Wednesday, January 21, 2009

Does A Cold Shoulder Make You Colder?

Researchers wanted to determine whether recalling a past experience of feeling excluded could make people feel colder, as measured by participants' estimates of the ambient room temperature. Sixty five students were randomized into groups; one group was told to recall a past experience of being excluded, the other of being included. The difference in room temperature estimates was significant, with the first group estimating the temperature to be an average of 2.6 degrees (Celsius) colder.

A second experiment found that people who were excluded in a mock computer exercise were more likely to desire warm beverages than people in a control group. An ANOVA test was used.

Source

Sunday, January 18, 2009

Too Many Significance Tests

A study published in April 2008 (link) reported that a pregnant woman's diet could influence the gender of her baby. A particular claim was that eating breakfast cereals increased the probability of having a boy. A Science Daily piece from Jan. 17, 2009 reports on a recently published explanation that indicates the earlier result is easily explained by chance.

According tot he Science Daily article, 132 food items were tested during two different time periods, for a total of 264 statistical tests. At a 0.05 level of significance, this number of tests would lead to, on average, 13 false positives (Type I error: rejecting the null hypothesis when the null hypothesis is indeed true).

Thursday, January 15, 2009

Effects of Intercessory Prayer

Another British Medical Journal study tried to determine if intercessory prayer for hospital patients had any effects on their recoveries. All 3393 subjects had bloodstream infections. This randomized comparative experiment measured mortality, length of hospital stay, and duration of fever, and found a significantly lower mean in two of the three groups which were prayed for.

Want more controversy? The prayer was retroactive! That is, the pray-ers were praying for people who had been sick 5 to 10 years before the study was initiated.

P.S. BMJ is a great source. It's free, and they post complete articles.

Friday the 13th

(An oldie but goodie.) The British Medical Journal published an article about the connection between Friday the 13th superstitions and health. They conducted separate t-tests comparing number of shoppers in supermarkets, and number of drivers on the highway on Fridays the 13th and ordinary Fridays to gauge superstition. (Are people staying in on these days?) They also compared rates of traffic fatalites on the two kinds of Fridays.

Religion and Politics

The Pew Foundation's weekly report of surveys of the American people reveal some interesting trends in terms of people's views on the relationship between religion and politics. They report that a majority think it important that the President have strong religious beliefs; at the same time, for the first time a majority of Americans think that churches should stay out of politics. The site contains results, graphics, tables, and a link to a page that explains the survey methodology.

Tuesday, January 13, 2009

More on Cell Phones

The bad news about cell phones on the road keeps rolling in. Two insurance companies have estimate that about 7 in 10 of the 244 million cell phone users use their phones while driving, and that 10% of all U.S. drivers are using their phones at a given time. From the University of Utah, we learn
  • Hands-free phones are just as dangerous as hands-on.
  • Drivers using cell phones increase the likelihood of getting into an accident by four times.
(Source)

The latest news: Cell phones are more distracting than passengers. A study with 41 drivers randomly paired them as drivers and conversation partners. When the conversation was on a cell phone, drivers were more likely to drift from their lane, kept a longer following distance, and were four times more likely to miss their exit. (Source)

Monday, January 12, 2009

Sexy TV and Teen Pregnancies

The Rand Corporation claims to have found a link between exposure to sexual content on television and teen pregnancies. An article from MSNBC claims, "teens exposed to high levels of sexual content on television were twice as likely to be involved in a pregnancy in the following three years as teens with limited exposure." Researchers interviewed 2003 teens by telephone during the year 2001, then followed up 1 to 3 years later. The article reports specific findings, questions, and TV shows. (November 3, 2008)

Sunday, January 11, 2009

Lauging Gas and Suggestibility

ScienceDaily.com reports on a double-blind matched-pairs (within subjects) experiment conducted to determine if laughing gas makes users more prone to experience suggested imaginings. Why is this important? Perhaps dental patients will accept suggestions to be more relaxed during treatment.

"During each session, participants were given a series of mental imagery tests and were asked to rate their response according to a scale of 1-7, where 1 was ‘as clear and vivid as the real thing’ and 7 was ‘no image present at all’. For example, participants were asked to close their eyes and imagine tasting oranges or smelling roast beef, feeling linen or hearing the honk of a car horn." (Source)

Two other examples given are suggestions of voices from a non-existent audio-speaker asking questions and a sour taste in their mouth. The researchers claim that both susceptibility and imaginative ability were enhanced by the nitrous oxide.

Friday, January 9, 2009

Early C-Sections associated with risk

The New York Times reports a study (Dr. Alan T.N. Tita at the University of Alabama) about Caesarean sections. Early C-sections (37 weeks) are associated with increased risks in several categories.

Researchers examined records of 24,077 Caesarean deliveries performed at term, 6.3% (n = 834) of which were performed at 37 weeks, 29.5% (n = 3909) at 38 weeks, 49.1% (n = 6512) at 39 weeks, 10.4% (n = 1385) at 40 weeks, and the rest (2.6%, n = 618) after 40 weeks.

Overall, 15.3% (n = 128) of babies delivered at 37 weeks had some type of complication, compared to 11% (n = 430) at 38 weeks, 8.0% (n = 524) at 39 weeks, and 7.3 % (n = 101) at 40 weeks. Complications include respiratory distress syndrome, hypoglycemia, infections, or the need for neonatal ICU.

The study appears in the January 8 issue of the New England Journal of Medicine.

Thursday, January 8, 2009

Teen Birth Rates

USA Today (and lots of other newspapers) give details from a CDC report about teen birth rates across the US in 2005 and 2006. The Seattle Post Intelligencer has a useful graphic to explore. Percentages are reported. The data are available at the CDC website.

Wednesday, January 7, 2009

Energy Drinks and Risky Behavior

Kathleen Miller surveyed college students to determine if there is any association between energy drink consumption and various risky behaviors. The answer? Yes! People who consume energy drinks more than five times per month are significantly more likely to smoke, fight, abuse prescription drugs, among other behaviors. The author carried out a correlational study. More details at http://www.sciencedaily.com/releases/2008/07/080724150438.htm.

Science Daily

Science Daily gives synopses of much of the latest scientific research in the news. It is an excellent source when searching for science that uses statistical tools. Classroom examples abound. Scanning the articles can point you in the right direction for relevant real-world data. You can sign up for weekly emails with links to the articles in several categories of interest.

Nature Walks Aid Memory

Berman et al report in Psychological Science (December, 2008) that walks in the woods enhance people's ability to perform memory-related tasks. This study describes randomized comparative experiments conducted between groups who walked through an arboretum and others walking in an urban setting. Those who walked in the woods after learning to perform a certain memory task showed significant improvement. Those who walked through the city showed none. A second experiment had participants view pictures of nature or city settings instead of walking, with the same results: significant improvement for those who viewed nature pics, none for those who viewed urban scenes.

The study contains results from t-tests and ANOVA tests. A synopsis of the study can be viewed at http://www.sciencedaily.com/releases/2008/12/081218122242.htm.

Tuesday, January 6, 2009

MySpace and Personal Information

The journal Archives of Pediatric and Adolescent Medicine published two studies of 18 to 22 year olds who use the social networking site MySpace. The first reports the rates at which men and women include content about sexual behavior, drug use, and violence, and associations with other factors. Here is the abstract. The second study gives the results of a randomized controlled experiment in which an email intervention is sent to students from "Dr. Meg." Does this influence whether MySpace users change the content or privacy settings at their sites? Click here for this abstract. You can also read a Washington Post article about this study.

Thursday, January 1, 2009

Americans on the Move

USA Today (online, December 31, 2008) posted a story about the rates at which Americans are moving from one state to another. Their method of sampling involves using statistics from two interstate moving companies. Data includes number of moves, and percentages moving in and out of each state. The print version contains graphics not available on the web.

Football: Scoring drive starting position

The New York Times (January 1, 2009) posted an article about determining first downs by moving the chains in football. Embedded in the article are two graphics: the first shows the average number of points per drive versus starting position of the drive; the second shows the distribution of starting drives. Both graphics use all NFL games from 1998 to the present.

Religion Surveys

The Pew Forum contains lots of information on public opinion polls related to religion, faith, and values. For example, here is an article today that reveals what Americans think about people of faiths different from their own.

College Alcohol Study

The Harvard School of Public Health maintains the College Alcohol Study website. There is plenty of data there that compares various rates of alcohol use and abuse among college students, past and present. See for example: http://www.hsph.harvard.edu/cas/What-We-Learned-08.pdf

Driving and Cell Phones

Does cell phone use impair driver reaction time? The following article includes information about t-tests they conducted in a randomized comparative experiment. You might find more information (and more recents studies) at the site for the Applied Cognition Lab at the University of Utah.

Strayer & Johnston, Psych. Science, vol. 21, 2002, pp. 462-466.

Comparing Affectionate Behaviors

This study compares several affectionate behaviors of married and dating partners (hugging, sitting close, kissing, winking, etc.). It's memorable for students because they are usually surprised to find out married people (at least according to this study) are more affectionate than those who are dating.

You might have to use inter-library loan to get your hands on the complete study. Email me if you would like a copy of the relevant data table.

Punyanunt-Carter, N M. "Reported Affectionate Communication and Satisfaction in Marital and Dataing Relationships." Psychological Reports 95 (2004): 1154-1160.

Old Faithful

This is a variation on a theme that appears in lots of places. The pattern of geyser eruptions for Old Faithful in Yellowstone National Park has changed over the years. (Some attribute this to a 1998 earthquake.) The bimodal aspect of inter-eruption times in 1985 seems to have disappeared by 2003. The data set here gives students an idea why exploring data graphically is important. Histograms (or dotplots) reveal information that summary statistics, boxplots, and t-tests would conceal.

Innate Mathematical Ability

A NY Times article (9/16/2008) describes an experiment to measure innate mathematical ability. The accompanying applet tests the ability to recognize - at a glance - which quantity of dots, blue or yellow, is more numerous. A running proportion of times the quantity is correctly identified is recorded. My students enjoyed taking the test, and the data collected can be used for an in-class t-test. Here are the links to the article and the applet.