I would love to have a mentor that is 1/5th quality of Feynman.
-
-
-
That's some high expectations! As an academic, I suggest you to lower your expectations. Only then, you may find happiness.
- Još 1 odgovor
Novi razgovor -
-
-
Unless the experiment is poorly designed, of course. Never read results without also reading the research design
-
Bingo! Similarly, in any survey or statistical study, always look at the sample size relative to the population. I've been surprised so often by how huge a jump researchers have made from the tiny agreement / correlation they observe in their inherently flawed sample choice.
- Još 1 odgovor
Novi razgovor -
-
-
Experiments are not the secure way to prove something in science that's why we take large no of observations to decrease the error rate!
- Kraj razgovora
Novi razgovor -
-
-
cc All Econ PhDs
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
"...or what his name is..." <audience giggles> Would love to know who he is poking fun at here.
-
Maybe he was talking generally against "appeal to authority".
- Još 1 odgovor
Novi razgovor -
-
-
Or you could simply change the experiment data to match the conclusions you desire. That’s known today as the “Mann Technique” You know ... he of the infamous “climategate” scandal
#IPCC -
or hacking p-value
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.