I curious about how people think about assumptions for your main model. Do you use them as:
A. Is my data "good enough" for this model (e.g. small sample issues)
B. Is my theory correct on what the DGP should be (e.g. maybe binomial - subgroups exist)
C. Ritualistic / no specific reason.
This was an excellent and confusing talk. Mediation is not for the faint of heart.
#justdont
"...the test doesn't "care" what type of data you have, they are just optimised for different distributions."
A very good way of looking at statistical models👆
#statstab #547 Statistical inference for exploratory data analysis and model diagnostics
Thoughts: A rather odd and provocative article. Taking visual inference to its limit.
#exploratory #eda #plots #Rorschach #inference #simulation #lineups
www.researchgate.net/publication/...
#statstab #548 Checking model assumption {easystats}
Thoughts: The {performance} package is great at a one-function plot for assunptions. Good explanations also (bug theory limited).
#rstats #assumptions #linearity #linearmodel #r #modelselection
easystats.github.io/performance/...
You need this shirt
rmk-designs.printify.me/product/1585...
#statstab #549 Nonrandomized studies using causal-modeling may give different answers than RCTs
Thoughts: "effect estimates deviated 1.58-fold between the study designs"
#Nof1 #randomization #causalinference #observational #marginalstructuralmodels
pubmed.ncbi.nlm.nih.gov/31704350/
#statstab #545 Dynamic Meta-analysis: When Transparency Meets Multiplicity
Thoughts: Seems like hard work but makes perfect sense. Combine this with live meta-analyses.
#metascience #metaanalysis #evidence #multiverse
drmattg.github.io/Uncertain_Ec...
#statstab #546 Assumption-checking rather than (just) testing: The importance of visualization and effect size in statistical diagnostics
Thoughts: Think more about what "assumption checking" means.
#assumptions #tutorial #nhst #epistemology #statistics
link.springer.com/article/10.3...
Dr Mircea Zloteanu 🌺🌞🍃
PDF | We propose to furnish visual statistical methods with an inferential framework and protocol, modelled on confirmatory statistical testing. In this... | Find, read and cite all the research you n...
Tired of people who want to pretend like a bounded outcome (proportion or percentage) can be modeled with OLS? Now you have the T-shirt to make that statemen...
Statistical methods generally have assumptions (e.g., normality in linear regression models). Violations of these assumptions can cause various issues, like statistical errors and biased estimates, wh...
#statstab #546 Assumption-checking rather than (just) testing: The importance of visualization and effect size in statistical diagnostics
Thoughts: Think more about what "assumption checking" means.
#assumptions #tutorial #nhst #epistemology #statistics
link.springer.com/article/10.3...
Dr Mircea Zloteanu 🌺🌞🍃
Dr Mircea Zloteanu 🌺🌞🍃
Dr Mircea Zloteanu 🌺🌞🍃
Dr Mircea Zloteanu 🌺🌞🍃
Dr Mircea Zloteanu 🌺🌞🍃
Now that's what I call a spicy opeing: Understanding mechanisms is not a research question.
Robert (Bob) Kubinec
Statistical methods generally have assumptions (e.g., normality in linear regression models). Violations of these assumptions can cause various issues, like statistical errors and biased estimates, wh...
I had a meeting on Friday with a student who used the "right" model on an ordinal DV, but I pointed out that people universally scored either 5 or 3. A nice moment to teach that the test doesn't "care" what type of data you have, they are just optimised for different distributions.
Dr Mircea Zloteanu 🌺🌞🍃
Nonrandomized studies using causal modeling with MSM may give different answers than RCTs. Caution is still required when nonrandomized "real world" evidence is used for healthcare decisions.
