Coverting a numeric variable into a ordinal variable

Question

I am working on a data set that contains a variable called "JobSatisfaction" that is shown as int [1,2,3,4]. In order to proceed with my data analysis, I need to convert this variable into a ordinal variable.

JobSatisfaction is supposed to have four levels: low, medium, high, very high

After that I will need to do a linear regression.

Answer 1

You can just use ordered(). Here is an example

df <- data.frame(code = rep(letters[1:4], 5),
                 JobSatisfaction =  sample(rep(1:4,5))) # data frame df
df$JobSatisfaction <- ordered(df$JobSatisfaction, levels = 1:4,
                              labels = c("low", "medium", "high", "veryhigh")) # conversion

Answer 2

You are asking for a solution that convert a integer numeric variable into an ordered categorical variable.

I suggest you to use the package dplyr because for this task it is perfect.

    dplyr::mutate(my_df,  
                      JobSatisfaction = 
                          dplyr::recode_factor(JobSatisfaction,   
                             `1`="low", `2`="medium",  
                             `3`="high", `4` = "very high",  
                             .ordered = TRUE)  

recode is used for mapping the value of a variable to new values

the parameter .ordered = TRUE allows us to define that low < medium < high < very_high