« November 2009 | Main | April 2010 »

March 31, 2010

Literature reviews

Notes from the U of M library course


MNCAT
Ideally you can find a book on the subject, as it should be thorough and comprehensive

ANNUAL REVIEWS
These are the next best option. Annual Reviews Database - field experts are invited to summarize current scholarly work on a topic. Consider searching all topics rather than the Public Health only. Wiley Interscience Database - more difficult to use because it incorporates all Wiley products. Use the advanced search and include "Compass" with your keywords to limit to the annual review.

DISSERTATIONS
Digital Dissertations includes abstract of most western European and N American institutions. There are other dissertation collections, or you can google. NDLTD, OpenDOAR, Repository66, WorldCat.

ALERTS/RSS
Many search tools will notify you when they find new matches to your old searches. You can also ask for citation alerts to see how a publication is received. You may need to look for a "help" link to find out how to use them.

SUBJECT LIBRARIAN

March 30, 2010

Publication process

The Publication Process

Notes from Biomed library presentation March 2010

Wayne A. Loftus, MLS, AHIP


Wayne A. Loftus, MLS, AHIP
Science Librarian, Health Sciences Libraries
University of Minnesota
loft0002@umn.edu

JOURNAL SELECTION
Choose early in process and write manuscript to their standards, rather than revise to meet them. Choose based upon
1 - readership
2 - impact/prestige
3 - Copyright policies (largely irrelevant to our field). Smaller publishers and those in non-NIH fields may not grant author open access permission - read the agreement! Often there is a second version for author's unsatisfied with the first.

SUBMISSION INSTRUCTIONS
Go to journal home page. Often found through the "About..." link.

REVIEW PART 1: ACADEMIC
Editor: Unpaid, top of field, does it for ego or commitment to the field.
Reads submissions and rejects (out of scope or failed to meet submission guidelines) or sends to reviewers.
Reviewers: General goal is to make the paper better. If they misunderstand a point, clarify.

Revise and resubmit is an encouraging rejection. This means you will need another peer review, so you may as well send to another journal.

REVIEW PART 2: BUSINESS
Managing editor handles business side - copyrights, etc.
Copy editor makes corrections/clarifications - do what they suggest

PROOFS
Author is in charge of quality control/proofreading, so go through it carefully.

OPEN ACCESS
http://www.lib.umn.edu/scholcom/
http://publicaccess.nih.gov/
http://www.pubmedcentral.nih.gov/
NIH funded must submit author's manuscript (can be final Word document, as opposed to journal's PDF's) within 12 months of acceptance. Most publishers will help.

March 26, 2010

Stratify despite no interaction?

Q: I have a statistically significant association between y and x, adjusting for z. If I add an x*z interaction term the p value is well above 0.10, but if I choose to stratify one stratum has a statistically significant association and one does not. How can this be?

A: First I though this could be figured out by plotting the data, suspecting the ranges didn't overlap. The scatterplots were similar. Then I looked at the regression coefficients and confidence intervals. The coefficients were almost identical (and very small in clinical terms). One group had a slightly wider CI.

Figure A: The slopes are similar, though not identical

Figure B: Add the CI and one crosses horizontal, so the slope is not statistically significant

Figure C: Overlay the two slopes and you clearly cannot say they are different, so an interaction term will be non-significant

interaction.bmp

Conclusion: This could be put in the "Beware of p-values" category. There is probably an inverse but weak association between X and Y. At an intuitive level there is no difference between the two groups, so stratifying the data is not justified.

March 20, 2010

MAGNITUDE, direction and statistical significance

From a response to a question:

In what I took as Epi 2 we were drilled on always reporting the direction, statistical significance and MAGNITUDE of associations. There are two ways to get the magnitude:

If you run a simple correlation it is the correlation coefficient. SAS output gives that, the sample size and the p-value. The r and the n determine the p, so I suppose you can use any two to approximate the third. If you report a "significant" finding it could be

A) r=0.9 n=10 p=0.05 or
B) r=0.1, n=10,000 p=0.04

In either case they are "associated", but in the first case the association "explains" 1 percent and in the second it "explains" 81 percent of the variation.

This is worse when findings are described as 'not significant'. Association A could be 'not STATISTICALLY significant' if the p-value is 0.0501, but I would certainly say it is CAUSALLY significant. (Meaning that there is an association, confounded or not.)

Another expression of magnitude is the regression coefficient. If changing caloric intake explains 100% of weight loss that's great, but it may or may not be useful in obesity prevention. If you have to cut 5,000 kcal per day to lose 1 pound a year then it is a worthless public health strategy.

March 16, 2010

Hierarchical group means


When analyzing randomized groups by their individual measurements the degree of imprecision can/should be used to "shrink" the estimated group mean towards the overall mean, as shown below.

Overall mean is given by the yellow RR crossing shape.

Note that taking a simple group mean and taking a mixed model hierarchical group mean gives a different ranking of the black and red groups. This is because the red dots are closer (more precise).

Shrinkage.JPG

March 9, 2010

Choosing statistical tests

This table is one that I think every public health student should be able to generate after taking statistics. Unfortunately it is not presented this way

Dependent/outcome
Independent/predictor Dichotomous Categorical Continuous
Dichotomous Chi-square Chi-square t-test
Categorical Chi-square Chi-square ANOVA
Continuous Logistic regression ??? Correlation or regression

Caveat: This ignores study design. In real analyses it is common to adjust for covariates, use repeated measures or do something else that requires different tests. Nevertheless, it shows the basic test underlying what you will use.

March 5, 2010

Communicating nutrients

The stoplight diet got me thinking of using color in place of the nutrition information on food packages. These examples show where a fruit on the bottom yogurt's calories come from. Protein is green (?), as are fiber and poly-unsaturated fats. Mono-unsaturated and polysaccharides are yellow, and saturated fats and monosaccharides are red. I'm not sure about my definitions, but I think the images communicate simply. It would be easy for the illiterate and non-English speakers. Children, too.

Caloricspread.bmpCaloricspread2.bmp