How to read academic research (beginner's guide)

13,007 views

Published on

An introductory review of how to read academic research articles aimed at people wanting to get practical suggestions from academic research.

1 Comment
12 Likes
Statistics
Notes
  • Very good tips, thanks Russell. Let me share a website I found, I just think this will be useful for you someday. You can convert docs to pdf here http://goo.gl/VGvvul everything can be done online, without installing anything, check it out.
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here
No Downloads
Views
Total views
13,007
On SlideShare
0
From Embeds
0
Number of Embeds
344
Actions
Shares
0
Downloads
307
Comments
1
Likes
12
Embeds 0
No embeds

No notes for slide

How to read academic research (beginner's guide)

  1. 1. How to read academic research (even if you’re not an expert)Dr. Russell James III, Texas Tech University www.EncourageGenerosity.com
  2. 2. Rule 1Don’t Freak Out!
  3. 3. You don’t need to eat the whole cow! You can get important concepts out of a research article without fully understanding every detail
  4. 4. How do you eat acake with rocks in it? Don’t try to eat the rocks
  5. 5. Questions for an article1.Do I care about the research topic?2.Do I believe the findings?3.So what?
  6. 6. Abstract: Do I care?Tables: What did they really find?Methods: Do I believe the table?Discussion: So what?Lit. Review: What did we already know?
  7. 7. Title and Abstract: Do I care?
  8. 8. Tables:What did they find?
  9. 9. Methods:Should I believe the table?
  10. 10. Discussion: So What?
  11. 11. Literature Review: What did we already know?
  12. 12. Should you believe the findings?Research is messy.Research often disagrees.We want to be able todistinguish strong resultsfrom weak ones.
  13. 13. Bad newsKnowing whetheryou should believethe findingsusually requiressome statistics
  14. 14. Core statistics concepts you must know 1. Association v. Causation 2. Correlation v. Multiple Regression 3. Significance v. Magnitude
  15. 15. Association v. CausationAssociation: A & B tend to occur togethermore frequently than one would expect byrandom chance
  16. 16. Explaining Associations1. Random chance (stuff happens)2. A causes B (sometimes)3. B causes A (sometimes)4. Something else causes both A & B (sometimes)
  17. 17. Sleeping in your shoes is associatedwith waking up with a headache. Why?
  18. 18. 1. Random chance2. Sleeping in shoes causes headaches3. The very early stages of a forthcoming headache causes sleeping in shoes4. Going to bed drunk causes both results
  19. 19. Association v. Causation• Statistics can show only association• Statistics can NEVER show causation We infer causation from experimental design or theory combined with statistical association
  20. 20. Statistics can easily determine thisExplaining associations: 1. Random chance 2. A causes B less so with 3. B causes A these 4. Something else causes both A & B
  21. 21. Correlation v. MultipleRegression
  22. 22. Correlation: A & B tend to occurtogether more frequently than onewould expect by random chanceMultiple Regression: Above is truewhen comparing those otherwisesimilar in certain ways
  23. 23. CorrelationHigher educationand charitable givingtend to occurtogether (morefrequently than onewould expect byrandom chance)
  24. 24. Multiple RegressionHigher educationand charitable givingtend to occurtogether (morefrequently than onewould expect byrandom chance)comparing thosewith otherwisesimilar incomeand wealth
  25. 25. Explaining Associations: 1. Random chance 2. A causes B 3. B causes A 4. Something else causes both A & BMultiple regressionallows us to excludespecific items from#4, unless we can’t ordidn’t measure it.
  26. 26. Nature says kids’ nightlights cause myopia “Although it does not establish a causal link, the statistical strength of the association of night-time light exposure and childhood myopia does suggest that the absence of a daily period of darkness during early childhood is a potential precipitating factor in the development of myopia.”G.E. Quinn, C.H. Shin, M. Maquire, R. Stone (University of Pennsylvania Medical School), 1999,Myopia and Ambient Lighting at Night, Nature, 399, 113.
  27. 27. Nature says kids’ nightlights cause myopia 1. Random chance 2. A causes B 3. B causes A 4. Something else causes both A & BG.E. Quinn, C.H. Shin, M. Maquire, R. Stone (University of Pennsylvania Medical School), 1999,Myopia and Ambient Lighting at Night, Nature, 399, 113.
  28. 28. Rebuttal: Maybe parents’ myopia causes both nightlights and child’s myopia? “…we find that myopic parents are more likely to employ night-time lighting aids for their children. Moreover, there is an association between myopia in parents and their children…” “…Quinn et al.’s study should have controlled for parental myopia.”J. Gwiazda, E. Ong, R. Held, F. Thorn (New England College of Optometry), 2000, Myopia andAmbient Night-Time Lighting, Nature, 399, 113.
  29. 29. Significance v.Magnitude
  30. 30. Statistics tests a small sample topredict the whole population Significance shows how likely our result might have been due to an unusual random sample, rather than an actual difference in the population
  31. 31. Most papers report some measure of statisticalsignificance (chance that the association wasdue to a weird random sample) • p-value • confidence interval
  32. 32. How likely is it to randomly drawthese five fruits from a truckloadwith as many apples as oranges? p-value
  33. 33. p-valuep<.05 = there is less than a 5% chance that the result was caused by an unusual random sample where there was no actual (population) difference
  34. 34. Was there a significant gender difference in planned givers with a will v. a trust? No
  35. 35. This (sample) difference could haveeasily occurred even if the two(population) groups were the same
  36. 36. It DOES NOT mean the two(population) groups do not differ,only that WE CAN’T TELL.
  37. 37. No “*” means we can’t confidently tell the effect of this item
  38. 38. 95% Confidence intervalIf you kept taking random samples, 95%of the time the true (population) valuewould appear inside the confidenceinterval associated with each sampleSampleAverageStrength Population Average Strength Confidence Interval
  39. 39. Dashed line is a 95% confidence intervalS. Huck and I. Rasul (2008) Testing consumer theory in the field: Private consumption versus charitable goods
  40. 40. Multiple Comparisons Problem How likely is it to randomly draw these five fruits from a truckload with as many apples as oranges? Would your answer change if I got to draw 20 times to find this group?
  41. 41. If all variables are random, about oneout of 20 will have a p-value<.05
  42. 42. “We tested 100 items and found 5 to be significant at p<.05.”
  43. 43. Significance v. MagnitudeIt is possible to be highly confident of avery small effect. This may be publishable,but not practically important.
  44. 44. Numbers(coefficients) resulting from complex statistical techniques may not be directlyinterpretable in terms of real world magnitude
  45. 45. The impact of children on the probability of exclusively secular giving is“-0.089”, butthe meaning of that number is not easily translated
  46. 46. Even with complex techniques, we can easily compare sign andmagnitude relative to other variables
  47. 47. Race and education factors are3-4 times as large. More children have an oppositerelationship compared with more education.
  48. 48. Odds ratios are differentUsually you cancompare sign andsize, but odds ratiosare always positive
  49. 49. Odds ratios: the odds of an event occurringin one group over the odds of it occurring in another group <1 negative; >1 positive; =1 none
  50. 50. Odds ratios <1 correspond with negative coefficient numbers in other reportingPamala Weipking (2008) Giving to particular charitable organizations: Do materialists support local organizations and do Democrats donate to animal protection?
  51. 51. Finding academic research articles ISI ranked academicIncludes everything, journals articles onlyeven workingpapers andindustry literature
  52. 52. How to read academic research (even if you’re not an expert)Dr. Russell James III, Texas Tech University www.EncourageGenerosity.com

×