Dass #OpenScience einmal im Koalitionsvertrag einer deutschen Bundesregierung stehen würde, hätte ich nicht gedacht.
Ein Vorschlag zur Umsetzung: Wir WissenschaftlerInnen evaluieren den Erfolg all der neuen Ampel-Gesetze mit pre-registered adversarial collaborations. Das heißt...
die Vielfalt und Gegensätzlichkeit an Grundüberzeugungen, die es auch Wissenschaft gibt, produktiv zu nutzen.

Jetzt ist es doch oft so, dass wirtschaftsnahe, gewerkschaftsnahe, verbrauchernahe Institute in ihren Studien oft das herausfinden, was sie schon immer richtig hielten.
Führen 12€ Mindestlohn zu höherer Arbeitslosigkeit?

Diese und andere Fragen können wir untersuchen ohne dass die Ergebnisse von den Interessen und Ansichten der Beteiligten gefärbt sind.
WissenschaftlerInnen von @boeckler_de, @insm oä könnten sich zusammentun und *vor* Inkrafttreten des Gesetzes einigen wie diese Frage untersucht wird und nach welchen Kriterien mögliche Ergebnisse beurteilt werden.
Bevor diese Ergebnisse vorliegen.
Wir wissen, dass auch kleine Details der Analysestrategie die resultierenden Befunde beeinflussen. Im besten Fall legen alle Beteiligten also bereits vor Zugriff auf Daten so weit wie möglich auch kleinste Details bis zum Statistikcode fest.

Genau ein solches Vorhaben führen wir gerade zur Frage durch, ob die Meinungsfreiheit an deutschen Universitäten bedroht ist.
ForscherInnen unterschiedlicher ideologischer, methodischer Hintergründe arbeiten am einem gemeinsam Forschungsdesign. osf.io/preprints/meta…
Und am Ende soll eine Einigung stehen:
Wir wissen nicht, was die Daten uns sagen werden, aber wir haben ein Prozess gefunden mit dem neue Daten unsere ursprünglichen, gegensätzlichen Ansichten überprüfen - entweder widerlegen oder unterstützen.
Ein solches Modell könnte und sollte Schule machen gerade in der Politikevaluation.

Denn gerade hier wollen wir uns darauf verlassen können, dass wir von wissenschaftlicher Evidenz wirklich lernen können.

• • •

Missing some Tweet in this thread? You can try to force a refresh

Keep Current with Alexander Wuttke

Alexander Wuttke Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!


Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @Kunkakom

5 May
Is freedom of speech under threat on university campuses?
Excited to announce this project:
➡️Preregistered adversarial collaboration
➡️Skeptics & proponents with diverging perspectives come together to devise a joint research design
Please participate&RT.
doi.org/10.31219/osf.i… Image
This project takes up a study by Revers / Traunmüller based on a survey among students at a German university.
The study claims to have found evidence for widespread support for restricting free speech on campus
Twitterverse and printed media discussed the study quite a bit.
Criticism concerned issues of study design and item wording as well as the normative framing of the results.
Read 8 tweets
23 Nov 20
What can you do when an experiment yields null results?

I developed a theory to explain why (some) people derive pleasure from political engagement
14 out of 15 predictions failed

▶️A step-wise process to maximize the informational value of null results
doi.org/10.1017/pls.20… Image
The need-based theory of political motivation in a nutshell:

Building on the ‘Pleasure Principle’, I suspect that people will seek behaviors that made them feel good in the past.
Citizens will therefore seek political engagement when it previously made them feel good. Image
To understand what actions provide pleasure, I built on the concept of basic psychological needs.
Differences in intrinsic political motivation are theorized to reflect whether political engagement was previously experienced as satisfying basic psychological needs. Image
Read 11 tweets
17 Oct 20
Fantastic work (@The_JOP) focusing on political representation with value for the entire discipline.
Exemplary of good science, I think.

▶️Multiverse analyses to assess robustness of earlier findings to model specifications
▶️Collaboration between replicator & original authors
After Hansen&Treul reported evidence for a substantive finding in a JOP article, Saraceno reproduced the analysis and found inconsistent evidence for different model specifications.
The journal then invited all three authors to team up and work together to check the robustness. Image
The newly minted team decided that multiple analytical choices are reasonable for six variables, leading in combination to 288 possible models with reasonable analytical specifications. Image
Read 12 tweets
18 Jul 20
Boba appears a huge leap towards transparent sensitivity analyses in empirical research
▶️easy multiverse analyses
▶️generates code for all reasonable analytical paths
▶️software-independent (R, Python...)
▶️amazing #dataviz
arxiv.org/abs/2007.05551 ImageImage
You will write your syntax and specify where two or more analytical choices are reasonable.
Boba will generate the code for all combinations of reasonable choices for you. ImageImage
Boba is a domain-specific language (and a visual analysis system) so it works software-independent for #Rstats, #Python etc...
Read 7 tweets
31 Mar 20
Regression analysis with observational data remains the primary analytical method in political science.

However, we will never know whether we controlled for all unobserved confounders.

New sensitivity tools help to assess how likely results are robust to missing controls.
The robustness value (@analisereal,@chadhazlett) applies to multivar. regressions: It is the minimum strength of association that unobserved confounding would need to have, both with the treatment and with the outcome, to change the research conclusions.
The robustness value can be calculated with a Shiny Application (carloscinelli.shinyapps.io/robustness_val…) or with the #rstats package sensemakr.
Read 8 tweets
24 Mar 20
V-DEM, potentially the most comprehensive measure on the state of democracy, has published a new report, and the results are staggering.
▶️Hungary is no longer considered a democracy
▶️India is close, too
▶️Now, the majority of people worldwide live in autocracies
The report (v-dem.net/media/filer_pu…) is worth reading.

It is a prime example of how to communicate complex data on important questions:
Accessible language combined with intuitive graphs that help to convey clear messages.

I'll copy key graphs and phrases while reading along.
Assessing "the state of democracy" is hard because the concept is complex and controversial.
But even if conceptual questions were settled, collecting all necessary measures to assess how democratic a country is is a huge undertaking.
Read 14 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Thank you for your support!

Follow Us on Twitter!