Statistics is in crisis, but with your help we can make it worse.
Don't wanna be here? Send us removal request.
Statistics
We looked inside some of the posts by terrible-statistics-advice and here's what we found interesting.
Average Info
Notes Per Post
54
Likes Per Post
37
Reblog Per Post
17
Reply Per Post
0
Time Between Posts
23 hours
Number of Posts By Type
Text
17
Last Seen Tumblr Blogs
Fun Fact
12.7% of mobile users access Tumblr.
Text
The Central Limit Theorem probably applies to data drawn from a Cauchy distribution, whatever the naysayers may argue.
0 notes
Text
Use Microsoft Excel to create all your charts.
1 note
·
View note
Text
Yeah, that time series is probably stationary already, don't worry about it.
0 notes
Text
Make yourself indispensable by making all your statistical analysis impossible to replicate.
0 notes
Text
Save time and effort by training your model on the test data.
0 notes
Text
Never normalize values. Units are important.
0 notes
Text
Don’t worry so much about measurement error or missing data.
0 notes
Text
Condition on a collider variable.
0 notes
Text
Create a chart with a secondary vertical axis.
0 notes
Text
Collect the data first, then worry about experimental design.
1 note
·
View note
Text
Add more regressors to your model to increase R^2.
0 notes
Text
Confounders are not real and cannot hurt you.
0 notes
Text
Focus all your efforts on calculating point estimates.
0 notes
Text
Illustrate a discrete time series using a chart with smooth lines.
0 notes
Text
Remove all outliers before attempting any analysis.
0 notes