Friday, July 13, 2012

Two theoretical/statistical questions about directions of correlations, forgive my statistical ignorance, I really need help!
  1. When I search for relevant articles to support my arguments, I often come across correlational studies. Often, the correlations found from regression models seem non-directional (e.g. life satisfaction and self-esteem can influence each other bidirectionally) but the articles often base their discussion on one direction of the correlation (e.g. life satisfaction can be predicted from self-esteem). Would it still be appropriate to cite the same study in support of "self-esteem can be predicted from life satisfaction"?
  2. Can a longitudinal design really eliminate the plausibility of having a correlational conclusion in a direction opposite to your prediction? This is what I found in one article, but it seems like most people assume the directions of certain correlations without doubt, especially if it is based on longitudinal studies. "On a more general level we believe that there are three common, important and less widely recognized misunderstandings with respect to longitudinal study designs in occupational health psychology. The first of these is that we can prove causality by using longitudinal study designs. The extent to which causal inferences can be made depends on the following four conditions: temporal ordering of the focal variables, the strength of the statistical association between them, theoretical plausibility of the presumed causal relationship, and exclusion of plausible rival hypotheses for this relationship (2, unpublished manuscript by de Lange et al). While the first three conditions are relatively easy to satisfy with a longitudinal design, it is impossible to exclude the possibility that particular associations are due to variables that were not measured in the study design. Thus we can never prove causal relationships; the best we can do is argue that it is plausible that certain statistical associations can be understood in causal terms." 



Higgs Boson Explained in Animation!!

http://www.phdcomics.com/comics/archive.php?comicid=1489

A Comic about Research.... very fitting

http://www.phdcomics.com/comics/archive.php?comicid=1506

Thursday, July 12, 2012

Jennifer has her finger on the literary pulse...

After all our talk about Sebald today, I come home to find this link to a new National Review Article about W.G. himself. Jennifer, it's clear your chosen topic is in the public eye. I do hope that by the end of the summer you will give us a few suggestions for Sebald things we should read.

This article is a review of a new volume of Sebald's collected poems: Across the Land and Sea. I'm afraid this reviewer finds his prose better than his poetry...some of which is very obscure - "something like reading “The Waste Land” without the notes".

I remember reading, in college, Wolfgang Borchert's play The Man Outside. A story of the impossibility of returning home after war, I found it very moving at the time. There is a beautiful, quiet US film on the topic called "The Best Years of our Lives" which is well worth seeing.

News from Around the World

I'm always looking for new avenues of acquiring news from around the world and am especially interested in finding and learning from different perspectives. I was very excited to learn from Cydney about Watching America. It's a site that translates articles from other languages into English so readers can form an understanding of how the rest of the world is seeing us. Cool right? I wish I knew more languages so I could simply reading them from source, but this is the next best thing. Even better, Cydney has recently began translating for the site! Check her out: http://watchingamerica.com/News/165592/follow-the-money-2/

Higgs Boson Evidence

Higgs Boson Evidence on Science Friday

What Higgs Boson evidence actually looks like! :)