Friday, September 4, 2015

I should be grading, but ...

Instead of grading, I'm fiddling with UGA data on -- believe it or not -- restrooms. I've done this before, but the data's been freshened and I thought I'd toss out a few semi-interesting tidbits. Keep in mind these data are from UGA.

  • The average size of male versus female restrooms is about the same. Women's lavatories (as it's described in the data) average 157.6 square feet. Men's, 148.7 square feet. So Women 1, Men 0.
  • On a related note, there are 413 female public restrooms listed, and 400 male restrooms. So make that Women 2, Men 0.
  • Favorite categories. There are a couple of restrooms coded as "corridors" and a couple listed as "stairways." No, I have no idea what the hell that means. Not gonna go there.
  • Some older buildings, if you're in a wheelchair, you're shit out of luck. Baldwin Hall, for example, has 18 listed bathrooms, with 17 listed as "non-access" for wheelchairs and the other one listed as "unknown." Joe Brown Hall has 12 restrooms, none wheelchair accessible.
  • A number of other buildings have a least a couple of wheelchair-accessible restrooms. Take Environmental Health Sciences, for example. It has 10 listed restrooms, with two as wheelchair accessible. Less shit out of luck there, I suppose, than Baldwin Hall.
  • In all, of the 1,939 restrooms in the data, 130 are not wheelchair accessible. An even thousand are listed as accessible, the other 809 as "unknown." Not so bad when you consider the age and construction style of many of the older campus buildings.
  • The smallest bathroom on central campus is 15 square feet. It's 101A in something called the "locomo diag center," which looks like the Vet school. There are two bathrooms listed at something called the Attapulgus Research Farm that are 9 square feet. No idea where that is.
  • The largest bathroom on campus is obvious. It's at the football stadium, a whopping 1,219 square feet. All of the biggest restrooms are at athletic facilities.

A quick caveat on the data. I didn't take the time to exclude UGA property not on the central campus. As such, this includes a few odd-and-end places, like agricultural facilities on College Station, etc.




Thursday, September 3, 2015

New Georgia Prez Poll


A new poll puts Trump ahead in Georgia. The leaders are:
  1. Trump (34%)
  2. Carson (25%)
  3. Bush (11%)
  4. Cruz (6%)
  5. Huckabee (5%)
  6. Fiorina (5%)
  7. Kasich (3%)
  8. Christie (2%)
  9. Rubio (2%)
  10. and all the rest of them, I'm tired of typing. Let's just say "undecided" is leading six candidates.
The nerd stuff -- a poll of 664 "likely" GOP primary voters, margin of error 3.8 percent. Data weighted to reflect the previous primary demographics like age and race (you can do this in Georgia as the data are collected by the state).

You can get more details here. Ya want some methodological fun? Look at that pdf and the breakdown by age and whether reached by landline (remember those?) and mobile. Of those reached by that thing called landline, 1.3 percent were between the ages of 18-29. That increases, of course, as age grouping increases. So among 30-34 years, it's 13.1 percent, among 45-64, it's 49.7 percent, and among 65 years old and up, they make up 35.9 percent of the landline sample. In other words, nearly 8 out of 10 landline respondents were over the age of 45.

In the mobile sample, 0 percent are ages 65 and up. Think about that, especially for surveys that rely so heavily on landlines (as this and others often do, as they used landlines first).

Indeed, it's hard to tell just how many surveys were landline versus mobile. That matters. Landline robo-polls (and yeah, it doesn't say so, but this is a robo-poll) skew older, more conservative, and come with problems that are difficult to offset through statistical weighting. That said, there are no surprises in the numbers above. Fiorina has the biggest change since this firm's last poll, again not a surprise.



Wednesday, September 2, 2015

The Circle of Academic Blog Life

So I'm waiting for a student to show for a meeting and I'm skimming the new issue of the Journal of Media and Religion. There's an article about religious responses to The Big Bang Theory, so I start reading the first graph and this appears in the third sentence:
Based on statistical analysis, Hollander (2013) suggests a more moderate perspective. He indicates that many people with differing perspectives about belief in the Bible still watch the highly popular television show, now in its eight season on the CBS network. He compares perspectives about this show with those who claim religious affinity and those who do not see religion as important. Biblical literalists, in Hollander's study, report that 28% of them watch the show; for those who see religion (and the Bible) as unimportant, the percentage of viewership was 31%. There is a slight difference in this report, but it is not significantly definitive (Hollander, 2013).
"Whoa," I think. "Another Hollander? Because I've never done research specifically about the TV show. Then I check out the references:
Hollander, B. (2013, October). What people know: B ig Bang Theory. Retrieved from http://whatpeopleknow.blogspot.com/2013/10/big-bang-theory.html.
In other words, they cite my blog. This very blog. Cool. And a first. Here's the link to that post and here's a related post even more to point, if you've nothing better to do. What it boils down to is I have tons of data and came across some questions that ask how often respondents watch various television programs. I saw Big Bang and then quickly analyzed it in terms of other questions available in the data. I even mulled over a bigger piece, but got busy elsewhere.

And thus we have the circle of life, the circle of academic/blogging life. I blogged about it, my blog post gets cited, and thus I must blog about the citation.

Oh, an abstract of the Media and Religion article is here, but I can neither point to nor see myself online the full article -- and I'm on the journal's friggin editorial board.


Trump and the Birthers

There's a PPP poll out that's gotten some attention out in the wild world of cable news (and some wacky news sites).

First, overall, 44 percent of Republicans in this survey believe Barack Obama was born outside the U.S. That's higher than usual. Over half (54 percent) think Obama is Muslim. That's high too. I've written extensively, and conducted actual research, on both topics. But what's fascinated some folks is the analysis of Donald Trump supporters. I even heard this reported today on Morning Joe, thankfully with some skepticism. Here it is:

  • Sixty-one percent of Trump supporters believe Obama was born outside the U.S.
  • Sixty-six percent of Trump supporters believe Obama is Muslim.

Wow. But let's do the math. Set aside the Dems, who aren't that interesting. The survey was of 572 Republican likely primary voters. So if Trump has 29 percent, that means an N here of about 166 respondents. That's a really small number to base a result on. Indeed, if you did into the crosstabs at the bottom of the link I provided above, you'll see stuff reported for candidates with only a handful of supporters. For example, 100 percent of Jim Gilmore supporters believe Obama is Muslim. All six of them, if my math is right.

I also worry, a little, about question order effects. If the questions were asked as presented (and they may have been randomized, it's hard to tell), then the questions about Obama followed a series of questions asking if you're a member of the Tea Party or are an evangelical Christian. Could these prime a different response to the Obama birther/religion questions? Perhaps. Which may explain the somewhat inflated numbers above, but those numbers may also simply reflect a more conservative voter who participates in primaries, versus general elections.




Monday, August 31, 2015

Best Bang?

An article in Columns, UGA's faculty and staff weekly newspaper, notes that the university is #3 in "best bang for the buck" in the southeast.

A few points:
  • Read "best bang for the buck" the wrong way and you'll get in trouble. So just stop.
  • While UGA is 3rd in the southeast, the article fails to note it's 52nd in the U.S., down from 32nd a year ago. Ouch.
  • UGA is actually tied for 1st in the southeast. Just listed third. Six schools have an overall score of "12." So that 52nd above nationally? We're in a tie for that, based on points.
The 2015 national rankings are here.

Ahead of us in the southeast are East Carolina University and North Carolina State University. For the life of me I can't figure out the tie-breakers. It's not alphabetic, not any of the obvious metrics listed across the page. Anyone see it? If so, lemme know.






Thursday, August 27, 2015

Dog Owners

I missed doing this for National Dog Day or whatever the hell it was called, but here's a quick look at how dog ownership correlates with other factors.

As compared to non-owners, dog owners tend to be:
  • more politically conservative
  • more likely Republican
  • more likely to believe in a literal interpretation of the Bible
  • younger
  • less educated
  • watch less TV news
  • read fewer newspapers
This is based on 2012 national survey data provides by ANES. When I have time, I'm gonna do a more complete cat vs dog owners because I have both questions available in a nice, fat data set with lots of other variables.



Excessive Drinking

Athens-Clarke County, home of UGA. Party School. Downtown bars. Vomiting students. Underage possession. You know the story. So you'd expect Clarke County to rank high in the state in terms of percent who meet the "excessive drinking" threshold.

No, not really.

According to the 2015 Georgia health data, the statewide average is 13 percent. The "winners" in the county excessive drinking contest are (envelope please) ...

1. Dawson (18%)
2. Fulton (16%)
3. (tie) Muscogee, Forsyth (15%)
5. (tie) Cobb, Chatham, DeKalb, and Richmond (13%)

So where's Athens-Clarke, home of UGA? Would you believe 31st place? At 9 percent "excessive drinking?" Wow. I'm not sure that word, excessive, means what they think it means.

Methodology note -- not every county is measured on excessive drinking. Perhaps people there were too drunk to ask other drunk people how much they drink. So the rankings cover just 58 of 159 counties.