R: Examples for 'emmeans::mvcontrast'

### ** Examples

MOats.lm <- lm(yield ~ Variety + Block, data = MOats)
MOats.emm <- emmeans(MOats.lm, ~ Variety | rep.meas)
mvcontrast(MOats.emm, "consec", show.ests = TRUE)  # mult.name defaults to rep.meas

$estimates
contrast = Marvellous - Golden Rain:
 rep.meas    estimate    SE df t.ratio p.value
 rep.meas0       6.67  7.84 10   0.851  0.4148
 rep.meas0.2    10.00  9.34 10   1.071  0.3093
 rep.meas0.4     2.50 12.30 10   0.203  0.8430
 rep.meas0.6     2.00 10.33 10   0.194  0.8503

contrast = Victory - Marvellous:
 rep.meas    estimate    SE df t.ratio p.value
 rep.meas0     -15.17  7.84 10  -1.936  0.0817
 rep.meas0.2   -18.83  9.34 10  -2.017  0.0713
 rep.meas0.4    -6.33 12.30 10  -0.515  0.6177
 rep.meas0.6    -8.33 10.33 10  -0.807  0.4385

Results are averaged over the levels of: Block 

$tests
 contrast                 T.square df1 df2 F.ratio p.value
 Marvellous - Golden Rain    3.082   4   7   0.539  0.9174
 Victory - Marvellous        9.181   4   7   1.607  0.4726

P value adjustment: sidak

# Test each mean against a specified null vector
mvcontrast(MOats.emm, "identity", name = "Variety",
           null = c(80, 100, 120, 140), adjust = "none")

 Variety     T.square df1 df2 F.ratio p.value
 Golden Rain   10.001   4   7   1.750  0.2430
 Marvellous    26.628   4   7   4.660  0.0377
 Victory       10.232   4   7   1.791  0.2352

# (Note 'name' is passed to contrast() and overrides default name "contrast")

# 'mult.name' need not refer to a multivariate response
mvcontrast(MOats.emm, "trt.vs.ctrl1", mult.name = "Variety")

 contrast                T.square df1 df2 F.ratio p.value
 rep.meas0.2 - rep.meas0   21.498   3   8   5.733  0.0634
 rep.meas0.4 - rep.meas0   37.578   3   8  10.021  0.0131
 rep.meas0.6 - rep.meas0  104.700   3   8  27.920  0.0004

P value adjustment: sidak

Examples for 'emmeans::mvcontrast'

Multivariate contrasts