NOTE this stuff is broken right now, need to fix.
For convenience, you may wish to transform one or more of your covariates within the model estimation call. For example, imagine we want to natural log transform the variable dist in a linear regression:
cars <- transform(cars, distance = dist, dist.log = log(dist))
m.log <- lm(speed ~ log(distance), data = cars)
m.log2 <- lm(speed ~ dist.log, data = cars)Then we want to find quantities of interest when the dist variable is 26 to 56 (the first to third quartile):
library(smargins)
summary(smargins(m.log, distance = c(26, 56)))## distance mean sd median lower_2.5 upper_97.5
## 1 26 13.84199 0.4617833 13.85162 12.94072 14.74233
## 2 56 18.13741 0.5155141 18.14441 17.10916 19.12809We could also estimate the model with dist as a polynomial. For example:
# Find range of polynomial values
m2 <- lm(speed ~ poly(distance, 2), data = cars)
summary(smargins(m2, distance = quantile(distance, seq(0, 1, .1))))## distance mean sd median lower_2.5 upper_97.5
## 1 2.0 12.99141 0.4973046 12.99788 12.00160 13.96686
## 2 15.8 13.99183 0.4366190 13.99682 13.13463 14.83580
## 3 21.6 14.37630 0.4258560 14.37970 13.52668 15.19530
## 4 26.0 14.65377 0.4220096 14.65653 13.82173 15.46188
## 5 32.0 15.01237 0.4211610 15.01364 14.18265 15.82197
## 6 36.0 15.23878 0.4225430 15.23867 14.39817 16.05637
## 7 46.0 15.76047 0.4292674 15.75571 14.91550 16.58397
## 8 54.0 16.13224 0.4351293 16.13012 15.27046 16.97216
## 9 64.4 16.55495 0.4407401 16.55512 15.67824 17.41067
## 10 80.4 17.07156 0.4456192 17.07674 16.18547 17.92683
## 11 120.0 17.65311 0.5548389 17.65892 16.55362 18.71160Splines and other transformations should generally work as expected.
library(splines)
m3 <- lm(speed ~ bs(distance, df = 4), data = cars)
summary(smargins(m3, distance = seq(min(distance), max(distance), 10)))## distance mean sd median lower_2.5 upper_97.5
## 1 2 4.738110 2.1007892 4.712074 0.6612385 8.935140
## 2 12 7.334477 1.0585096 7.339090 5.2777960 9.397163
## 3 22 10.113624 0.6741707 10.120130 8.7670558 11.423903
## 4 32 12.874144 0.5274330 12.877663 11.8221971 13.905404
## 5 42 15.414629 0.5931427 15.417901 14.2500052 16.576044
## 6 52 17.533674 0.7341443 17.546929 16.0663042 18.953153
## 7 62 19.040774 0.7364010 19.053327 17.5840248 20.459963
## 8 72 19.996204 0.8859907 20.000110 18.2797111 21.705790
## 9 82 20.711011 1.2512117 20.707253 18.2404908 23.150062
## 10 92 21.507152 1.4442417 21.482937 18.6482456 24.337453
## 11 102 22.706577 1.5399503 22.694490 19.7192689 25.775006
## 12 112 24.631242 2.8411004 24.567075 19.2890227 30.238632