Are the explicit measures correlated with language bias?

Read in behavior and language biases

countries_langs <- read_csv("../../data/other/countries_lang.csv") %>%
  mutate(language_name = ifelse(language_name == "Spanish; Castilian", "Spanish", language_name),
         language_name = ifelse(language_name == "Dutch; Flemish", "Dutch", language_name))


IAT_behavior_measures <- read_csv("IAT_behavior_measures.csv") %>%
  left_join(countries_langs %>% select(country_name, language_name, language_code)) %>%
  filter(type %in% c("country_fam_male", 
             "country_career_male", 
             "career_importance", 
             "family_importance",
             "actual_duties")) %>%
  group_by(type, language_code, sex) %>%
  summarize(mean = mean(mean)) 

lang_bias <- read_csv("career_effect_sizes.csv")

lang_bias_google <- read_csv("google_translate/career_effect_sizes_google.csv",
                             col_names = c("language_code",   "test",  "test_name", "lang_bias")) %>%
  filter(language_code != "he", language_code != "zu", language_code != "th") 
#,language_code !=  "ha",language_code !=  "id",language_code !=  "zh")


d <- left_join(IAT_behavior_measures, lang_bias) %>%
  mutate_if(is.character, as.factor) %>%
  filter(!is.na(lang_bias))

There are 22 languages represented here.

Measures

Behavior

ggplot(d, aes(x = mean)) +
  geom_histogram() +
  facet_wrap(~type, scales = "free_x")+
  theme_bw()

Correlation between measures - Hand-translations

d %>%
  mutate(type2 = ifelse(type %in% c("country_gender_D_score_diff", "country_means_D_score", "country_gender_D_score"), "D-score", ifelse(type %in% c("country_RT_ratio", "country_RT_mean"), "RT", "explicit"))) %>%
ggplot( aes(x = mean, y = lang_bias, group = sex, color = sex, shape = type2)) +
  geom_point() +
  geom_smooth(method = "lm") +
  facet_grid(.~type2 + type, scales = "free_x", drop = T) +
  theme_bw()

d %>%
  group_by(type, sex) %>%
  do(tidy(cor.test(.$mean, .$lang_bias))) %>%
  arrange(p.value) %>%
  select(-parameter, -method, -alternative) %>%
  kable()
type sex estimate statistic p.value conf.low conf.high
country_fam_male m -0.4425174 -2.2068315 0.0391791 -0.7282558 -0.0257047
country_fam_male all -0.3651060 -1.7538813 0.0947633 -0.6817686 0.0667824
actual_duties f 0.3147368 1.4829086 0.1536861 -0.1232228 0.6500821
country_career_male m -0.2716986 -1.2625678 0.2212680 -0.6220509 0.1693037
country_fam_male f -0.2011662 -0.9184176 0.3693442 -0.5740846 0.2408714
family_importance f 0.1190989 0.5364448 0.5975682 -0.3185025 0.5148549
actual_duties m 0.1139498 0.5129402 0.6136124 -0.3231851 0.5110083
career_importance f 0.1110479 0.4997119 0.6227311 -0.3258148 0.5088334
career_importance m -0.0172190 -0.0770170 0.9393753 -0.4356646 0.4073467
family_importance m 0.0128722 0.0575710 0.9546617 -0.4109666 0.4321354
country_career_male f -0.0035605 -0.0159230 0.9874536 -0.4245316 0.4186765

Correlation between measures - Google-translations

d <- left_join(IAT_behavior_measures, lang_bias_google) %>%
  mutate_if(is.character, as.factor) %>%
  filter(!is.na(lang_bias))

There are 24 languages represented here.

d %>%
  mutate(type2 = ifelse(type %in% c("country_gender_D_score_diff", "country_means_D_score", "country_gender_D_score"), "D-score", ifelse(type %in% c("country_RT_ratio", "country_RT_mean"), "RT", "explicit"))) %>%
ggplot( aes(x = mean, y = lang_bias, 
            group = sex, color = sex, shape = type2)) + 
  geom_point() +
  geom_smooth(method = "lm") +
  facet_grid(.~type2 + type, scales = "free_x", drop = T) +
  theme_bw()

d %>%
  group_by(type, sex) %>%
  do(tidy(cor.test(.$mean, .$lang_bias))) %>%
  arrange(p.value) %>%
  select(-parameter, -method, -alternative) %>%
  kable()
type sex estimate statistic p.value conf.low conf.high
country_career_male m -0.2693992 -1.3121047 0.2030113 -0.6068470 0.1503351
country_fam_male m -0.1911728 -0.9135289 0.3708681 -0.5520001 0.2299579
actual_duties m 0.1191114 0.5626880 0.5793369 -0.2986344 0.4985531
career_importance f 0.0756430 0.3558165 0.7253672 -0.3380696 0.4648551
actual_duties f -0.0534211 -0.2509256 0.8042004 -0.4471811 0.3576836
country_fam_male all -0.0524387 -0.2462984 0.8077348 -0.4463926 0.3585424
country_career_male f -0.0522501 -0.2454098 0.8084140 -0.4462411 0.3587073
family_importance f -0.0421212 -0.1977415 0.8450630 -0.4380744 0.3675202
career_importance m -0.0281069 -0.1318850 0.8962740 -0.4266660 0.3795938
family_importance m 0.0248419 0.1165550 0.9082701 -0.3823867 0.4239898
country_fam_male f 0.0121356 0.0569254 0.9551185 -0.3931859 0.4135080