Large data set, line graph, multiple lines, ggplot: need help!

I'm new to R and programming in general, and I am struggling to create a line graph with multiple lines, representing large groups of respondents. I work in development economics and I am using a large data set containing information on 18,000+ individuals in South Africa. I want to plot income on the x axis and years of education achieved on the y axis. Education is a discrete variable and only has values of 0-18 years. Income is continuous and spans from 652 (ZAR per month) to 20,000+. I then want to do this for 3 groups of people, representing 2,000 to 4,000 people each, and thus have 3 lines. I have tried several graphs and haven't gotten anywhere near what I need. Here is the code I have so far, but it is fairly useless as it creates a graph nothing like what I want (and yes, I know my data set name and var names are huge, but that is for a reason). Do I need to re-code the income data and put it in buckets? What am I doing wrong here? I put a link to a graph in a paper that I basically want to re-create, but with income instead of age.

e <- ggplot(data = Cross_w5_e_h_i_g_a_RStudio_25Sept23, aes(x = w5_hhinc_perm_CSGPool_CSM, y = w5_eduyrs_CSGPool_CSM_T1A)) +
  geom_line() +
  xlim(652, 20000) +

Very similar to the graph I want - except this one has age instead of income, and has only 2 lines:

See page 27, graph on top right of page (I tried to cut and paste this in, and it didn't work)

Would someone provide some advice on how to solve this?!

Btw, I tried to do reprex but I kept getting error messages.  Thanks.

I don't think you want a line plot. I expect the scatter in the data makes such a plot unreadable. Try using geom_smooth instead.
To get three lines, you need to have a column that labels each point as belonging to a group. If you post the output of


someone could give detailed advice about that.

This topic was automatically closed 42 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.