Dr Mircea Zloteanu ๐บ๐๐#statstab #532 Fractional Bayes Factors for Model Comparison Free - O'Hagan (1995)
Thoughts: Use a fraction of the data to convert an improper prior into a minimally informative prior.
#statstab #531 Effect Size Calculator [Campbell]
Thoughts: A nice place for quick formulas for variance and effect sizes of various designs and data types.
#metaanalysis #effectsize #CohenD #calculator #Variance #Eta #effects
#statstab #530 On the Need to Revitalize Descriptive Epidemiology
Thoughts: Paper that shows how to properly conduct a "descriptive" piece of research. More ppl should do this.
#descriptive #research #guide #example #methods #epistemology #epistemology
#statstab #529 How Do I Know What My Theory Predicts?
Thoughts: I'd like to see more researchers adopt Dienes' framework and way of thinking about research.
#bayesian #bayesfactor #evidence #epistemology #research #tutorial
#statstab #527 How to interpret โconfidence intervalsโ in observational studies
Thoughts: A great example of a conversation that goes nowhere but is interesting to read
#debate #unhelpful #discussion #forum #confidenceintervals #observational #inference
How to interpret โconfidence intervalsโ in observational studies
This question complements the one in the thread Random sampling versus random allocation/randomization- implications for p-value interpretation. Given that observational studies involve neither random sampling nor random allocation, why are they riddled with โ95% confidence intervalsโ?
#statstab #526 Splines, B-splines, P-splines, and a disapproving kitten
Thoughts: Nice R tutorial on splines with some explanations and illustrations.
#statstab #525 Falsificationism and clinical trials
Thoughts: A strongly worded paper on the role of Poperrian induction on inference.
#Popper #falsification #induction #inference #philosophy #evidence #clinical
#statstab #524 {simglm}: Tidy simulation and power analyses
Thoughts: As your design becomes more complex, simulation is the only way to go.
#simulation #r #rstats #tidy #tidyverse #poweranalysis #design #tutorial
Simulate Models Based on the Generalized Linear Model
Simulates regression models, including both simple regression and generalized linear mixed models with up to three level of nesting. Power simulations that are flexible allowing the specification of missing data, unbalanced designs, and different random error distributions are built into the package.
