Table 1 Predicting diversionary tweets (CJI) from threatening media coverage (Russia-Mueller; columns 1–3) and predicting suppression from diversionary tweets (columns 4–6).

From: Using the president’s tweets to understand political diversion in the age of social media

Dependent variable

CJI tweetst

NYTa

ABCa

Averageb

 

(1)

(2)

(3)

(4)

(5)

(6)

NYT Russia/Muellert

0.012

     
 

(0.004) p = 0.005

     
 

[0.005] p = 0.007

     

ABC Russia/Muellert

 

0.213

    
  

(0.084) p = 0.012

    
  

[0.078] p = 0.006

    

Average Russia/Muellert

  

0.226

   
   

(0.067) p = 0.001

   
   

[0.062] p = 0.000

   

CJI tweetst−1

o

o

o

−0.403

−0.038

−0.050

    

(0.207) p = 0.052

(0.020) p = 0.052

(0.020) p = 0.016

    

[0.219] p = 0.066

[0.020] p = 0.061

[0.022] p = 0.024

N

721

721

721

703

710

703

  1. Each model included control variables for each week during the sampling period and long-term time trends as well as the appropriate number of lagged observations for the dependent variable (see “Methods”). Table entries are coefficients (OLS standard errors) [Newey-West standard errors].
  2. aCoverage of Russia-Mueller on day t.
  3. bAverage of the standardized values of coverage of NYT and ABC.
  4. oLagged predictor is shown only when of interest.
Back to article page