3. Where doesn’t Naperville do well? A C+ for cost of living as well as for weather.
  4. The top five cities are all within major metropolitan areas where they are sizable communities but nowhere near the biggest community. This may be notable until you look at Niche’s list of the “best places to live” and there you find smaller suburbs.

Money’s Best Places to Live are pretty well-off

The top communities on Money‘s Best Places to Live 2015 are not the wealthiest suburbs but they are fairly wealthy compared to national incomes. Only 7 have median household incomes less than $70,000 (the lowest is $57k) and 17 have median household incomes over $100,000. The median household income for the entire United States? $53,046 (data from 2009-2013).

Money’s methodology contributed to having communities with these income levels. Among other factors that went into creating these rankings:

-“[excluded] places with a median family income less than 80% of the state average”

-“Eliminate places with a median family income of more than 210% of the state average or a median home price over $1 million. Rank the rest on factors including job growth, diversity, and ease of living, giving the most weight to economic opportunity, housing affordability, education, and safety.”

In other words, the methods ensured that these communities couldn’t be too poor or too wealthy. Yet, the above-average incomes in these communities are connected to all sorts of other factors: not just jobs but higher-paying jobs (likely white collar), the money available in the tax base, the education level of residents, the kinds of available housing, and so on.

Could the average American live in these communities? Perhaps there would be some cheaper housing (that is a factor in these rankings though it is primarily about cost and not about having apartments and smaller and/or older houses) and the median household income suggests half of residents in these communities are below the figures posted here. However, these rankings are geared toward people of higher social classes.

Naperville ranked as the 186th most diverse city out of 230 biggest cities

Naperville may be the safest big city but it doesn’t have much diversity according to new rankings from WalletHub:

As the culmination to our series on diversity studies, this final installment combines our previous reports on economic class diversity, ethno-racial and linguistic diversity, and diversified economies with household diversity to paint the clearest image of America’s cities today. Recognizing that economic opportunity follows diversity, where in the U.S. would you rather live? Better yet, where would your unique background be most valuable to society?

To help you answer those questions, WalletHub once again examined the demographic profiles of the 230 most populated U.S. cities. In order to construct our final rankings, we tallied each city’s scores in the four major diversity categories we analyzed in this series.

Los Angeles leads the way at #1 and Chicago is at #32 overall. For the record, Naperville ranks 125 in income diversity, 336 in educational diversity, 265 in racial & ethnic diversity, 170 in language diversity, 149 in region of birth, and 183 in industry diversity. Naperville is also listed as one of the five lowest in marital status diversity as well as in household type diversity.

The commentary on the rankings suggests that economic opportunity is linked to higher levels of diversity. This may be the case but it doesn’t necessarily mean that the economic opportunities are equitably spread across cities. Perhaps having opportunities nearby is better than no opportunities at all – though I’m reminded of some of the earliest American sociological neighborhood studies like The Gold Coast and the Slum that noted how closely the rich and poor could live near each other with no interaction. Even if Naperville is not diverse in many of these areas, that doesn’t mean that it can’t be wealthier or that it won’t be viewed as a desirable place to live (ask Money or other magazines). Indeed, some might see the lack of diversity as highly desirable for both defensible (wanting a higher quality of life – isn’t that what the suburbs are supposed to be about?) and indefensible (trying to avoid members of a different racial/ethnic groups or certain social classes).

Naperville named safest American city over 100,000 people

Niche.com recently named Naperville the safest American city:

The rankings were based on evaluations from 215 cities with populations of more than 100,000 residents and included analysis of the city’s violent and property crime data, including murder, assault, robbery, burglary, larceny and vehicle theft rates.

Niche, a Pittsburgh-based ranking and review web site, used the 2013 FBI Uniform Crime Report “Crime in the United States,” an annual publication that reports the number and rate of violent and property crime offenses. They then used a formula to determine the city’s safety ranking, which includes weighting the crime by category: murder rate at 30 percent; assault and robbery at 20 percent each; and burglary and larceny at 10 percent each.

Two Naperville officials are quoted in the story praising crime prevention efforts. This helps but my guess regarding the bigger factor is the wealth of the community. According to the latest (2013) Census estimates: Naperville has a median household income of $108,302, the poverty rate is 4.1%, and the percent of residents with a high school degree is 96.5% and 65.9% have a bachelor’s degree. There are plenty of wealthy communities in the United States but they tend to be smaller. Once you get cities bigger than 100,000, it is hard to find many that have the number of educated and wealthy residents as Naperville.

Picking apart the top cities for singles rankings

Rankings of the top cities for singles may not be that valid:

“It doesn’t make much difference” where millennials live in terms of their marriage prospects, Andrew Cherlin, director of Johns Hopkins’ sociology department, wrote in an email. He said most major cities now have about the same rate of millennial inhabitants…

And indeed, most of the top cities for this category were near military installations. No. 2 on Wang’s list was San Luis Obispo, which is less than an hour from Vandenberg Air Force base, the third-largest air force base in the country. No. 4, in Hanford, Calif., has a large Navy presence…

So what does predict whether you’ll get married? The reigning champ of marriage indicators is Mormonism, even for millennials. Utah towns occupy the top three slots among 18-34 year-old marriage rates (nearly 2/3rds of millennials are already spoken for in western Utah County, Utah). And the U.S.’s top-three Mormon states, Utah Wyoming and Idaho, occupy the top three slots for states.

Surprise, surprise; rankings found on the Internet may not be that great. Sometimes this has to do with methodology: what is included in the rankings and how are the different dimensions rated? This is discussed here: do you want to look at millennial composition (where Washington D.C. leads the pack) or millennial marriage rate (Washington D.C. doesn’t do as well)? One lesson might be to have more specific rankings – do you really mean it is best for singles if your data is based on the marriage rate?

Additionally, two other issues arise. One, what if the cities aren’t that different from each other? Rankings are intended to differentiate between options but mathematical differences do not necessarily equal substantive significances. Second, why are the rankings in this order? Here, what related factors – such as the proximity of military installations – might be relevant? This may be hard to pick up at times because not all the cities may be affected by the same phenomena. Thus, the researcher has to do some extra digging to try to explain the rankings rather than just simplistically report them.

Even with the argument from Richard Florida about the creative class seeking out cities with enticing culture and entertainment, how many people move where they do because of such rankings?