glm output in R: analysis without coefficients Generally, coefficients and their p values are focused upon while assessing the regression output. However, there are other things mentioned. How can we analyze the output of glm without the coefficients: 
> summary(mod)

Call:
glm(formula = outvar ~ ., family = binomial, data = mydf)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.3537  -0.8172  -0.6462   1.2131   2.2757  

Coefficients:
....
....


(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 8973.8  on 7760  degrees of freedom
Residual deviance: 8526.6  on 7752  degrees of freedom
AIC: 8544.6

Number of Fisher Scoring iterations: 4

Can I use the glm output shown above to understand my regression without coefficients being available?
 A: If the covariates explain the response properly, they should lower deviance statistically significantly. Deviance analysis can be performed using anova(). In the output table, Null Deviance is where only the intercept is added to fit while Residual Deviance is from the fitted model. The difference follows the chi-squared distribution and, if it is statistically significant, the fitted model can be considered to improve model fit - it can be simply done using anova() as shown below.
Here deviance analysis can be performed as the null and fitted models are nested - only some covariates are added to the null model. If a non-nested model (eg time series model) is to be compared, an information criterion can be used. AIC and BIC are popular and AIC is shown by default.
counts <- c(18,17,15,20,10,20,25,13,12)
outcome <- gl(3,1,9)
treatment <- gl(3,3)
d.AD <- data.frame(treatment, outcome, counts)
glm.D93 <- glm(counts ~ outcome + treatment, family = poisson())
glm.reduced <- glm(counts ~ 1, family = poisson())

glm.D93
#Call:  glm(formula = counts ~ outcome + treatment, family = poisson())

#Coefficients:
#  (Intercept)     outcome2     outcome3   treatment2   treatment3  
#    3.045e+00   -4.543e-01   -2.930e-01    1.338e-15    1.421e-15  

#Degrees of Freedom: 8 Total (i.e. Null);  4 Residual
#Null Deviance:     10.58 
#Residual Deviance: 5.129   AIC: 56.76

anova(glm.reduced, glm.D93, test = "Chisq")
#Analysis of Deviance Table

#Model 1: counts ~ 1
#Model 2: counts ~ outcome + treatment
#Resid. Df Resid. Dev Df Deviance Pr(>Chi)
#1         8    10.5814                     
#2         4     5.1291  4   5.4523    0.244

