Everything is not normal
Management of non-normal data. When we are dealing with the management of non-normal data, we must use other strategies to make a hypotheses contrast.
Science without sense...double nonsense
Evidence Based Medicine pills
Science without sense...double nonsense
Evidence Based Medicine pills
Read MoreEverything is not normal
A very robust family
Robust location parameters. We describe robust location parameters that are more robust to the presence of extreme values than arithmetic mean. The mean is a whimsical statistic. Of course, I am referring to the arithmetic mean. And why do I say that…
Having a large n, who needs a small p?
Statistical significance vs clinical relevance. We must always prioritize the effect size and its clinical relevance over its statistical significance, which depends on the sample size.
As an egg to a chestnut
Bar plot and histogram. We review the differences between bar plots, useful for representing qualitative variables, and histograms, for quantitative ones.
With very little we fine-tune a lot
Confidence interval and sample size. The characteristics of the standard error of a proportion allow us to make with confidence precise inferences without the need of very large samples.