mgaughan/24_deb_pkg_gov
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

updating EDA around outcome variables

Browse Source
This commit is contained in:
Matthew Gaughan 2024-06-13 13:40:27 -05:00
parent b48a684185
commit 00a1c5d157
2 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
R/contribRDDAnalysis.R
View File

@ -43,6 +43,11 @@ mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg")
#logging #logging
all_actions_data$logged_count <- log(all_actions_data$count) all_actions_data$logged_count <- log(all_actions_data$count)
all_actions_data$log1p_count <- log1p(all_actions_data$count) all_actions_data$log1p_count <- log1p(all_actions_data$count)
#EDA
range(all_actions_data$log1p_count) # 0.000000 6.745236
mean(all_actions_data$log1p_count) # 1.200043
var(all_actions_data$log1p_count) # 1.753764
median(all_actions_data$log1p_count) # 0.6931472
# now for merge # now for merge
mrg_actions_data$logged_count <- log(mrg_actions_data$count) mrg_actions_data$logged_count <- log(mrg_actions_data$count)
mrg_actions_data$log1p_count <- log1p(mrg_actions_data$count) mrg_actions_data$log1p_count <- log1p(mrg_actions_data$count)

3
R/readmeRDDAnalysis.R
View File

@ -45,6 +45,7 @@ mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg")
#log the dependent #log the dependent
all_actions_data$logged_count <- log(all_actions_data$count) all_actions_data$logged_count <- log(all_actions_data$count)
all_actions_data$log1p_count <- log1p(all_actions_data$count) all_actions_data$log1p_count <- log1p(all_actions_data$count)
range(all_actions_data$log1p_count)
# 3 rdd in lmer analysis # 3 rdd in lmer analysis
# rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design # rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc # lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
@ -55,8 +56,10 @@ library(lattice)
#some more EDA to go between Poisson and neg binomial #some more EDA to go between Poisson and neg binomial
var(all_actions_data$log1p_count) # 1.125429 var(all_actions_data$log1p_count) # 1.125429
mean (all_actions_data$log1p_count) # 0.6426873 mean (all_actions_data$log1p_count) # 0.6426873
median(all_actions_data$log1p_count) #0
var(all_actions_data$count) # 268.4449 var(all_actions_data$count) # 268.4449
mean (all_actions_data$count) # 3.757298 mean (all_actions_data$count) # 3.757298
median(all_actions_data$count) # 0
#all_log1p_gmodel <- glmer.nb(log1p_count ~ D * week_offset+ scaled_project_age + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1, control=glmerControl(optimizer="bobyqa", #all_log1p_gmodel <- glmer.nb(log1p_count ~ D * week_offset+ scaled_project_age + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1, control=glmerControl(optimizer="bobyqa",
# optCtrl=list(maxfun=1e5))) # optCtrl=list(maxfun=1e5)))
all_log1p_gmodel <- readRDS("final_models/0510_rm_all.rda") all_log1p_gmodel <- readRDS("final_models/0510_rm_all.rda")