Some preparation:

ESS <- transmute(ESS, # Recode several variables & keep only the recoded ones (i.e., transmute vs mutate). #<<
                 idno = zap_labels(idno),
                 # Make the following variables factors:
                 cntry = as_factor(cntry), 
                 gndr = as_factor(gndr),
                 facntr = as_factor(facntr),
                 mocntr = as_factor(mocntr),
                 # Make the following variables numeric:
                 imbgeco = max(imbgeco, na.rm = TRUE) - zap_labels(imbgeco), # Also turn scale around.
                 imueclt = max(imueclt, na.rm = TRUE) - zap_labels(imueclt), # Also turn scale around.
                 imwbcnt = max(imwbcnt, na.rm = TRUE) - zap_labels(imwbcnt), # Also turn scale around.
                 # Homophobia #<<
                 freehms = as_factor(freehms),
                 hmsfmlsh = as_factor(hmsfmlsh),
                 hmsacld = as_factor(hmsacld),
                 agea = zap_labels(agea),
                 pspwght = zap_labels(pspwght),
                 eduyrs = zap_labels(eduyrs))
ESS <- dplyr::filter(ESS,
                     # Now keep respondents of immigrant origin!
                     # facntr == "Yes" & mocntr == "Yes" & # Keep respondents of immigrant origin #<<
                       # Only respondents from direct neighbors of Denmark:
                       (cntry == "Denmark" | cntry == "Germany" | cntry == "Sweden" | cntry == "Norway")
)

# Casewise deletion of missing values
ESS <- drop_na(ESS)
  1. Get the ggplot2 cheat sheet, and check out the reference page of ggplot2. Look at geoms for univariate (one variable) figures. Make an appropriate (weighted) figure that describes the distribution of cntry. Which country (Denmark, Germany, or Sweden) has the largest number of observations? 
ggplot(data = ESS) +
  geom_bar(aes(x = cntry, weight = pspwght)) +
  labs(x = "Country of interview")

  1. Make an appropriate (weighted) figure that describes the distribution of agea. Across all four countries, are there more or less than 20 respondents who are older than 100? 
ggplot(data = ESS) +
  geom_histogram(aes(x = agea, weight = pspwght)) +
  labs(x = "Age")

  1. Are women more or less in favor of adoption rights for gay men and women? Make a plot that answers this question. Women are in favor of adoption rights for gay men and women.
ggplot(data = ESS, mapping = aes(x = hmsacld, weight = pspwght)) +
  geom_bar() +
  facet_grid(. ~ gndr) +
  labs(x = "Gay and lesbian couples should have right to adopt children") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

  1. Is this the same in all four countries? 
ggplot(data = ESS, mapping = aes(x = hmsacld, weight = pspwght)) +
  geom_bar() +
  facet_grid(cntry ~ gndr, scales = "free_y") +
  labs(x = "Gay and lesbian couples should have right to adopt children") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

  1. Add another country to your data set. Make it your personal country of origin, or some other country you are interested in (in case you are born in Denmark or your country of birth is not covered in the ESS). In which country are people most ashamed if a family member is gay? Use boxplots and different colors for the countries.
ESS <- import_rounds(rounds = 9, ess_email = "YOUR-EMAIL", format = "spss")

ESS <- transmute(ESS, # Recode several variables & keep only the recoded ones (i.e., transmute vs mutate). #<<
                 idno = zap_labels(idno),
                 # Make the following variables factors:
                 cntry = as_factor(cntry), 
                 gndr = as_factor(gndr),
                 facntr = as_factor(facntr),
                 mocntr = as_factor(mocntr),
                 # Make the following variables numeric:
                 imbgeco = max(imbgeco, na.rm = TRUE) - zap_labels(imbgeco), # Also turn scale around.
                 imueclt = max(imueclt, na.rm = TRUE) - zap_labels(imueclt), # Also turn scale around.
                 imwbcnt = max(imwbcnt, na.rm = TRUE) - zap_labels(imwbcnt), # Also turn scale around.
                 # Homophobia #<<
                 freehms = as_factor(freehms),
                 hmsfmlsh = as_factor(hmsfmlsh),
                 hmsacld = as_factor(hmsacld),
                 agea = zap_labels(agea),
                 pspwght = zap_labels(pspwght),
                 eduyrs = zap_labels(eduyrs))

# Some case selection, now also including: France!
ESS <- dplyr::filter(ESS, # Denmark, Sweden, Norway, Germany, and France.
              cntry == "Denmark" | cntry == "Sweden" | 
                cntry == "Norway" | cntry == "Germany" | cntry == "France")

# Casewise deletion of missing values
ESS <- drop_na(ESS)
ggplot(data = ESS) +
  geom_boxplot(aes(y = as.numeric(hmsfmlsh), fill = cntry, weight = pspwght)) +
  labs(y = "Not Ashamed if close family member \n was gay or lesbian")

  1. Find an alternative to using boxplots.
ggplot(data = ESS, mapping = aes(y = hmsfmlsh, x = cntry)) +
  geom_jitter(alpha = 0.1, aes(size = pspwght)) +
  geom_violin(mapping = aes(fill = cntry, weight = pspwght), 
              alpha = 0.6, draw_quantiles = c(0.25, 0.5, 0.75)) +
  labs(y = "Not Ashamed if close family member \n was gay or lesbian",
       x = "Country of interview")

  1. Remember that the years of education have some rather low and large values. Recode all values smaller than 10 years of education to missing. Also Recode all years of education larger than 20 to 20. Visualize how that changes the association between hmsfmlsh and years of education. Does it change the main conclusion/insight of that figure? 
ESS <- mutate(ESS,
              eduyrs_rec = case_when(
                eduyrs < 10 ~ as.numeric(NA), # Eduyears smaller 10 ~ Missing
                eduyrs > 20 ~ 20, # Eduyears larger 20 ~ 20
                TRUE ~ eduyrs) # Leave all others as is.
)

The old one:

ggplot(data = ESS, mapping = aes(y = hmsfmlsh, x = eduyrs, weight = pspwght)) +
  geom_point(aes(size = pspwght), alpha = 0.1) +
  geom_smooth() +
  labs(y = "Not Ashamed if close family member \n was gay or lesbian",
       x = "Years of education")

The new one:

ggplot(data = ESS, mapping = aes(y = hmsfmlsh, x = eduyrs_rec, weight = pspwght)) +
  geom_point(aes(size = pspwght), alpha = 0.1) +
  geom_smooth() +
  labs(y = "Not Ashamed if close family member \n was gay or lesbian",
       x = "Years of education")