create a character column by combining estimate, lower and upper columns.
This is similar to tidyr::unite().
unite_ci(
x,
col = NULL,
...,
remove = TRUE,
digits = 2,
m100 = TRUE,
percent = FALSE,
ci = FALSE
)
merge_ci_df(x, e = 3, l = e + 1, u = e + 2, digits = 2)
merge_pci_df(x, e = 3, l = e + 1, u = e + 2, digits = 2)a data frame with at least three columns defining an estimate, lower bounds, and upper bounds.
the quoted name of the replacement column to create
three columns to bind together in the order of Estimate, Lower, and Upper.
if TRUE (default), the three columns in ... will be replaced by col
the number of digits to retain for the confidence interval.
TRUE if the result should be multiplied by 100
TRUE if the result should have a percent symbol added.
TRUE if the result should include "CI" within the braces (defaults to FALSE)
the column of the estimate (defaults to the third column). Otherwise, a number
the column of the lower bound (defaults to the fourth column). Otherwise, a number
the column of the upper bound (defaults to the fifth column), otherwise, a number
a modified data frame with merged columns or one additional column representing the estimate and confidence interval
fit <- lm(100/mpg ~ disp + hp + wt + am, data = mtcars)
df <- data.frame(v = names(coef(fit)), e = coef(fit), confint(fit), row.names = NULL)
names(df) <- c("variable", "estimate", "lower", "upper")
print(df)
#> variable estimate lower upper
#> 1 (Intercept) 0.740647656 -0.774822875 2.256118188
#> 2 disp 0.002702925 -0.002867999 0.008273849
#> 3 hp 0.005274547 -0.001400580 0.011949674
#> 4 wt 1.001303136 0.380088737 1.622517536
#> 5 am 0.155814790 -0.614677730 0.926307310
unite_ci(df, "slope (CI)", estimate, lower, upper, m100 = FALSE, percent = FALSE)
#> variable slope (CI)
#> 1 (Intercept) 0.74 (-0.77--2.26)
#> 2 disp 0.00 (-0.00--0.01)
#> 3 hp 0.01 (-0.00--0.01)
#> 4 wt 1.00 (0.38--1.62)
#> 5 am 0.16 (-0.61--0.93)