Conversation

you guys are right though I should have made this a scatterplot, I am not used to my data being scatterplottable so it didn't occur to me

Quote Tweet

Aella

@Aella_Girl

Dec 5, 2022

The comments here are full of poor understanding of statistics, in case ppl wanted to go help and e.g. explain what a "bin" means twitter.com/Aella_Girl/sta

Show this thread

7:33 PM · Dec 6, 2022

Replying to

OLS time

Replying to

Also: 18.5-24.9 - Healthy 25.0 to 29.9 - Overweight 30.0+ - Obese

Replying to

Hopefully the controversy leads to enough traction to rerun the survey with a much larger sample size.

Replying to

Binscatter may be the way to go

Replying to

I like to believe that the x-axis origin is actually 0 (even though it’s probably supposed to be 15) and that there’s a spooky skeleton escort with a BMI of ~5 earning about $20,000 a month.

Replying to

Gorgeous age plot you have there.

Replying to

Sns.kdeplot in seaborn is also a pretty visualisation tool

Max Limelihood Estimator | Lime

@StatsLime

Dec 6, 2022

Replying to

@Aella_Girl

can you do a log-log plot? Distributions like this are a lot easier to understand and model if you apply a variance-stabilizing transformation first. (Also, both of these are rates, so I suspect the distribution is roughly log-normal).

Replying to

I’d be wary of sampling biases, as I’d imagine this is collected from online/OF sphere escorts. Unless you also interviewed “streetwalkers” in impoverished communities?