• Enter your email address to follow this blog and receive notifications of new posts by email.

    Join 49 other followers

  • March 2019
    S M T W T F S
    « Jan    
  • Recent Bookmarks:

  • Archives

  • Categories

  • Advertisements

Gun Ownership by Country


Smaller Sample Size, Please

This is an interesting tidbit from David Lykken’s “Professional Autobiography” that was once available on the webpage of the U of MN’s Psych department website:

When I was a graduate student circa 1950, I had a job for several months in the Student Counseling Bureau analyzing the returns from a “After High School What?” survey that one of the counseling faculty had administered to 57,000 seniors in Minnesota high schools. In the basement of Eddy Hall, I would run boxes of IBM cards, each bearing the responses of one student, through the IBM sorting machine. A few years later, when I was on the faculty myself, Paul Meehl and I used those data for our unpublished “crud factor” study in which we showed that, in psychology, everything is related to everything else, at least a little bit. We cross-tabulated all possible pairs of 15 categorical variables on the questionnaire and computed Chi-square values. All 105 Chisquares were statistically significant and 96% of them at p less than 10-6. Thus, we found that a majority (52%) of Episcopalians “like school” while only a minority (47%) of Lutherans do. Fewer ALC Lutherans than Missouri Synod Lutherans play a musical instrument.

What this silly-sounding study implies is that Group A is bound to differ from Group B on Variable X so that, if your theory predicts that A > B, you have about a 50:50 chance of confirming that prediction empiricallyat least if you have a large enough sampleeven if your theory is dead wrong.

Meehl used these data as illustrations in a 1967 paper in Philosophy of Science. He pointed out that the physical sciences, whose theories are strong enough to permit point predictions (Group A will average 125% of Group B’s score, rather than merely A > B), use significance tests in a way that is obverse to the way they are used in the soft sciences. Psychologists say, e.g., that X and Y will be correlated positively and, if that much proves true, then we try to “reject the null hypothesis” by showing that the correlation is so far above the zero or null point, that there is less than one chance in 20 (or more) that the true value of the correlation (which our obtained value estimates) could be as low as zero.

One unhappy consequence of this way of proceeding is that our conclusions become more suspect as our experiment gets better! If we use good, reliable measures of X and Y, then we are more likely to detect the (almost inevitable) correlation between them, and the larger our sample, the more likely it is that this detected correlation will be statistically significant, i.e., have a small enough sampling error and be far enough from zero to believe it really is not zero. A cheap, crappy experiment with poor measures and a small sample that can report a statistically significant result is therefore regarded as more persuasive than a good, big study!

I’ve added some bolding for emphasis. This form of data-mining isn’t really discussed anywhere, from what I can tell, in the popular press or even in academic settings.

Professor Lykken’s autobiography is worth a read.

Interesting Abstract

Aspartame consumption is implicated in the development of obesity and metabolic disease despite the intention of limiting caloric intake. The mechanisms responsible for this association remain unclear, but may involve circulating metabolites and the gut microbiota. Aims were to examine the impact of chronic low-dose aspartame consumption on anthropometric, metabolic and microbial parameters in a diet-induced obese model. Male Sprague-Dawley rats were randomized into a standard chow diet (CH, 12% kcal fat) or high fat (HF, 60% kcal fat) and further into ad libitum water control (W) or low-dose aspartame (A, 5-7 mg/kg/d in drinking water) treatments for 8 week (n = 10-12 animals/treatment). Animals on aspartame consumed fewer calories, gained less weight and had a more favorable body composition when challenged with HF compared to animals consuming water. Despite this, aspartame elevated fasting glucose levels and an insulin tolerance test showed aspartame to impair insulin-stimulated glucose disposal in both CH and HF, independently of body composition. Fecal analysis of gut bacterial composition showed aspartame to increase total bacteria, the abundance of Enterobacteriaceae and Clostridium leptum. An interaction between HF and aspartame was also observed for Roseburia ssp wherein HF-A was higher than HF-W (P<0.05). Within HF, aspartame attenuated the typical HF-induced increase in the Firmicutes:Bacteroidetes ratio. Serum metabolomics analysis revealed aspartame to be rapidly metabolized and to be associated with elevations in the short chain fatty acid propionate, a bacterial end product and highly gluconeogenic substrate, potentially explaining its negative affects on insulin tolerance. How aspartame influences gut microbial composition and the implications of these changes on the development of metabolic disease require further investigation.

Low-dose aspartame consumption differentially affects gut microbiota-host metabolic interactions in the diet-induced obese rat.

Interesting Abstract

Taking notes on laptops rather than in longhand is increasingly common. Many researchers have suggested that laptop note taking is less effective than longhand note taking for learning. Prior studies have primarily focused on students’ capacity for multitasking and distraction when using laptops. The present research suggests that even when laptops are used solely to take notes, they may still be impairing learning because their use results in shallower processing. In three studies, we found that students who took notes on laptops performed worse on conceptual questions than students who took notes longhand. We show that whereas taking more notes can be beneficial, laptop note takers’ tendency to transcribe lectures verbatim rather than processing information and reframing it in their own words is detrimental to learning.

The Pen Is Mightier Than the Keyboard, Advantages of Longhand Over Laptop Note Taking. Authors: Pam A. Mueller, Daniel M. Oppenheimer

Source, Link to Paper.

Tech is bad for Kids

Also, good parents are good for kids.

New York (Reuters) – Recollections of strict, unaffectionate parents were more common among young adults with an unhealthy attachment to Internet use, compared to their peers, in a new Greek study.

Young adults who recall their parents being tough or demanding without showing affection tend to be sad or to have trouble making friends, and those personality traits raise their risk of Internet addiction, the researchers say.

“In short, good parenting, including parental warmth and affection, that is caring and protective parents, has been associated with lower risk for Internet addiction,” said lead author Argyroula E. Kalaitzaki of the Technological Education Institute (TEI) of Crete in Heraklion, “whereas bad parenting, including parental control and intrusion, that is authoritarian and neglectful parents, has been associated with higher risk for addiction.”


SOURCE: http://bit.ly/1m8inLg Addictive Behavior, online December 8, 2013.

Interesting Abstract

Throughout their lives, women provide for their own and their children’s and grandchildren’s needs and thus must minimize their risk of incurring physical harm. Alliances with individuals who will assist them in attaining these goals increase their probability of survival and reproductive success. High status in the community enhances access to physical resources and valuable allies. Kin, a mate, and affines share a mother’s genetic interests, whereas unrelated women constitute primary competitors. From early childhood onwards, girls compete using strategies that minimize the risk of retaliation and reduce the strength of other girls. Girls’ competitive strategies include avoiding direct interference with another girl’s goals, disguising competition, competing overtly only from a position of high status in the community, enforcing equality within the female community and socially excluding other girls.

The development of human female competition: allies and adversaries
Joyce F. Benenson

You’re Not Special; Multitasking is Bad for You


Chronic media multitasking is quickly becoming ubiquitous, although processing multiple incoming streams of information is considered a challenge for human cognition. A series of experiments addressed whether there are systematic differences in information processing styles between chronically heavy and light media multitaskers. A trait media multitasking index was developed to identify groups of heavy and light media multitaskers. These two groups were then compared along established cognitive control dimensions. Results showed that heavy media multitaskers are more susceptible to interference from irrelevant environmental stimuli and from irrelevant representations in memory. This led to the surprising result that heavy media multitaskers performed worse on a test of task-switching ability, likely due to reduced ability to filter out interference from the irrelevant task set. These results demonstrate that media multitasking, a rapidly growing societal trend, is associated with a distinct approach to fundamental information processing.

I have made it a point to no longer have, ever, more than one screen on around me at one time. And I even make it a rule not to jump around from one article to the next when I working through a reading list. I read one article completely before moving on to the next.

Social Sciences – Psychological and Cognitive Sciences: Eyal Ophir, Clifford Nass, and Anthony D. Wagner, Cognitive control in media multitaskers. PNAS 2009; published ahead of print August 24, 2009, doi:10.1073/pnas.0903620106

Random Link


Justifiable Homicide

Keith Ellison on 9-21-06, taken by user.

Keith Ellison on 9-21-06, taken by user. (Photo credit: Wikipedia)

The Trayvon Martin shooting has put ‘Stand Your Ground’ legislation at the center of the national second-amendment/self-defense debate. Among others, Keith Ellison has raised the issue of these laws at the national level:

Democrats backed off of their effort Tuesday to offer a “Trayvon amendment” to pressure states to drop their stand-your-ground laws after learning it was likely to be ruled out of order under the evening’s rules for debate on the House floor.

Rep. Keith Ellison, Minnesota Democrat, said he will still try to force a debate at a more “appropriate” time in the future, saying action is demanded by the case of Trayvon Martin, the Florida teenager who police said was shot dead in a street encounter with a neighborhood watch volunteer.

The Ellison amendment would have docked federal criminal justice grants to states that have stand-your-ground laws, which allow residents to use deadly force to respond to an attack without first having to retreat.

Ellison et al. cite the increase in ‘justifiable homicides’ in recent years as a reason to re-evaluate these laws.

So, I looked up the numbers, and they’re right. Justifiable homicides are up:

But look closely at the graph. If Justifiable homicides are up because of ‘stand your ground’ (SYG) laws, we should see independence between private citizens and police, i.e. there should be a lack of correlation between the two groups of people. Police are held to a different standard than private citizens; they are expected to approach dangerous situations, and don’t have the option of retreat or avoidance. Thus police are given more leeway (and rightfully so).

Wait! Those are old numbers!

Here are some more recent numbers from Florida:

Again, check out the high correlation between police and citizens.

So why are police and private citizen numbers so closely correlated? The two lines are nearly identical in shape. In theory, there should be an increase in justifiable homicides among private citizens with no corresponding increase in police shootings. But that isn’t the case.

It is my opinion that other factors are at work. Either demographics are shifting, crime rates vary (maybe copper thievery comes into vogue, reducing the number of violent encounters) or something else is going on. A state by state study looking at the rates of justifiable homicide before and after SYG laws would give us a clearer answer. Perhaps a small relationship can be found. Even if that happens, it is still important to remember justifiable homicides are deemed such for normally good reasons. A ‘justifiable homicide’ is when an attempted homicide goes bad for the bad guy. Overrall, violent crime is down across the country. Increased guns and carry permit holders might be part of the reason. We should not surrender the civil right to self-defense because of one very sad incident, as painful as it might be for those involved.

(Here’s another interesting post on the subject. The main takeway being how small the change has been over the past decade and how details are lost in the reporting.)

The D’oh of Keynesianism

The great success of government intervention in the economy, so far this century, has been convincing people to leave the labor market.

Update: Mitch Berg does some simple math to show us how the shrinking workforce affects the total number of people working. Basically, while the U3 and even U6 numbers show improvement, the total percent of people working compared to the total population is in fact dropping.

And it looks like things might be getting worse.