Now estimate five models, the first four using different
categories of the variable `min_ed_fct`. For example, use the
`subset` option in the `lm()` command to run a regression of
`score` on `cathhs` for only `min_ed_fct = 'drop out'` in the first
column. The second column should contain the same regression
using data only for `min_ed_fct = 'high school'` and so on.
In the fifth column, use all the data but control for
`min_ed_fct` in the regression.
- Now Estimate Five Models The First Four Using Different Categories Of The Variable Min Ed Fct For Example Use The 1 (20.96 KiB) Viewed 44 times
In Now estimate five models, the first four using different categories of the variable 'min_ed_fct. For example, use the subset" option in the 'Im command to run a regression of score on cathhs' for only "min_ed_fct 'drop out in the first column. The second column should contain the same regression using data only for "min_ed_fct = "high school and so on. the fifth column, use all the data but control for "min_ed_fct in the regression. 1. Interpret the coefficient on cathhs' in each of the first four columns, 2. Interpret the coefficient on cathhs' in the fifth column, 3. Interpret the coefficients on "min_ed_fct'why are there only three coefficients? which category is the reference group? 4. calculate the average of the coefficient on cathhs' across the first four columns.
**'{r, eval = F} models <- list 1m (score - cathhs, data = df, subset = min_ed_fct == "drop out"), modelsummary(models, vcov = 'robust', stars = T, gof_omit "[^R2 R2 Adj. Num. obs]") %>% kable_classic_20