### Table 1. Standard binomial model.

"... In PAGE 5: ... The null hypothesis is defined as p H = q : . For all possible values of d, Table1 pres- ents the figures to compare our measure with the standard ones. To compute the Bayes Factor, we con-... ..."

### Table 1. Rate of the size of log

1997

Cited by 2

### Table 2: Estimation using Negative Binomial Regression

in Abstract

"... In PAGE 7: ... We performed a negative binomial regression because the dependent variable (number of worms or number of variants released per month) fit well the negative binomial distribution. The results of the regression are reported in Table2 , column 2. Only the coefficients on dummy for FastTrack and eDonkey networks turned out to be significant predic- tors of worm count8.... In PAGE 7: ... Surprisingly, the coefficient on number of users was insignificant. A similar trend was observed for variant count data ( Table2 , column 3). An implicit assumption in the above estimation was that worm writers are focused only on P2P networks and respond directly to change in user population.... ..."

### Table 2: Estimation using Negative Binomial Regression

"... In PAGE 7: ... We performed a negative binomial regression because the dependent variable (number of worms or number of variants released per month) fit well the negative binomial distribution. The results of the regression are reported in Table2 , column 2. Only the coefficients on dummy for FastTrack and eDonkey networks turned out to be significant predic- tors of worm count8.... In PAGE 7: ... Surprisingly, the coefficient on number of users was insignificant. A similar trend was observed for variant count data ( Table2 , column 3). An implicit assumption in the above estimation was that worm writers are focused only on P2P networks and respond directly to change in user population.... ..."

### Table 2: Checkability of the binomial regression model

1998

"... In PAGE 8: ... The second stage assumes i i N ; 2 0 0 2 ; i = 1; :::; 20 with the illustrative informative priors, 2 IG(c; d) such that E( 2 ) = 10; V ar( 2 ) = 3; 2 IG(e; f) such that E( 2 ) = 1; V ar( 2 ) = 1 and N ??0 2 ; ?100 0 1 : Sampling based tting of this model is accomplished using Metropolis steps within a Gibbs sampler. Table2 summarizes the checkability of this model in terms of the I(d) and the interstage corre- lations using 1000 replications each providing 1000 pos- terior samples. We see that associations are weak, that d2j1 should be very e ective, d1 less so with the d2 apos;s o ering little promise.... ..."

Cited by 2

### Table A: Binomial Logit Regression Coefficients

2001

Cited by 1

### Table 2. Binomial/highpass Filter Matrix

1998

Cited by 1

### Table 2: Rising k-binomial transforms

Cited by 1