Archive | Methods/Stats RSS feed for this section

Social science and the Pentagon

19 Jun

Pentagon preparing for mass civil breakdown

Social science is being militarised to develop ‘operational tools’ to target peaceful activists and protest movements

This would be a good article to discuss ethics and political motives with social science research.

Dancing statistics

10 Oct

Statistics Explained Through Modern Dance: A New Way of Teaching a Tough Subject

in Math | October 1st, 2013 2 Comments

You want a gentle introduction to statistics, and maybe those Khan Academy videos aren’t quite working out for you. Well, here’s another approach: statistics explained with modern dance. That’s the novel approach explored by Lucy Irving (Middlesex University) and Andy Field (University of Sussex), who produced four short films demonstrating different statistical concepts through dance. The films touch on Correlation, Frequency Distributions, Sampling and Standard Error, and Variance. Speaking about the project, Irving explained: “We worked with the choreographer and experimented with the dancers to find ways of communicating the concepts.  Our hope is that, as well as being fun and educational, the films will demystify and take some of the fear out of statistics.  Students often report that ‘the stats’ are the most difficult part of their psychology degree and these the films aim to challenge this by demonstrating that thinking about them in new ways may make them easier to comprehend.” You can follow Lucy on Twitter at @statsdancer.

Central Limit Theorem

10 Oct

Many real-world observations can be approximated by, and tested against, the same expected pattern: the normal distribution. In this familiar symmetric bell-shaped pattern, most observations are close to average, and there are fewer observations further from the average. The size of flowers, the physiological response to a drug, the breaking force in a batch of steel cables — these and other observations often fit a normal distribution.

There are, however, many important things we would like to measure and test that do not follow a normal distribution. Household income doesn’t — high values are much further from the average than low values are.

But even when raw data does not fit a normal distribution, there is often a normal distribution lurking within it. This makes it possible to still use the normal distribution to test ideas about non-normal data. This hidden normal distribution is revealed by collecting samples of multiple observations, and calculating the average for each sample. As the number of observations in each sample increases, the distribution of these averages becomes more and more similar to the normal distribution. The existence of this hidden normal distribution is known as the Central Limit Theorem.

Cuddling more important to men

10 Jul

This is a good report to critique.

Circular statements:
“”For them, an affectionate hubby leads to more sexual pleasure.”
“We have had ups and downs in our sexual relationship over the years, but I have to say that the times when we were having an active sex life was when I was happiest in our marriage.” When things are going well, couples will be more likely to be more active in their sex life.

The last statements contradict and be detached from the purpose of the article: “This study may also offer comfort to many men who think they’re the only ones whose wives or girlfriends aren’t always interested in sex.
Perhaps this will soothe some of the men in their thirties and forties who think that their situation of having a wife who is not all that enthusiastic about sex is unique,” said Zoldbrod.”

It does point out one of the study’s own weaknesses: “However, experts say sexual satisfaction is difficult to measure, and it could also be the case that study participants define it in different ways.” It is also cautious to make the international comparison significant.

Declining birthrates in the US.

8 Jun

This could be used with discussion on population and change.
The article is also a good example of invisible white normativity. Interesting fact about dogs outpopulating children.

Fun example of how facts can be skewed

30 May

This site has two videos of Ned and Edna. Should they stay together? The yes video is different from the no video, although they are talking about the same people and same relationship.
This is a fun example of how results and facts can be skewed to the reporter’s fancy. I would use this when discussing methods.

U.S. racial segregation in cities and population stats

30 May

The census info is available online by state and if you dig around, I did see it by census tract somewhere online.

This site has county-specific data, very neat stuff!

The NPR story below addresses how segregation is diminishing but at a very slow pace. Immigration is not helping neighborhood integration either.

Another interactive site with population stats by county: