Table 4

Regression Models to Explain Double Jeopardy in Long Tail with Log Average per Viewer as the Dependent Variable

StatisticModel 1Model 2Model 3Model 4
βTβTβTβT
Unique (log)  .191**24.89  .203**  26.65  .205**  26.85  .033**    5.85
News−.198**−24.05−.199**−24.10−.227**−37.28
Lifestyle−.128−12.02−.128**−12.02−.089**−11.33
Sports  .058    3.14  .057    3.10−.131**  −9.48
Months                 
Visits (root)  .504**140.72
Control
Intercept0.315**12.210.310**  12.170.301**  10.960.063**  3.23
Adjusted R2  .025  .052  .053  .482
  • Note: N = 24,000. The dependent variable is the logarithm of average total pages viewed in millions.

  • After adding monthly data as an independent variable, the author found that there were no significant effects on beta values of the independent variables and controls.

  • ** p < .01.