model4 = glm(y~prod+NF+NF2, quasibinomial)

Analysis of Deviance Table
Model: quasibinomial, link: logit
Response: y
Terms added sequentially (first to last)
     Df Deviance Resid. Df Resid. Dev      F Pr(>F)
NULL                    29     2645.2
prod  1    73.95        28     2571.3 1.0803 0.3082
NF    1     2.52        27     2568.8 0.0368 0.8493
NF2   1   346.69        26     2222.1 5.0649 0.0331 *
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1