EDIT - response to Scortchi question - no, not actually:
> m = glm(cbind(young, adults) ~ as.factor(month) + effort, family = "quasibinomial")
> summary(m)
Call:
glm(formula = cbind(young, adults) ~ as.factor(month) + effort, family = "quasibinomial")
Deviance Residuals:
Min 1Q Median 3Q Max
-2.6829 -1.1138 0.0000 0.9717 4.0090
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -0.7868764 0.2170738 -3.625 0.000306 ***
as.factor(month)2 0.8857561 0.2606780 3.398 0.000710 ***
as.factor(month)3 0.7055741 0.2918895 2.417 0.015843 *
as.factor(month)4 0.3943665 0.3269973 1.206 0.228138
as.factor(month)5 0.4831113 0.3730987 1.295 0.195713
as.factor(month)6 -0.5217349 0.5027560 -1.038 0.299676
as.factor(month)7 0.1612901 0.4333682 0.372 0.709851
as.factor(month)8 0.5114890 0.3545159 1.443 0.149444
as.factor(month)9 0.7741060 0.3126087 2.476 0.013466 *
as.factor(month)10 0.6601093 0.2609937 2.529 0.011608 *
as.factor(month)11 0.4891778 0.2647303 1.848 0.064967 .
as.factor(month)12 0.4743091 0.2565709 1.849 0.064849 .
effort 0.0032506 0.0007976 4.075 5.02e-05 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for quasibinomial family taken to be 1.270962)
Null deviance: 1518.0 on 878 degrees of freedom
Residual deviance: 1447.8 on 866 degrees of freedom
(750 observations deleted due to missingness)
AIC: NA
Number of Fisher Scoring iterations: 4
Warning message:
In summary.glm(m) :
observations with zero weight not used for calculating dispersion
>
>
> m = glm(cbind(young, adults) ~ as.factor(month), family = "quasibinomial")
> summary(m)
Call:
glm(formula = cbind(young, adults) ~ as.factor(month), family = "quasibinomial")
Deviance Residuals:
Min 1Q Median 3Q Max
-3.1142 -1.1266 0.0000 0.9235 3.6484
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -0.2296 0.1590 -1.444 0.14890
as.factor(month)2 0.8610 0.2059 4.181 3.09e-05 ***
as.factor(month)3 1.0887 0.2062 5.280 1.51e-07 ***
as.factor(month)4 0.4184 0.2374 1.762 0.07822 .
as.factor(month)5 0.1495 0.3086 0.485 0.62802
as.factor(month)6 -0.6177 0.3872 -1.595 0.11091
as.factor(month)7 -0.4636 0.3666 -1.265 0.20622
as.factor(month)8 0.1089 0.2976 0.366 0.71440
as.factor(month)9 0.4932 0.2490 1.980 0.04787 *
as.factor(month)10 0.6322 0.2096 3.016 0.00261 **
as.factor(month)11 0.4919 0.2152 2.286 0.02243 *
as.factor(month)12 0.2296 0.2127 1.079 0.28071
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for quasibinomial family taken to be 1.309215)
Null deviance: 2400.1 on 1345 degrees of freedom
Residual deviance: 2310.4 on 1334 degrees of freedom
AIC: NA
Number of Fisher Scoring iterations: 4
Warning message:
In summary.glm(m) :
observations with zero weight not used for calculating dispersion
>
>
>
> m = glm(cbind(young, adults) ~ effort, family = "quasibinomial")
> summary(m)
Call:
glm(formula = cbind(young, adults) ~ effort, family = "quasibinomial")
Deviance Residuals:
Min 1Q Median 3Q Max
-2.718 -1.119 0.000 1.011 4.236
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -0.326899 0.102473 -3.190 0.00147 **
effort 0.003827 0.000688 5.563 3.52e-08 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for quasibinomial family taken to be 1.268467)
Null deviance: 1518.0 on 878 degrees of freedom
Residual deviance: 1475.4 on 877 degrees of freedom
(750 observations deleted due to missingness)
AIC: NA
Number of Fisher Scoring iterations: 4
Warning message:
In summary.glm(m) :
observations with zero weight not used for calculating dispersion
