Maarten van Smeden
@MaartenvSmeden
Followers
41,652
Following
837
Media
1,419
Statuses
20,246
Statistician • associate prof • statistics/epidemiology/AI methodology, Julius Center @umcutrecht • own views
Utrecht
Joined December 2010
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
#スポ男
• 54948 Tweets
La ONU
• 48196 Tweets
WIN X VELENCE
• 46821 Tweets
NuNew 3rd Single
• 36540 Tweets
ゴジラ-1.0
• 31909 Tweets
#最強スポーツ男子頂上決戦
• 22857 Tweets
ランウェイ
• 22458 Tweets
猫の恩返し
• 21117 Tweets
長嶋茂雄
• 17079 Tweets
雇用統計
• 16265 Tweets
ミスター
• 12681 Tweets
#njDONTAKU
• 12478 Tweets
Marco Reus
• 12069 Tweets
PondPhuwin Vichy Live
• 11754 Tweets
まことお兄さん
• 11408 Tweets
#فيصل_ابو_رميه
• 10184 Tweets
Pinned Tweet
NEW PAPER
I was challenged by
@morleycp
to write a 1000-word paper about a tweet. It was fun to do, and hopefully useful to some of you
Open acces 👉
28
392
1K
If I throw my paper into a forest, I can claim on my CV that I have submitted to Nature
152
1K
20K
How to become a SUCCESSFUL academic: a guide 1/n
175
3K
16K
Students often ask me: why do so many choose 5% as the threshold for significance (“alpha”)?
So let me try to explain the main rationale
1/20
212
2K
14K
COVID has killed a lot of my heroes although none of them have died
129
1K
11K
“After adjusting for known confounders, the association remained highly significant”
119
1K
11K
Math question: ever wondered what is n^-1?
Let me explain...
1/n
123
1K
9K
Statistical terms: what they really mean
Multicolinearity— they all look the same
Heteroscedasticity— the variation varies
Attenuation— being too modest
Overfitting— too good to be true
Confounding— nothing is what it seems
P-value— it’s complicated
59
2K
8K
The sound of machine learning that is just logistic regression
60
2K
6K
After my CV, personal and institution website, Google Scholar, ResearchGate, Publons, LinkedIn, Orchid, Web of Science, Scopus, Pure, Academia, I can’t wait for the next tool to simplify managing my academic profile
63
724
5K
Have never seen a better way to describe the Dutch response to Covid
54
796
4K
You are not even a real scientist until someone on Twitter says you don’t understand the one thing you have been studying for years
54
316
4K
Once you realize p-values are probabilities relating to observing data rather than probabilities of an hypothesis being true, you are already doing significantly better than most people
43
396
4K
Linear regression with bootstrapped standard errors
48
635
3K
Trying to control the position of figures in MS Word
34
369
3K
Why did you become a scientist?
Wrong answers only
3K
387
3K
manuscript_v1.docx
manuscript_v2.docx
manuscript_v4b.docx
manuscript_v5_with_comments.docx
manuscript_v7_tv_tdl_mvd_omg.docx
manuscript_final.docx
manuscript_final_v2.docx
manuscript_final_v2_with_comments.docx
manuscript_final_v3.docx
manuscript_final_FINAL.docx
80
202
3K
Stats question: what is the relative contribution of a single individual in a sample of size n to the sample mean
Let me tell you…
1/n
47
289
3K
I sincerely hope this thread will help YOU become an even more successful academic
n/n
98
47
2K
Personal top 10 fallacies and paradoxes in statistics
1. Absence of evidence fallacy
2. Ecological fallacy
3. Stein’s paradox
4. Lord’s paradox
5. Simpson’s paradox
6. Berkson’s paradox
7. Prosecutors fallacy
8. Gambler’s fallacy
9. Lindsey’s paradox
10. Low birthweight paradox
39
670
2K
Nature: you pay $10k for an open access publication
Also Nature:
Study finds open-access papers have fewer lead authors from low-income countries than paywalled articles
132
217
776
24
414
2K
If art were like scientific manuscripts
Artist: worked some months on this painting that would fit your gallery I believe. Would you consider?
Gallery: fill out these forms
A: okay
G: please remove the frame and attach it to the bottom
A: what? Okay...
23
695
2K
absence of evidence ≠ evidence of absence
measurement error ≠ bias towards null
clinical trial ≠ study with patients
multivariate ≠ multivariable
95%CI ≠ 95% probability
p-value ≠ probability H0
correlation ≠ causation
significant ≠ relevant
bias ≠ error
odds ≠ risk
28
574
2K
academics to other academics: stay in your lane
the lanes:
12
232
2K
Probably the best introductory text on modern statistical learning I have read so far. Great for non-economists (like me) too. Highly recommended
h/t
@causalinf
5
369
2K
T-test, ANOVA and linear regression walk into a bar.
Barman asks: are you here alone or are you waiting for someone?
41
194
2K
First they ignore you,
then they laugh at you,
then they fight you,
then you realize they never actually read your paper.
21
252
2K
Statisticians, let’s be realistic we are terrible with branding. If it was up to us Deep Learning would have been called Hidden Layers Black Boxy Box
42
140
2K
Experienced PI reading critical reviewer reports
10
193
2K
Terminology explained
- Statistics: we fitted a curve through data points
- Data science: we fitted a curve through data points
- Machine learning: we fitted a curve through data points
- Artificial intelligence: we fitted a curve through data points
40
225
2K
RR: 0.50 [0.33; 0.99]
🚨🚨HOLY MOTHER OF GOD 🚨🚨treatment reduces cases by 50%
RR: 0.50 [0.32; 1.01]
treatment ineffective, study shows
26
135
1K
1) Be the ultimate collaborator but also don't be
Say yes to as many collaborations as physically possible: co-produce papers, LEARN, co-write grants, DISCUSS, it is all about synergy. But also, collaborations slow you down, have your own ideas! Just say no to collaborations
4
27
1K
Data from UK or US: this is a very important study
Data from anywhere else: this is an interesting study, but the authors should clarify how the data from X generalizes to other countries
27
201
1K
Stop calling everything AI is a good suggestion
35
210
1K
Five simple ways to write a better scientific paper than your colleagues
14
298
1K
Top 10 statistics things you should NEVER do
1) dichotomize unnecessarily
2) conclude no effect from p>.05
3) use Hosmer–Lemeshow test
4) test normality of covariates
5) impute the mean for missing data
6) confuse correlation for causation
7) make top 10 never do lists
30
199
1K
Sensitivity analysis— tried a bunch of stuff
Post-hoc— main analysis not sexy enough
Multivariate— oops, meant to say multivariable
Normality— a very rare shape for data
Dichotomized— data was tortured
Extrapolation— just guessing
12
152
1K
1. choose your supervisors carefully
2. choose your supervisors carefully
3. choose your supervisors carefully
4. choose your supervisors carefully
...
10. choose your supervisors carefully
24
168
1K
“A prediction model was developed and externally validated”
Footage of the validation:
23
216
1K
Terminology explained
- Regression: we used an algorithm
- Machine learning: we used a fancy algorithm
- Artificial intelligence: we used a VERY fancy algorithm, please don't ask
19
346
1K
Police? I would like to report a dataviz murder
35
132
1K
Lots of relevant work in epidemiology is *descriptive* in nature and very often such work is NOT improved by "correcting" for a bunch of stuff in a multivariable regression or by doing automated variable selection. Sometimes, averages and percentages is just what you need
21
133
1K
I love my job, but at least 35 more years seems terribly long to continue discussing whether a model for X predicting Y is statistics, statistical modeling, machine learning, artificial intelligence, statistical learning, data science, data analytics or just regression
32
105
1K
The biggest difference between statistics and machine learning may be in language! So a few months ago I created this (inspired by
@DanielOberski
) but haven't made much progress since. Welcoming suggestions for improvements
27
322
1K
2) Be the methods ninja but also don't be
Science is only as good as its weakest link: don't be satisfied by applying the default analyses in the field. But also, don't let perfect be the enemy of the good and don't confuse reviewers. Just apply the default analyses in the field
2
26
1K
3) Be the superstar teacher but also don't be
Professor means teacher, it is LITERALLY in the name. Being a good professor means being a superstar teacher. But also, focus on the science and minimize the hours of teaching, don't try to become a superstar teacher
5
29
1K
We thank the reviewers for their thoughtful comments. Below we will provide a point by point response
14
134
1K
Still consult this much more often than I like to admit
18
168
1K
Remember folks, it is only causal if it originates in the causalité region of France.
Otherwise, it is just sparkling correlation
11
140
1K
This is my *top 10* favorite methods papers of 2022
Appearing in a single thread and in random order
12
253
1K
Making a meme within 3 minutes
Twitter: ❤️ 2k, 🔁 500
Sharing work that costs 2 years of my life with never ending discussions, 56 drafts, 20 rounds of peer review, blood, sweat, tears and a kidney
Twitter: ❤️ 12, 🔁 3, only one kidney?
25
85
1K
Periodic reminder of the best place on the whole internet
18
91
992
I have had single rounds of peer review that took longer than it took to develop, test and get approval for a vaccine
20
74
970
protocol, submitted manuscript, published article
9
111
948
Do not understand why not every PI is hiring a statistician. There is a wealth of data showing that statisticians are very effective in making research slower, more difficult to understand for non-statisticians, analyses more expensive, results less impressive and more boring
42
79
955
Pretty nervous about sharing my FIRST single author paper (still a preprint). Comments welcome
Link:
43
92
935
Statistics is hard.
That’s it. That’s the tweet
32
78
922
5) Be the literature addict but also don't be
READ YOUR LITERATURE. Be the literature addict and know what is out there to prioritize your own science and become THE EXPERT. But also, there is just too much! Invest time spend on reading in writing your own stuff! DON'T READ
5
31
922
R: could not find function "lenght"
me: alright then... lenght <- length
25
43
906
When people ask you to explain publication bias
9
156
906
Linear regression— line through data points
t-test— linear regression
correlation— linear regression
ANOVA— linear regression
ANCOVA— linear regression
Chi-square test— logistic regression
Deep learning— bunch of regressions
5
161
894
Statistical things to worry about *less*
1) significance of univariable associations
2) significant model goodness-of-fit tests
3) imbalance in randomized trials
4) non-normality of observations
5) multicollinearity
10
223
880
Why are so few clinical prediction models actually implemented in medical practice? This leaky model implementation pipeline summarizes some of the reasons
17
217
868
Why do we continue to focus on *doing* stats instead of stats comprehension and critical appraisal in the medical curriculum? I don’t care whether or not my doctor knows SPSS but I surely want them to be able to critically read their literature
38
97
851
4) Be the open science practitioner but also don't be
A modern scientist is an open scientist. Open up your code, your data and your publications. But also, your code is messy, the data isn't yours to share and you should save the APC of open publishing to hire new lab members
5
19
849
If you are looking for a short paper to read today, let it be this lovely 2-pager article by
@ADAlthousePhD
23
213
848
6) Be the supreme knowledge sponge but also don't be
Become the best in the world by borrowing knowledge from different scientific disciplines and by working in multidisciplinary teams. But also, be THE SPECIALIST. Focus on your own discipline and team, your CV is begging you
1
21
840
10) Be the family person but also don't be
Don't forget to live while becoming successful: family time should always be the number 1 priority. But also, all of the above should be number 1 priority
5
19
829
How do I know how to become a successful academic? I don't, but I have received plenty of advice. As a good academic, I will just summarize what I have learned from listening
8
35
821
1. Google for code
2. Google for code
3. Google for code
4. Google for code
5. Google for code
6. Google for code
7. Google for code
4
111
816
Was asked for personal favorite resources for improving methods and statistics skills. I promised to make it a thread, so here it is
1/n
13
257
807
Based on my experience with simulation and advanced modeling, let me summarize my thoughts on this:
HAHAHAHAHAHAHAHAHAHAHAHAHA
Ray Kurzweil: "I believe that by the end of the decade we will be able realistically model all biology and simulate interventions for diseases without the need for human trials."
27
32
93
23
95
793
I am moving from R to STATA, tips anyone?
You've been kidnapped. Your kidnappers allow you to keep tweeting to pretend everything is alright. What would you tweet that would alarm your followers without the kidnappers knowing you're asking for help?
"And then I put in the exact amount of garlic the recipe called for."
6K
1K
16K
35
50
797
Computer: change your password
Me: **********
Computer: new password does not meet requirements
Me: ****************
Computer: new password does not meet requirements
Me: **************************
Computer: new password does not meet requirements
Me:
20
148
785
7) Be the social media rockstar but also don't be
Outreach! Show you can and will communicate with the public to explain your science. But also, TIME DRAIN! Surely your tenure track committee is not impressed by your 30k SoMe followers half of whom are bots anyway
4
19
794