Prefrosh2022_preprocess

cleaning out ineligible participants

df.prefrosh2022 = df.prefrosh2022.deid %>% 
  filter(age18 == 1) %>% 
  group_by(PID) %>% 
  slice(1)

#removing participants who had more than half NA's
# For Fall 2022 we didn't get amazing participation so I commented out this line
#df.prefrosh2022 <- df.prefrosh2022[rowSums(is.na(df.prefrosh2022)) < 55,]

reverse-scored items

#reverse-scored items: LayEmpathy_3, TIPI_Criti, TIPI_Anx, TIPI_Reserv, TIPI_Disorg, TIPI_Conven, TAI_1, TAI_3, TAI_6, TAI_7, TAI_10, TAI_13, TAI_14, TAI_16, TAI_19, NeedToBelong_2, LifeSatisfaction_6, CESD_5, CESD__8, loneliness_3, and loneliness_6.

df.prefrosh2022 <- df.prefrosh2022 %>% 
  mutate(LifeSatisfaction_7R = 8 - LifeSatisfaction_7R,
         LayEmpathy_3R = 8 - LayEmpathy_3R,
         TIPI_Criti_R = 8 - TIPI_Criti_R,
         TIPI_Anx_R = 8 - TIPI_Anx_R,
         TIPI_Reserv_R = 8 - TIPI_Reserv_R,
         TIPI_Disorg_R = 8 - TIPI_Disorg_R,
         TIPI_Conven_R = 8 - TIPI_Conven_R,
         CESD_4R = 5 - CESD_4R,
         CESD_6R = 5 - CESD_6R,
         loneliness_3R = 6 - loneliness_3R,
         loneliness_6R = 6 - loneliness_6R)

mean/sum scores

df.prefrosh2022 <- df.prefrosh2022 %>% 
  rowwise() %>% 
  mutate(layEmpathy = mean(c(LayEmpathy_1,
                             LayEmpathy_2,
                             LayEmpathy_3R)),
         extraversion = mean(c(TIPI_Extra,
                               TIPI_Reserv_R)),
         agreeableness = mean(c(TIPI_Criti_R,
                                TIPI_Symp)),
         conscientiousness = mean(c(TIPI_Depen,
                                    TIPI_Disorg_R)),
         emotionalStability = mean(c(TIPI_Anx_R,
                                     TIPI_EmoSta)),
         openToExperience = mean(c(TIPI_Open,
                                   TIPI_Conven_R)),
         stress = mean(c(Stress_1,
                         Stress_2)),
         TAI = sum(c(TAI_7,
                     TAI_8,
                     TAI_15,
                     TAI_16,
                     TAI_18)),
         EROS = mean(c(EROS1_1,
                       Empathy_10,
                       EROS1_6,
                       EROS1_7,
                       Empathy_6,
                       EROS1_9)),
         Satwithlife = mean(c(LifeSatisfaction_3,
                              LifeSatisfaction_4,
                              LifeSatisfaction_1,
                              LifeSatisfaction_6,
                              LifeSatisfaction_9)),
         loneliness = mean(c(loneliness_1,
                             loneliness_2,
                             loneliness_3R,
                             loneliness_4,
                             loneliness_5,
                             loneliness_6R,
                             loneliness_7,
                             loneliness_8)),
         CESD = sum(c(CESD_1,
                      CESD_2,
                      NegativeWellBeing_1,
                      CESD_3,
                      CESD_4R,
                      NegativeWellBeing_10,
                      CESD_6R,
                      CESD_7,
                      CESD_8)),
         ideo = mean(c(PoliIdeology_general,
                       PoliIdeology_social,
                       PoliIdeology_economic))) %>% 
  ungroup()

write csv

#write.csv(df.prefrosh2022, "~/Google Drive/Shared drives/Stanford Communities Project/2022-2023/MASTER/Prefrosh_survey/Fall 2022/df.prefrosh2022_1_10.csv", row.names = F)