Calvin Heal

[Daniël Lakens @lakens]

A second point in the recent Nature Human Behavior editorial https://t.co/nq8hLR5RRg is to adhere to threshold interpretations. Do not use ‘marginally significant’. A finding is significant, or not. But why would scientists make dichotomous claims?

[Maarten van Smeden @MaartenvSmeden]

Kind reminder. There is no such thing as a validated prediction model
https://t.co/nDVROL5QRQ

[Asjad Naqvi @AsjadNaqvi]

A #StataTip: If you are repeatedly using the same set of commands, for example for graphs or regressions, then:

1) start using macros, and/or
2) define small programs

This saves you:
(a) space, and
(b) the hassle of copy/pasting

and looks neater!

[John V. Kane @UptonOrwell]

Want to clean up your @Stata data more efficiently (& carefully)?

Generating, recoding, & rescaling variables is a crucially important part of data analysis--yet it's hard to find a succinct guide. I've created one for my students & thought I'd share!😁

https://t.co/qCsBkzBIeZ

[Anders Granholm @andersgranholm]

#MethodMonday 2: This week I'm sharing @statsepi s excellent post on balancing of variables in RCTs https://t.co/Sl5fLwGoSw
A common misconception is that we randomise to 'balance' baseline variables (incorrectly termed confounders) - we don't 1/..

[John V. Kane @UptonOrwell]

Want to have nicer scatterplots in @Stata?

Students often ask me how to adjust individual labels & clean up overlapping/cluttered labels. So, I finally decided to make a guide w/ every possible fix that I'm aware of:

https://t.co/GFebv17BaG

Hope it's helpful for you!🙂

[David White @m0457356748]

We have updated our Stata Graph Gallery. Now over 160 graphs! New features include: search across all the graphs, select by complexity, or select by graph type. Check it out at https://t.co/5qFB320qbn

[Todd Jones 🦊 @toddrjones]

Quick @Stata tip (ICYMI):

keep if inlist(state, "AL", "AK", "AZ")

is the same as:

keep if state=="AL" | state=="AK" | state=="AZ"

And:

keep if inrange(distance, 10, 91)

is the same as:

keep if distance>=10 & distance<=91

[Todd Jones 🦊 @toddrjones]

Quick @Stata tip: use "restore, not" to fix the "already preserved" error that arises if you try to preserve the data when already preserved.

[Miguel Hernán @_MiguelHernan]

No matter what you were taught,

don't bother to test for proportional hazards

in survival analyses.

Hazards are never proportional because hazard ratios vary over the follow-up if treatment has an effect on survival.

@mats_julius and I explain it here:
https://t.co/hlRstEmPse

[Todd Jones 🦊 @toddrjones]

Quick @Stata tip: use "ereplace" to replace when using "egen" commands:

*typical way:
sysuse auto2, clear
*doesn't work:
replace mpg = max(mpg)
*instead:
egen mpg2 = max(mpg)
drop mpg
rename mpg2 mpg

*better way:
ssc install ereplace
sysuse auto2, clear
ereplace mpg = max(mpg)

[Todd Jones 🦊 @toddrjones]

Quick @Stata tip: get rid of the leading and trailing space of a string variable with "trim":

clear all
input str12 str
"String A "
" String B "
" String C"
end

replace str = trim(str)
compress

[Todd Jones 🦊 @toddrjones]

Quick @Stata tip: when using bysort, say you have a variable you want to sort with, but *not* group by. Put this variable in parentheses:

sysuse census, clear
*keep least-populous state within each region, so sort by pop within each region:
bys region (pop): keep if _n==1

[Todd Jones 🦊 @toddrjones]

https://t.co/hYyY2zynd9

[Hunt: Showdown @HuntShowdown]

Were you able to foretell this? Serpent Moon Giveaway for our Prescient Night DLC! 🔮

For every 100 Retweets, we are giving away another Steam DLC key. ���️

To enter the giveaway all you have to do is:
- Follow us on Twitter✔️
- Like this Post ✔️
- Retweet this Post 🔁

[Calvin Heal @CalvinHeal1]

@Lucyy31 @jamiecsergeant @glen_martin1 @khyrich @MatthewSperrin Fantastic! Congrats

[Rob Riley @robriley73]

Well @TUIUK As promised here's another photo from the room I had to endure last week.

It's a bath mat!

Why was I not moved?
Why am I not being refunded?

#TUIfails #badcustomerservice @TUIGroup @WhichUK #poorcustomerservice #MartinLewis @TUIUKPR

[Rob Riley @robriley73]

"These standard double rooms come with a balcony or terrace with a garden view"

Really @TUIUK ?

#badcustomerservice @TUIGroup @WhichUK #poorcustomerservice #MartinLewis

[Maarten van Smeden @MaartenvSmeden]

Nice paper. (Some of?) the most important statistical ideas in past 50 years
https://t.co/4Jym4RUD6E