Solved – Creating formula object for coxph()

cox-modelrsurvival

I am trying to create the formula object for coxph() manually, as I want to reproduce it in RSRuby. Note that the response variable needs to be a Surv object, the output of the Surv() method. The Surv object is basically a matrix with columns time and status.

Now, I am doing the following:

length_of_stay <- c(13, 4, 5, 21, 33, 10) 
exited_care <- c(1, 0, 1, 1, 0, 1) 
survival_object <- Surv(length_of_stay, exited_care)
gender <- c(1, 0, 1, 0, 1, 0)
mydata <- data.frame(length_of_stay = length_of_stay, 
                     exited_care = exited_care, 
                     gender = gender)
data_frame_for_formula <- data.frame(cbind(survival_object, gender))
my_formula <- formula(data_frame_for_formula)
mod.los <- coxph(formula = my_formula, data = mydata)

and getting the following error message:

"Error in eval(expr, envir, enclos) : object 'status' not found"

traceback() shows the formula is

time ~ status + gender

How can I avoid that and make the survival object the response variable?

Best Answer

Your issue arise from how formula.data.frame (the method associated with data.frames) works and how data.frame(cbind(...)) strips the Surv object of the Surv class attribute.

What you want is

 mod.los <- coxph(Surv(length_of_stay, exited_care)~ gender, data = mydata)

Or perhaps

  mod.los <- coxph(Surv(time,status) ~ gender, data = data_frame_for_formula)

Related Solutions

Solved – “Object not found” error in gls

From the documentation of ?gls: data: an optional data frame

In relation, the documentation of ?read.spss shows a parameter to.data.frame, whose default is FALSE, so typically reg1 will be a list instead of a data.frame.

The code you provided is not useful for testing on my system (as you do not provide the actual dataset), but this will probably work (disregarding library statements):

reg1 <- read.spss("URL of the spss file", to.data.frame=TRUE)
class(reg1) #check that it is indeed a data.frame
colnames(reg1) #check that all column names are properly imported
model1 <- gls(v1 ~ x1 + x2 + x3 + x4 + x5 + x6, correlation=corARMA(p=1), data=reg1)

Solved – Percentages as the response variable in GLMM (glmer), proportional binomial or not

I think that You might use simply a discrete binomial GLMM rather than continuous, which is just slightly different from the model You described. By the way, the warning message You've mentioned is no error: it simply notifies You, that the binomial response variable was continuous (having non-integer, i.e. non-zero and non-one values). If the non-integer values are between zero and one, there should be no problem.

If I understand correctly, You are interested in whether the structural vegetation coverage influences the presence of P. malvae eggs, correct? In that case, Occupancy should be the response variable, because You expect change in the presence of eggs in response to other environmental variables. Having the cause and causation in the right order helps to make sense of the results of such ecological models. In my opinion, the model You might want to use would look something like this:

glmer(Occupancy~VS_G+HP_spp+(1|VS_Date)+(1|Pair_nr), family="binomial", data=PM_data106)

In this model, You can add all 3 variables representing vegetation-coverages, although You should keep an eye out for the possible interactions between the three coverage variables. Also, i think it would make more ecological sense, to specify the hostplant species as fixed effect, because it has relevance to see, whether one plant species or another is preferred by the animal for laying eggs.

Cheers,

Best Answer

Related Solutions

Solved – “Object not found” error in gls

Solved – Percentages as the response variable in GLMM (glmer), proportional binomial or not

Related Question