Pinned Tweet
🚨It's finally out AND #OpenAccess!!!
Do you do survey experiments? This article is for you! 7 things that increase the risk of null/non-significant results & how to detect/prevent them. It's one of my fav things I've ever written so I hope you enjoy.😊
cup.org/3OQhKNv
🗓️ 𝐃𝐨 𝐲𝐨𝐮 𝐨𝐫 𝐲𝐨𝐮𝐫 𝐬𝐭𝐮𝐝𝐞𝐧𝐭𝐬 𝐝𝐨 𝐬𝐮𝐫𝐯𝐞𝐲 𝐞𝐱𝐩𝐞𝐫𝐢𝐦𝐞𝐧𝐭𝐬?
On 12/3, I'm hosting a free, 1 hr. online seminar called, "Doing Better Survey Experiments" from 1pm - 2pm (ET). Please help spread the word if you can! 🙏
instats.org/seminar/doing-be…
John V. Kane retweeted
🥳 Wow am I excited to FINALLY be sharing this co-authored article with @littleconnors out today in @PolBehavior!
We show that people feel social pressure to overreport political engagement, but that this pressure can be reduced in surveys by "un-priming politics" 👍
🚨 New publication alert: Do Americans change their attitudes toward "culture war" groups when these groups shift how they vote in presidential elections?
In a word, 𝐧𝐨. 👎 An important case of null results, we find no clear shift in attitudes, either for better or for worse.
John V. Kane retweeted
Yay this paper took many years of data collection - so happy it's finally out!!
🥳 Wow am I excited to FINALLY be sharing this co-authored article with @littleconnors out today in @PolBehavior!
We show that people feel social pressure to overreport political engagement, but that this pressure can be reduced in surveys by "un-priming politics" 👍
🥳 Wow am I excited to FINALLY be sharing this co-authored article with @littleconnors out today in @PolBehavior!
We show that people feel social pressure to overreport political engagement, but that this pressure can be reduced in surveys by "un-priming politics" 👍
John V. Kane retweeted
Enjoyed this conversation!
Many thanks to @verasight_data for interviewing me about my recent research with @CBWlezien ! Had fun discussing how the public (mis)understands inflation information, and why it matters 👍
youtu.be/KO4Ask_7vto?is=fTcQ…
John V. Kane retweeted
"The inflation rate is still positive, right? Prices are still increasing, just at a slower rate than before. Yet again, over half the sample said that that would mean that prices decreased. Again conflating rates with prices."
@UptonOrwell, Clinical Associate Professor at @NYUCGA, on his work and his new working paper with Christopher Wlezien, "The Effects of Inflation Information: Rates, Prices, and Politics in the Public Mind."
Kane and Wlezien's paper uses Verasight data. Read the full paper here: doi.org/10.33774/apsa-2026-v…
Watch the full interview on YouTube: youtu.be/KO4Ask_7vto
Many thanks to @verasight_data for interviewing me about my recent research with @CBWlezien ! Had fun discussing how the public (mis)understands inflation information, and why it matters 👍
youtu.be/KO4Ask_7vto?is=fTcQ…
I can totally see using AI when hiring a graphic designer just isn't in the cards (so, the real options are: No visual vs. AI visual).
That said, if you do use AI for design, please *check it thoroughly*
@AdventurelandLI, I love you very much, so I'm looking at you here...
Difficult to imagine a higher honor than being included in this group, and by this scholar. Thank you, @jayvanbavel !!! 🙏
Excited to share this fully revamped WP w/ @CBWlezien on the effects of information about economic inflation on people's economic and political attitudes. Lots of great data from @verasight_data, two of my favorite experimental designs ever, plus some extra-fun @Stata graphs! 😁
John V. Kane retweeted
🧐 What do citizens think about "null results" in scientific research?
To find out, @JohnHolbein1 & I fielded a large-scale online experiment. We gave respondents straightforward info about a study, asked them some Qs, showed them the results, then asked them Qs again.
🧐 What do citizens think about "null results" in scientific research?
To find out, @JohnHolbein1 & I fielded a large-scale online experiment. We gave respondents straightforward info about a study, asked them some Qs, showed them the results, then asked them Qs again.
And it's not just about "noisy null" effects--though there's some variation across study type, the overall effects show that even precisely estimated nulls are disadvantaged relative to studies showing a "statistically significant effect."