Fit a Relative Risk Model for Binary data with Log Link

Fit a Relative Risk Model for Binary data with Log Link using the COPY method.

relRisk(
  formula,
  id,
  waves = NULL,
  data = parent.frame(),
  subset = NULL,
  contrasts = NULL,
  na.action = na.omit,
  corstr = "indep",
  ncopy = 1000,
  control = geese.control(),
  b = NULL,
  alpha = NULL
)

Arguments

formula

same as in geese

id

same as in geese

waves

same as in geese

data

same as in geese

subset

same as in geese

contrasts

same as in geese

na.action

same as in geese

corstr

same as in geese

ncopy

the number of copies of the original data in constructing weight.

control

same as in geese

b

initial values for regression coefficients as in geese but more difficult to obtain due to the log link.

alpha

same as in geese

Value

An object of class "geese" representing the fit.

References

Lumley, T., Kornmal, R. and Ma, S. (2006). Relative risk regression in medical research: models, contrasts, estimators, and algorithms. UW Biostatistics Working Paper Series 293, University of Washington.

Author

Jun Yan jyan.stat@gmail.com

Examples

## this example was used in Yu and Yan (2010, techreport)
data(respiratory)
respiratory$treat <- relevel(respiratory$treat, ref = "P")
respiratory$sex <- relevel(respiratory$sex, ref = "M")
respiratory$center <- as.factor(respiratory$center)
## 1 will be the reference level

fit <- relRisk(outcome ~ treat + center + sex + age + baseline + visit,
               id = id, corstr = "ar1", data = respiratory, ncopy=10000)
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: step size truncated due to divergence
#> Warning: glm.fit: algorithm did not converge
#> Warning: glm.fit: algorithm stopped at boundary value
summary(fit)
#> 
#> Call:
#> relRisk(formula = outcome ~ treat + center + sex + age + baseline + 
#>     visit, id = id, data = respiratory, corstr = "ar1", ncopy = 10000)
#> 
#> Mean Model:
#>  Mean Link:                 log 
#>  Variance to Mean Relation: binomial 
#> 
#>  Coefficients:
#>              estimate  san.se    wald         p
#> (Intercept) -1.067172 0.14658 53.0079 3.322e-13
#> treatA       0.383759 0.09608 15.9537 6.491e-05
#> center2      0.049071 0.06179  0.6307 4.271e-01
#> sexF         0.068237 0.07173  0.9048 3.415e-01
#> age         -0.001451 0.00153  0.8994 3.429e-01
#> baseline     0.688950 0.13276 26.9297 2.110e-07
#> visit       -0.035775 0.02009  3.1697 7.501e-02
#> 
#> Scale is fixed.
#> 
#> Correlation Model:
#>  Correlation Structure:     ar1 
#>  Correlation Link:          identity 
#> 
#>  Estimated Correlation Parameters:
#>        estimate    san.se  wald         p
#> alpha 0.0008631 0.0001281 45.43 1.578e-11
#> 
#> Returned Error Value:    0 
#> Number of clusters:   222   Maximum cluster size: 4 
#> 
## fit <- relRisk(outcome ~ treat + center + sex + age + baseline + visit,
##               id = id, corstr = "ex", data = respiratory)
## summary(fit)
## fit <- relRisk(outcome ~ treat + center + sex + age + baseline + visit,
##                id = id, corstr = "indep", data = respiratory)
## summary(fit)