The clinician’s guide to the literature: Interpreting results​

By Greenberg BL, Kantor ML. ​

Date: 01/2009
Journal: JADA


This article covered several of the basic concepts that underlie the majority of statistical analyses reported in the clinical research literature: variability, hypothesis testing, CIs and sample size. 

Variability :

Is the source of uncertainty in clinical studies. 

Measures of variability:

  • Standard deviation (SD) : is the distribution of the sample  data around the sample mean. Small SD little variability. ​
  • Standard error (SE): measures the variability of sample means if the study were repeated many times. 

Researchers use two approaches to quantify this uncertainty:

hypothesis testing with values, and estimation with confidence intervals ​

  • Hypothesis testing: test relationship between exposure and outcome. Null, alternative hypothesis.​
  • P-value: measures the probability that the results are due to chance. P< α: reject null hypothesis.​
  • Confidence intervals (CIs)to estimate the upper and lower limits of the variability in the sample data, measures significance, and association of Relative Risk (RR). 95 percent CI does not include 1significant results ​
  • Relative Risk (RR): measure the strength of the association, 1=no association, RR>1: positive association, RR<1: protective factor ​
  • Power: is the probability that the study will be able to detect a difference/association 

Clinical significance:​