67/100: That's like, a serious majority or something, dude

I read somewhere that between one-third and one-half of American Colonists were either actively sympathetic to the Rule of The Crown and the status quo, or were such low information subjects that they weren't even paying attention to Thomas Paine.

How one would go about gathering data on the attitudes of folks in the 1770s and 80s is a mystery to me. This, not so much. Via Instapundit.com:

THE WAGES OF FAILURE: Blame Obamacare: 7 in 10 think the federal government stinks. “The disastrous rollout of President Obama’s signature healthcare initiative has helped to crater the faith Americans have in the federal government, with only 19 percent having a favorable view of Washington and a shocking 67 percent with an unfavorable view.”

Good morning!

"... common business procedures with which every one should be familiar... ."

From the Preface to Junior Business Training by Frederick G. Nichols (American Book Company, New York, 1923) a text book for "boys and girls in junior high schools." The book has two parts, the first aimed at every one, "regardless of his vocational aim."

Page 16: Cash Account.

The task, as illustrated above, was to keep a detailed record of your family's household spending for one month. [Chick to enlarge. $3.50 on the telephone bill!]

What a crappy old idea! Familiarizing kids-- in junior high, no less!-- with how to manage money! What good is that going to do them in the real world? Good grief. Fortunately we as a society are well over that  crappy old notion. We now know what kids in junior high really need to learn to become productive members of society.

In Grade 8, instructional time should focus on three critical areas: (1) formulating and reasoning about expressions and equations, including modeling an association in bivariate data with a linear equation, and solving linear equations and systems of linear equations; (2) grasping the concept of a function and using functions to describe quantitative relationships; (3) analyzing two- and three-dimensional space and figures using distance, angle, similarity, and congruence, and understanding and applying the Pythagorean Theorem.

 I don't know about you, but I use bivariate linear equations every day. 

         ∑ xy
r =  ----------
               2     2
      √ ∑x   ∑y

See? I just used one! Pearson's correlation coefficient.

[Just to be clear, note that in the denominator, it's the square root of the sum of all x's squared times the sum of all y's squared. That was the best square root symbol I could find.]

You have 10 minutes, Mississippi!

Daughter C sent me a link to an article with some photos of crappy old stuff -- no, "crappy old stuff" is reserved for stuff I like. There was nothing to like about what was pictured. The article, by one Brian Galindo, begins:

Last week, in a 5-4 decision, the Supreme Court struck down Section 4(b) of the 1965 Voting Rights Act, a key provision in the law that mandated nine states with a history of racial discrimination, mostly in the South, to get federal permission before they could change their voter laws. 

True enough. These are statements of facts, and last week's news. Tying these statements to photographs or scans of the literacy test-- which had to be completed perfectly within 10 minutes-- given to Blacks in Louisiana in the early 1960s implies that... what? The Supreme Court erred because nothing has changed in the South since the 1960s and Black Americans here don't or can't vote? That may be true. It may be false. But you know what, Brian Galindo? There is a way to actually find out which it is!

And so, I shall.

Let us ask, "Nationally, and for each state, what percentage of Black Americans voted in the 2012 election?" Call me silly, but I think this might be a pretty good indicator of whether or not the South needs to be babysat by the Feds when it comes to "voter laws."

Fortunately, The United States Census Bureau collects such data and makes it available on the World Wide Web for all to see. (I'm looking at you, Brian.) The data, in the form of MSExcel spreadsheets are here: Table 4b. Reported Voting and Registration by Sex, Race and Hispanic Origin, for States: November 2012

Nationally, 62.0% of Black Americans voted in the 2012 election-- so that's the average for the country. (FYI, I'm reporting data from the category "Black alone" meaning these are American who self-describe as only Black, contrasted with "Black alone or in combination" which would include mixed-race Blacks.)


Top & bottom states below the fold. 

And Speaking of Joseph Warren... | I Laughed So Hard I Almost Cried

A bit of background about why I found this article so so so funny... .

Yesterday I had occasion to learn a bit about Joseph Warren, who among other things, helped craft the Suffolk Resolves of 1774 which denounced Parliament after the Boston Tea Party. Paul Revere carried the Suffolk Resolves to the Continental Congress in Philadelphia.

And, as long time readers of the blog and I guess now just about every civil servant knows, I like data. So this cracked me up.

The betweenness centrality scores of some crappy old terrorists

The larger the score, the more connected a node is in the network-- in this case a "Social Networke" of suspected terrorists. Note that Warren is third most connected. Here's how the author of this really really really funny serious article describes it:

Once again, I remind you that I know nothing of Mr Revere, or his conversations, or his habits or beliefs, his writings (if he has any) or his personal life. All I know is this bit of metadata, based on membership in some organizations. And yet my analytical engine, on the basis of absolutely the most elementary of operations in Social Networke Analysis, seems to have picked him out of our 254 names as being of unusual interest. We do not have to stop here, with just a picture. Now that we have used our simple “Person by Event” table to generate a “Person by Person” matrix, we can do things like calculate centrality scores, or figure out whether there are cliques, or investigate other patterns. For example, we could calculate a betweenness centrality measure for everyone in our matrix, which is roughly the number of “shortest paths” between any two people in our network that pass through the person of interest. It is a way of asking “If I have to get from person a to person z, how likely is it that the quickest way is through person x?”

That's pulled from near the end of the article. Don't be put off by talk of tables and matrices. The author, Kieran Healy, does an awesome job of walking even the data-adverse through an analysis of a sample of metadata--nothing more than the names of 254 men, and their membership in one or more of seven organizations, that's all-- to uncover a treasure trove of information that culminates in a most interesting person of unusual interest. 

To give you a taste, here's how the article-- really a blog post-- begins:

fb | BIG Data

via Instapundit.com:

BIG DATA: Study: Facebook Likes Can Be Used to Determine Intelligence, Sexuality.

Simply by delving into volunteers’ Likes, the researchers could determine in 95 percent of cases whether a person was Caucasian or African American and in 88 percent of cases whether the person was heterosexual or homosexual. They could determine whether the person is Christian or Islamic 82 percent of the time.

The researchers described Facebook Likes as “a generic class of digital record that could be used to extract sensitive information.” Volunteers used the myPersonality Facebook app to track their Likes, which were fed into algorithms to arrive at the results. The data were supported by information from volunteer profiles and personality tests.

Of course some of these Likes are a no-brainer. Liking “Being Gay” is at least a decent indicator of one’s sexuality. Liking Barack Obama means there’s a good chance you’re voting Democratic next time around. This is not exactly rocket science. But some Likes appeared to have zero connection to personal attributes. Sure, curly fries are delicious, but is Liking them the best indicator that you have a high IQ? Also, one of the Likes that helped identify heterosexual men was “Being Confused After Waking Up from Naps.” Is that really a trait only straight men are afflicted with?

While the results can be seen as hilarious for anyone that’s not a Harley-Davidson rider (I kid), the privacy implications are alarming. Facebook Likes are public by default.

Facebook isn’t about privacy.

The Farm doesn't have a Facebook page.

1.5 People

For your amusement, via Breitbart:

Full image here

Wonder what becomes of the other half?

Oh! What fun!

via NRO's The Corner.

It's probably going to rain for the next couple of days and there's only so much rain-watching a body can do. 

How much fun am I going to have looking at these data?

First thought? Moving from Ohio Oiho Oihi to Mississippi That Landmass was a very smart move.

Second thought? If you are surprised by Texas, you haven't been paying attention.  

Third? What the heck is the color-coding scheme?

Pascal Meets Pickling

Mr. Big Food and I put up 12 pints and three quarts of four different kinds of pickled things this afternoon. It took about four hours-- we are experienced and efficient picklers. Music was playing in the background and we seldom run out of extraneous things to chat about, e.g., poor Randy. We guess he's not even going to be playing at State Fairs any more. It's one thing to be drunk, but quite another to be publicly drunk and publicly naked all at the same time. I have no sympathy.

That said, we'd sort of reached the end of the line. We fell one ring/lid rig short. 

I FOUND IT!

Over a month ago, I realized I didn't know where my Little Orange Book was. I looked, I asked, and yes, I accused. Who would have stolen my Little Orange Book from me?

Today, I am pleased to report that my Little Orange Book has been found and retrieved from behind the bookshelf thanks to  

• large barbeque tongs (not pictured; didn't work), 
• a dry-wall square (not pictured; used to push it to the other side of the bookshelf where the gap is larger), 
• carpenters' square (lever to raise it to where the gap is large enough for my hand), 
• flashlight (obvious), and 
• if I do say so myself, 

some good old fashioned America ingenuity.

It's much oranger than it appears. (Photo taken with the camera I hate.)

Just sayin'

Read this:

Math Is Hard  

"Most people killed or wounded in stray-bullet shootings were unaware of events leading to the gunfire that caused their injuries, and nearly one-third of the victims were children and nearly half were female, according to a new nationwide study examining an often-overlooked form of gun violence," according to a report from the University of California, Davis:


Unlike the risk pattern for violence in general, which typically affects young males, most victims of stray bullets were outside the 15-34 age range, and nearly half (44.8 percent) were females, the study found. 

Since these are random shootings, you would expect women and girls to be victims at roughly their proportion of the population, which is slightly over 50%--or maybe higher, if it turns out that the shootings are concentrated in urban areas with low sex ratios. The question, then, is not why so many victims of this type of shooting are female but why a disproportion of them (55.2%) are male.

From James Taranto's "Best of the Web" column at the Wall Street Journal today.

Was I not sayin' just the other day that we should think for ourselves, especially when it comes to numbers?

Just your Average American Thinking for Herself

The average American, who should consume about 2,000 calories a day, eats out six times a week. 

The second real sentence in an article by Margo Wootan at The Hill, "Eating in the dark can be dangerous."

Reading sentences like this automatically causes me to go into statistician geek mode. (Haha. That was a statistics joke.) Furthermore, reading sentences like this so early on in an article causes me to read the remainder more critically than I otherwise might have.

Please do read the whole thing yourself. If you are not so inclined, here is a brief summary with commentary followed by a little stats rant (fun stuff).
~~

People eat out more now than in the crappy good ol' days.

Your tax dollars at work

I'm actually o.k. with some agency of the Federal Government collecting data on the weather. I would voluntarily donate $1 every year to fund such an agency. Imagine what would happen if we were able to vote on every line item in the Federal budget, assuming there is one some day.

It would be fun to plot these data, from NOAA-- and agency that does far too much.

Think about it for a minute. This is what counts as income [insert short list: wages & compensation (not tips), rent you are paid, profit from sale of a product you produce or service you provide, interest on investments, etc.]. Add them up. Multiply by 0.10. This is what you owe the Federal Government for executing only Constitutionally mandated jobs. What follows is a list of Constitutionally Legitimate entities of the Federal Government. Please indicate, in whole cents, to which entities your payment should be allotted. The amounts must sum to at least the total you owe. If the sum is greater than what you owe, please include a check for the overage. Thanks!

Wouldn't that be a kicker? You like the EPA? Give it your all. What's given to the EPA by the Citizens will be what the EPA has to work with next year. Think your Senator deserves a pay cut? Give him one. 

If I were to give $1 to an agency that collected, and made public, data on the weather, I would  insist that the folks working at the agency and doing the reporting report medians, not averages. You cannot average a date. It just don't make no sense. See? That's how to make folks accountable. Pay them and expect them to do a good job.

Of course, we'd have to look into the legitimacy of this agency-- and a lot of others.

Record keeping: Is 60 too many?

03/03/2010

Today I planted tomato seeds in 60 peat pots, so if all goes well, I should have somewhere in the neighborhood of 60 tomato plants to plunk into the ground around the end of April. Looking at this photo of pepper seedlings from two years ago makes me feel as if I am behind-- and I certainly am compared to 2010-- but there's still plenty of time. When it comes to tomatoes, peppers, eggplant and so on, there's just no point planting in the ground before the last of April.

But to answer the question, "Is 60 too many?": No. Not for Mr. Big Food and me! 

According to the experts,

 "... motor vehicles discourage walking."

What an insight!

Car owners with a television are 27 percent more likely to suffer heart attacks than people who have neither, according to a global study on physical exercise and heart disease published Wednesday.

It's hard to know where to begin. The article tells us that the lead researcher is "Claes Held, a professor at Uppsala University in Sweden" and that the study was published in "the European Heart Journal." We are also told that the study covered "more than 29,000 people in 52 countries." Isn't that nice? A sample that represents 4/1000th of 1% of the population.

Of course, there's no actual link to the study, or even any real citation information. But here's all you need to know from this scientific study-- at least all the unnamed author of the article thinks you need to know. All emphases mine. 

(Information on Mississippi also below the fold.) 

Stats and guns

In my travels around the World Wide Web the other morning, I came across this:

Rob is very explicit that there is no positive correlation between violent crime and liberalized carry laws rather than a proven negative correlation. He feels that it will take more rigorous statistical analysis before this negative correlation could be said to be proven. [my emphases]

[I'm not sure I like the use of the word "proven." But that's a nit to pick another time.]

Everyone knows statistics lie, right? Wrong. Statistics are numbers. Numbers do not have brains and thus cannot tell a lie. Human beings, on the other hand, can. Humans can-- and do-- manipulate numbers, images, words, and so on in order to lie. What I like very much about Rob-- and I'm assuming Rob is a gun-friendly guy-- is that he's careful about what these numbers do and do not show.

US violent crime rate vs. % US population living in shall issue and Constitutional carry states

The quote and graph come from "Every Picture Tells a Story, Part Two" at No Lawyers, Only Guns and Money (h/t Instapundit).

What these numbers show is exactly what Rob says they show: no positive correlation between violent crime rates and liberalized, i.e., less restrictive, gun laws.

A positive correlation is a relationship between two sets of numbers such that as one set increases, in this case over time, so does the other. A negative correlation is the opposite, as one increases the other decreases. Note that in both sorts of correlations, neither set of numbers is necessarily "more important" than the other. In the abstract (without time), if there is a positive correlation between A and B we can say

As A increases B increases,

and we can also say

As B increases A increases.

It doesn't matter that A come before B in the alphabet!

Likewise, we can just as well say that these data do not show states' gun laws becoming less restrictive as violent crime rates have fallen. Either way, these data do not show a positive correlation between A and B. 

Assuming that more rigorous statistical analyses do reveal a (strong) negative correlation between violent crime rates and increased liberalism (less restriction) over states' gun laws, what does that mean? It means there's a (strong) negative correlation. Period.  No one-- including Rob it I'll bet-- would should then say that less restrictive gun laws cause violent crime rates to go down. Correlation is not causation. Duh. To put it another way, no one should now say violent crime rates went down because more people were able to get concealed carry licenses.

I say "should" because some will say that. And they'd be wrong, given these data. Does it make sense to say that armed potential crime victims are better able to ensure they are not actual victims. Sure! 

5 in 1000

H/t Instapundit who links to Dailymarkets.com

Add caption; I would if I could think of one.

According to the National Shooting Sports Foundation, hunting with firearms is one of the safest recreational activities in America (here’s the press release and here’s the fact sheet with sources provided).

Here's the link to the whole short piece (where the links in the quote are hot). 

You know me, I have some questions about what counts as an "injury,"* but assuming what counts is consistent across activity, ... well the numbers speak for themselves, now don't they?

* I didn't follow the links. Are there differences in sample sizes? How were these data collected? Et cetera. That the data are presented "According to the National Shooting Sports Foundation" make me want to be particularly careful about the methodology of data collection and analyses, even though I like the result.

This, my friends, is what we should aim to teach our children. How easy would it be to take the numbers in this chart and make fun of those helmeted bicyclists who suffer injury at a three times a higher rate than gun tottin' hunters? Very easy. I won't do that. Because I haven't looked at the numbers.

A Thought Experiment, pt. 2

Imagine a group of 100 people. Any 100 people will work just fine. For the purposes of this thought experiment the "sample" doesn't have to be random, and we need no control group.

Imagine these folks have five choices-- what Mr. Big Food will grill when they all come out to the Farm next weekend. They can choose only one. 

[If you don't think Mr. Big Food can grill for 100+ people, I refer you to the first post here at Big Food, etc.: 260 Pieces of Chicken.]

The choices are:

1. Salmon

2. Vegetables

3. Chicken

4. Hamburgers (made from freshly ground sirloin tip)

5. Ribeyes

Each individual writes the numeral corresponding to his or her choice on a slip of paper and drops it in a box.

Mr. Big Food is very busy so he asks a colleague whose specialty is Experimental Philosophy to determine what will please most of the crowd when they show up at the Farm. This is an important task because we have to purchase what will be grilled. 

Mr. X-Phi happily agrees to help. Shhh... although I am very busy, I do a quick tabulation of my own:

Lest there be any mistake, I do know how to properly label a graph. What I don't know is how to get Numbers to properly label a graph. X-axis: Numeral corresponding to choice; Y-axis: # of people choosing each choice.

Soon, Mr. X-Phi reports to Mr. Big Food that 3-- chicken-- is the average response.

STOP RIGHT THERE. IF THIS MAKES SENSE TO YOU, GO BACK TO BED.

A thought experiment

Imagine two sets of 10 numerals that were specified to code for strength of a positive emotion/opinion versus strength of a negative emotion/opinion, such that "5" coded for "strongly disagree." and "1" coded for "strongly agree."

A: [1,5,2,4,3,1,5,2,4,3]

and

B: [1,5,1,5,1,1,5,1,5,5]

When you sum the numbers that the numerals stand for, the total is 30. There were ten participants. What's the average response?

Stop right there. If this question makes sense to you, go back to bed.

Look at the data!

In A, each of the five responses gets two "votes." That is what a null hypothesis looks like. There is not a consensus opinion. Respondents are just as likely to be neutral as they are to have a strong opinion.

In B, there is strong (dis)agreement.

To mistakenly report a statistic that cannot truly be reported, given the nature of the data, is a crime.

To be continued.