Methoden der empirischen Kommunikations- und Medienforschung
Freie Universität Berlin
Falls nicht: Besprechung von Aufgabe 2
Mit Material von Prof. Tobias Dienlin, Universität Zürich. Original hier

Your task is to click on the curtain that you feel has the picture behind it. The curtain will then open, permitting you to see if you selected the correct curtain.


Versuchsperson rät.
Zufallsgenerator legt Position des Bilds fest.
Ausgewählter Vorhang wird geöffnet.


“Across all 100 sessions, participants correctly identified the future position of the erotic pictures significantly more frequently than the 50% hit rate expected by chance: \(53.1\%\), \(t(99) = 2.51\), \(p = .01\), \(d = 0.25\).”


“In contrast, their hit rate on the nonerotic pictures did not differ significantly from chance: \(49.8\%\), \(t(99) = 0.15\), \(p=.56\). This was true across all types of nonerotic pictures: neutral pictures, \(49.6\%\); negative pictures, \(51.3\%\); positive pictures, \(49.4\%\); and romantic but nonerotic pictures, \(50.2\%\). (All \(t\) values \(<1\).) The difference between erotic and nonerotic trials was itself significant, \(t_{\text{diff}}(99) = 1.85\), \(p = .031\), \(d = 0.19\).”

“I’m all for rigor,” he continued, “but I prefer other people do it. I see its importance—it’s fun for some people—but I don’t have the patience for it.” It’s been hard for him, he said, to move into a field where the data count for so much. “If you looked at all my past experiments, they were always rhetorical devices. I gathered data to show how my point would be made. I used data as a point of persuasion, and I never really worried about, ‘Will this replicate or will this not?’”

“I preferred to do it at home, late in the evening, in fact at the beginning of the night, when everybody else was asleep. I would make some tea, put my laptop on the kitchen table, get my notebook from my rucksack, take my fountain pen out, and make a careful list of all the results and effects I needed to create for the study I was doing. Neat tables with the results I expected based on extensive reading, theorizing, and thinking. Simple, elegant, comprehensible. Next I started to enter the data, column by column, row by row. I tried to imagine how the participants’ answers to my questionnaire would look. What were some reasonable answers that might be expected? 3, 4, 6, 7, 8, 4, 5, 3, 5, 6, 7, 8, 5, 4, 3, 3, 2. When I’d input all the data, I ran some quick preliminary analyses. Often these didn’t show what I was expecting, so I went back to the matrix of data to change a few things. 4, 6, 7, 5, 4, 7, 8, 2, 4, 4, 6, 5, 6, 7, 8, 5, 4. And so on, until the analyses came up with the results I was looking for. That is, until the data showed what was logical, and therefore true.”
Datenanalyse mit dem Ziel “statististischer Signifikanz” (p < .05)
Viele Variablen erheben
Viele Varianten der Datenaufbereitung testen
Viele Analysen durchführen
Fälle aus Analyse ausschließen
Weitere Fälle erheben
Während der Studie auswerten und abhängig von Zwischenergebnis stoppen
Am Ende: Selektiv berichten, was “funktioniert” hat

Entscheidung der Herausgeber:innen von Fachzeitschriften: Studien mit “statistisch signifikanten” Ergebnissen haben bessere Publikationschancen
Entscheidung der Wissenschaftler:innen: Studien mit nicht “statistisch signifikanten” Ergebnissen verschwinden in der Schublade (file drawer)
Betrifft unter anderem nicht erfolgreiche Replikationsstudien
Folge: Verzerrter Forschungsstand, selbst wenn die publizierten Studien unverzerrt sind

Open science refers to the process of making the content and process of producing evidence and claims transparent and accessible to others. Transparency is a scientific ideal, and adding ‘open’ should therefore be redundant (Munafò et al., 2017, S. 5).
Agent-based simulation (Prof. Annie Waldherr, Uni Wien)
Marko Bachl