# With Comments

unknown

plain_text

a year ago

2.5 kB

3

Indexable

Never

^{}

# Do the package and library thing for model summary in 2d and 2f install.packages("modelsummary") library(modelsummary) # import the dataframe as variable 'z' z<-read.csv("entrepreneurs.csv") ### 2b # How many variables? Just count the groups. # How many observations in the 'control', 'treated' and 'true winners' groups? summary(z) # since there are no NA values in the Groups, I can add 1112 + 729 + 475 # to get the total number of observations, which = 2316. # I'd usually just use dim() to get the number of observations and variables, # but I'm playing Code Golf against another student, i.e. I'm aiming for # as few non-comment characters as possible ### 2c aggregate(.~z[,5],z[(3:10)],mean) ### 2d # write a big function to save characters: # the 's' function takes a single argument: the name of a # factor level of the variable "Group" in the main data # then the function subsets the data by removing all the # observations that have the given variable. # then the function adds a column 'b' to the data # and if an observation belongs to the control group, b = 0 # but if it doesn't, b = 1 s<-function(i){j<-z[z[,5]!=i,] j$b<-ifelse(j[,5]=="control",0,1) return(j)} # create a subset 'q' of the data, where the "true winners" group is # dropped, then add the 1 if treated and 0 if not q<-s("true winners") # write another function to save characters: # the function takes a subsetted dataframe as it's argument 'y' # first, the function creates a sub-function 'f' # the sub-function takes a variable as its first argument 'x', # and the given dataframe as its second argument, # then creates a linear model that regresses the passed variable # on the b (binary) variable in the passed dataframe. # back to the main function, the function creates a modelsummary of # the two linear models on column 10 of the given dataframe (which will # always be 'OperatesFirm') and column 11 of the given dataframe (which will # always be 'WorkHours') g<-function(y){ f<-function(x,y)lm(x~b,y) modelsummary(list(f(y[,10],y),f(y[,11],y)), stars=TRUE,gof_map=c("nobs","adj.r.squared"))} # look I'm sorry about this but I've got a Code Golf game to win # return the model summary for subset 'q' g(q) ### 2f # subset the data as before, but this time into subset 'e', and # drop the 'treated' factor level of the 'Groups' variable and # add a column b in which there is an 0 if the observation is # in the control group and a 1 if not e<-s("treated") # then return the model summary for subset 'e' g(e)