Pew Survey

1. This will change the variable web1a, which represents the social media website Twitter, into a factor that can then be recoded.

pew <- pew %>% 
  mutate(web1a = as.factor(web1a))


pew %>% 
  count(web1a)

The data for web1a shows the answers to whether or not respondents use Twitter. This will recode web1a so that the answers will appear as “Yes” and “No” instead of “1” and “2”. This will also change the answers of “Don’t know” and “Refused” to NULL, to indicate that the data is missing. It will also changed the name of the factor from “web1a” to “Twitter”.

pew <- pew %>%
  mutate(Twitter = fct_recode(web1a, 
                                 "Yes" = "1", "No" = "2", NULL = "8", NULL = "9"))

pew %>% 
  count (Twitter)

2. This will change educ2, which represents education level, into a factor like Twitter.

pew <- pew %>% 
  mutate(educ2 = as.factor(educ2))

pew %>%
  count(educ2)

NA

Like with web1a, this will change each of the answers from a number to a corresponding level of education. “Don’t know” and “Refused” answers will also be changed to NULL to indicate that the data is missing. It will also changed the name of the factor from “educ2” to “education_level”.

pew <- pew %>% 
  mutate(education_level = fct_recode(educ2, "Less than HS" = "1", "Some HS" = "2", "HS graduate" = "3", "Some college" = "4", "Associate degree" = "5", 
                                    "College degree" = "6", "Some grad school" = "7", "Grad degree" = "8", NULL = "98", NULL = "99"))
pew %>%
  count(education_level)

NA

3. These tables show the count data for Twitter, education_level, and both. The first table shows the data for Twitter.

pew %>%
  count(Twitter)

This table shows the data for education_level.

pew %>% 
  count(education_level)

This table shows the combined data for Twitter and education_level.

pew %>% 
  drop_na(Twitter, education_level) %>%
  count(Twitter, education_level)

4. This will create graph showing the use of Twitter by level of education.

pew %>% 
  drop_na(education_level) %>% 
  drop_na(Twitter) %>%
  ggplot(aes(x = education_level, fill = Twitter)) +
  geom_bar() + 
  scale_fill_viridis_d() +
  coord_flip() +
  labs(y = "Count", 
       x = "Education Level", 
       title = "Use of Twitter by Education Level")

5. This will combine different data from education_level into two categories, HS or less and More than HS.

pew <- pew %>% 
  mutate(education_level = fct_collapse(education_level, HS_or_less = c("Less than HS", "Some HS", "HS graduate"),
                                     more_than_HS = c("Some college", "Associate degree", "College degree", "Some grad school", "Grad degree")))

pew %>% 
  count(education_level)

This will create a graph with the new categories of education_level compared to Twitter usage.

pew %>% 
  drop_na(education_level, Twitter) %>% 
  ggplot(aes(x = education_level, fill = Twitter)) +
  geom_bar(position = "fill") + 
  scale_fill_viridis_d() +
  coord_flip() +
  labs(y = "Count", 
       x = "Education Level", 
       title = "Use of Twitter by Education Level")