I don't understand the distinction you're making; if a relationship between two variables holds at one level of a third variable but not at another level, that is a legitimate statistical interaction by definition (assuming a significant interaction term). ________________________________ From: Lilienfeld, Scott O [slil...@emory.edu] Sent: Monday, June 14, 2010 6:15 PM To: Teaching in the Psychological Sciences (TIPS) Subject: RE: [tips] a recent corr/causation example
This study, which I haven’t read, raises another question (in addition to the correlation-causation question) that I always find interesting to ponder…when does detecting an effect in one group (e.g., African-Americans) but not another (e.g., Hispanics) constitute a legitimate statistical interaction vs. a failed replication? And is the author justified in interpreting it as the former rather than latter, as he seems to be? It’s something I struggle with, and I’d be curious to hear others’ thoughts. ….Scott Scott O. Lilienfeld, Ph.D. Professor Editor, Scientific Review of Mental Health Practice Department of Psychology, Room 473 Psychology and Interdisciplinary Sciences (PAIS) Emory University 36 Eagle Row Atlanta, Georgia 30322 slil...@emory.edu (404) 727-1125 Psychology Today Blog: http://www.psychologytoday.com/blog/the-skeptical-psychologist 50 Great Myths of Popular Psychology: http://www.wiley.com/WileyCDA/WileyTitle/productCd-140513111X.html Scientific American Mind: Facts and Fictions in Mental Health Column: http://www.scientificamerican.com/sciammind/ The Master in the Art of Living makes little distinction between his work and his play, his labor and his leisure, his mind and his body, his education and his recreation, his love and his intellectual passions. He hardly knows which is which. He simply pursues his vision of excellence in whatever he does, leaving others to decide whether he is working or playing. To him – he is always doing both. - Zen Buddhist text (slightly modified) From: David Hogberg [mailto:dhogb...@albion.edu] Sent: Monday, June 14, 2010 6:01 PM To: Teaching in the Psychological Sciences (TIPS) Subject: [tips] a recent corr/causation example from today's Reuters Health Report: Murder rates affect IQ tests scores: study Maggie Fox<http://blogs.reuters.com/search/journalist.php?edition=us&n=maggie.fox&;>, Health and Science Editor WASHINGTON Mon Jun 14, 2010 5:36pm EDT WASHINGTON (Reuters) - A murder in the neighborhood can significantly knock down a child's score on an IQ test, even if the child did not directly witness the killing or know the victim, U.S. researchers reported on Monday. <http://www.reuters.com/news/us> The findings have implications both for crime control efforts and for the heavy reliance on standardized tests, said New York University sociology professor Patrick Sharkey, who conducted the study. They can also explain about half the achievement gap between blacks and whites on such tests, he reported in the Proceedings of the National Academy of Sciences. "It means being more aware of the potential for violence to have a reach that extends beyond just those victimized and those who witness a violent event, to reach across a community and affect all children in a community," Sharkey said in a telephone interview. Sharkey compared data on crimes broken down to within a few blocks in a neighborhood with school test scores. He collected details of more than 6,000 murders in the Chicago area and the results of two surveys of children and families in Chicago neighborhoods. The surveys included scores from tests that are used to determine a child's IQ. If a murder occurred in a child's neighborhood -- an area of roughly six to 10 square blocks as denoted by the U.S. Census -- the children's test scores fell by an average of half a standard deviation, Sharkey reported. On an IQ test using 100 as the average or norm, one standard deviation is 15 points. So if a child took the test within a week of a local murder, his or her score was 7-8 points lower on average than the score of a similar child in a similar neighborhood where there was no murder. This fits in with what is known about the effects of post traumatic stress, Sharkey said. "The results suggest that children may carry the burden of violence with them as they take part in daily life within the neighborhood or school settings," he said. PASSING EFFECT The effects wear off after a week to nine days, Sharkey found. But in areas with a lot of crime, this does not provide much relief. "When one takes into account the prevalence of homicide in the most violent neighborhoods in cities like Chicago, these results mean that some children spend about one week out of every month functioning at a low level as they navigate the home or school environment," he said in a statement. In general, black U.S. children score about one standard deviation lower on standardized tests than white children. This finding accounts for half that difference, Sharkey said. He was unable to find enough murders in predominately white neighborhoods to see if white children were affected. Curiously, there were enough murders in Hispanic neighborhoods but Latino children seemed unaffected. "I just didn't find the same effect," Sharkey said. It could be the Hispanic children did not identify with the violence, Sharkey added. "Most of the victims, even in the Hispanic neighborhoods, were black." It is well documented that blacks are far more likely to be murdered than members of any other U.S. ethnic group -- murder is the most common cause of death for young black men. Sharkey said the findings also have implications for IQ tests, which are supposed to be neutral assessments of ability. "These tests are not purely capturing some underlying intelligence," he said. -- David K. Hogberg, PhD Professor of Psychology, Emeritus Department of Psychological Science Albion College Albion MI 49224 Tel: 517/629-4834, Mobile: 517/262-1277 --- You are currently subscribed to tips as: slil...@emory.edu<mailto:slil...@emory.edu>. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13509.d0999cebc8f4ed4eb54d5317367e9b2f&n=T&l=tips&o=3082 (It may be necessary to cut and paste the above URL if the line is broken) or send a blank email to leave-3082-13509.d0999cebc8f4ed4eb54d5317367e9...@fsulist.frostburg.edu<mailto:leave-3082-13509.d0999cebc8f4ed4eb54d5317367e9...@fsulist.frostburg.edu> ________________________________ This e-mail message (including any attachments) is for the sole use of the intended recipient(s) and may contain confidential and privileged information. If the reader of this message is not the intended recipient, you are hereby notified that any dissemination, distribution or copying of this message (including any attachments) is strictly prohibited. If you have received this message in error, please contact the sender by reply e-mail message and destroy all copies of the original message (including attachments). --- You are currently subscribed to tips as: mbour...@fgcu.edu<mailto:mbour...@fgcu.edu>. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13390.2bbc1cc8fd0e5f9e0b91f01828c87814&n=T&l=tips&o=3083 (It may be necessary to cut and paste the above URL if the line is broken) or send a blank email to leave-3083-13390.2bbc1cc8fd0e5f9e0b91f01828c87...@fsulist.frostburg.edu<mailto:leave-3083-13390.2bbc1cc8fd0e5f9e0b91f01828c87...@fsulist.frostburg.edu> --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=3085 or send a blank email to leave-3085-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
