# exp R1 (first one) - 96931/2717785 (3.57%) are quote tweets - ITT: b = -0.079 [-0.171, 0.013], p = .091 distribution of tweet types with matching domains ```r type n_tweets pct_tweets <char> <int> <num> 1: retweet 2428321 89.35 2: tweet 155343 5.72 3: quote 96931 3.57 4: reply 37190 1.37 ``` modeling/results: quote vs. retweet t-values (for winsorization0.95, threshold70) - quote-tweet results are directionally same as retweets, but t-values are less strong (ie smaller effects) ![[compare-with-retweets_tvalues_conditionC 1.png]] ![[compare-with-retweets_estimates_conditionC.png]] ![[compare-with-retweets_SEs_conditionC.png]] cluster by user vs block - specs where user SE<=clustblock SE: 162/162 (varied winsorization, outcome [count/sum/frac], threshold) - clusterblock is more conservative (wider SEs) # exp R2 (trucker) hashtag - 11273/241712 (4.66%) of matched hashtags are in quote-tweets - ITT: b = -0.101 [-0.225, 0.024], p = .112 ```r type n_hashtags pct_hashtags <char> <int> <num> 1: quote 11273 4.66 2: reply 15528 6.42 3: retweet 201034 83.17 4: tweet 13877 5.74 ``` ![[compare-with-retweets_tvalues_conditionC 4.png]] ![[compare-with-retweets_estimates_conditionC 3.png]] ![[compare-with-retweets_SEs_conditionC 3.png]] # exp R2 (trucker) domains - 946528/7592482 (12.47%) are quote-tweets - ITT: b = -0.011 [-0.089, 0.068], p = .788 ```r type n_tweets pct_tweets <char> <int> <num> 1: retweet 6080900 80.09 2: quote 946528 12.47 3: tweet 433930 5.72 4: reply 131124 1.73 ``` ![[compare-with-retweets_tvalues_conditionC 5.png]] ![[compare-with-retweets_estimates_conditionC 4.png]] ![[compare-with-retweets_SEs_conditionC 4.png]] # exp R3 (deepstate) - 341228/2454486 (13.90%) are quote tweets - ITT: b = 0.080 [-0.031, 0.191], p = .159 ```r type n_tweets pct_tweets <char> <int> <num> 1: retweet 1959576 79.84 2: quote 341228 13.90 3: tweet 126245 5.14 4: reply 27437 1.12 ``` ![[compare-with-retweets_tvalues_conditionC 2.png]] ![[compare-with-retweets_estimates_conditionC 1.png]] ![[compare-with-retweets_SEs_conditionC 1.png]] # exp NR - 230775/4808015 (4.80%) are quote-tweets - ITT: b = -0.029 [-0.079, 0.020], p = .248 ```r type n_tweets pct_tweets <char> <int> <num> 1: retweet 4071947 84.69 2: tweet 421513 8.77 3: quote 230775 4.80 4: reply 83780 1.74 ``` ![[compare-with-retweets_tvalues_conditionC 3.png]] ![[compare-with-retweets_estimates_conditionC 2.png]] ![[compare-with-retweets_SEs_conditionC 2.png]]