'LS Means' statistics reporting

Creates a desc object for "LS Means" statistics reporting.

For more examples see the website: ClinReport website

report.lsmeans(lsm, at.row = NULL, infer = c(T, T), round = 2, x1,
  x2, x3, x1.name, x2.name, x3.name, data, contrast, contrast.name, type,
  transpose = FALSE, y.label = NULL)

Arguments

lsm	emmGrid object (result of a emmeans call)
at.row	Character. Passed to spacetable function. Used to space the results per levels of the mentioned variable
infer	A vector of one or two logical values. Passed to summary.emmGrid function.
round	Numeric. Specify the number of digits to round the statistics
x1	deprecated
x2	deprecated
x3	deprecated
x1.name	deprecated
x2.name	deprecated
x3.name	deprecated
data	deprecated
contrast	deprecated
contrast.name	deprecated
type	deprecated
transpose	Logical. If TRUE Statistics will be reported in columns
y.label	Character Indicates the label for y parameter to be displayed in the title of the table

Value

A desc object that can be used by the report.doc function.

Details

You can produce formatted Least Square Means table for up to 3 factors. It doesn't work for quantitative covariates.

See examples below.

See also

report.quali emmeans report.doc desc

Examples

library(emmeans)
library(lme4)

data(datafake)

#Simple lm model

mod=lm(Petal.Width~Species,data=iris)
raw.lsm=emmeans(mod,~Species)
report.lsmeans(raw.lsm)
#> 
#> ############################################
#> LS-Means table of: Petal.Width
#> ############################################
#> 
#>      Statistics      setosa  versicolor   virginica
#> 1 Estimate (SE)  0.25(0.03)  1.33(0.03)  2.03(0.03)
#> 2        95% CI [0.19;0.30] [1.27;1.38] [1.97;2.08]
#> 3       P-value      <0.001      <0.001      <0.001
#> 
#> ############################################
#> 

# You can display the Statistics in columns

report.lsmeans(raw.lsm,transpose=TRUE)
#> 
#> ############################################
#> LS-Means table of: Petal.Width
#> ############################################
#> 
#>      Species Estimate (SE)      95% CI P-value
#> 1     setosa    0.25(0.03) [0.19;0.30]  <0.001
#> 2 versicolor    1.33(0.03) [1.27;1.38]  <0.001
#> 3  virginica    2.03(0.03) [1.97;2.08]  <0.001
#> 
#> ############################################
#> 

# In case of just one intercept 

mod=glm(Species~1,data=iris,family=binomial)
raw.lsm=emmeans(mod,~1)
report.lsmeans(raw.lsm)
#> 
#> ############################################
#> LS-Means table of: Species
#> ############################################
#> 
#>      Statistics           1
#> 1 Estimate (SE)  0.69(0.17)
#> 2        95% CI [0.35;1.03]
#> 3       P-value      <0.001
#> 
#> ############################################
#> 

# Display statistics in columns

report.lsmeans(raw.lsm,transpose=TRUE)
#> 
#> ############################################
#> LS-Means table of: Species
#> ############################################
#> 
#>   1 Estimate (SE)      95% CI P-value
#> 1 1    0.69(0.17) [0.35;1.03]  <0.001
#> 
#> ############################################
#> 


#Mixed model example using lme4

mod=lmer(y_numeric~GROUP+TIMEPOINT+GROUP*TIMEPOINT+(1|SUBJID),data=datafake)
#> boundary (singular) fit: see ?isSingular
raw.lsm=emmeans(mod,~GROUP|TIMEPOINT)
report.lsmeans(lsm=raw.lsm,at="TIMEPOINT")
#> 
#> ############################################
#> LS-Means table of: y_numeric
#> ############################################
#> 
#>    TIMEPOINT    Statistics             A             B             C
#> 1         D0 Estimate (SE)   -0.93(0.20)   -0.67(0.24)   -1.19(0.26)
#> 2         D0        95% CI [-1.32;-0.54] [-1.16;-0.19] [-1.72;-0.66]
#> 3         D0       P-value        <0.001         0.010        <0.001
#> 4                                                                   
#> 5         D1 Estimate (SE)    1.83(0.20)    4.17(0.24)    4.98(0.26)
#> 6         D1        95% CI   [1.44;2.22]   [3.70;4.63]   [4.46;5.50]
#> 7         D1       P-value        <0.001        <0.001        <0.001
#> 8                                                                   
#> 9         D2 Estimate (SE)    1.97(0.20)    4.04(0.24)    4.90(0.26)
#> 10        D2        95% CI   [1.58;2.35]   [3.56;4.52]   [4.38;5.42]
#> 11        D2       P-value        <0.001        <0.001        <0.001
#> 12                                                                  
#> 13        D3 Estimate (SE)    1.78(0.19)    3.81(0.24)    5.07(0.27)
#> 14        D3        95% CI   [1.40;2.16]   [3.33;4.29]   [4.54;5.61]
#> 15        D3       P-value        <0.001        <0.001        <0.001
#> 16                                                                  
#> 17        D4 Estimate (SE)    1.83(0.20)    3.80(0.24)    5.17(0.27)
#> 18        D4        95% CI   [1.44;2.22]   [3.32;4.28]   [4.64;5.71]
#> 19        D4       P-value        <0.001        <0.001        <0.001
#> 20                                                                  
#> 21        D5 Estimate (SE)    2.27(0.19)    3.64(0.24)    4.43(0.26)
#> 22        D5        95% CI   [1.89;2.65]   [3.18;4.11]   [3.91;4.95]
#> 23        D5       P-value        <0.001        <0.001        <0.001
#> 
#> ############################################
#> 

# Display statistics in columns

report.lsmeans(lsm=raw.lsm,at="TIMEPOINT",transpose=TRUE)
#> 
#> ############################################
#> LS-Means table of: y_numeric
#> ############################################
#> 
#>    TIMEPOINT GROUP Estimate (SE)        95% CI P-value
#> 1         D0     A   -0.93(0.20) [-1.32;-0.54]  <0.001
#> 2         D0     B   -0.67(0.24) [-1.16;-0.19]   0.010
#> 3         D0     C   -1.19(0.26) [-1.72;-0.66]  <0.001
#> 4                                                     
#> 5         D1     A    1.83(0.20)   [1.44;2.22]  <0.001
#> 6         D1     B    4.17(0.24)   [3.70;4.63]  <0.001
#> 7         D1     C    4.98(0.26)   [4.46;5.50]  <0.001
#> 8                                                     
#> 9         D2     A    1.97(0.20)   [1.58;2.35]  <0.001
#> 10        D2     B    4.04(0.24)   [3.56;4.52]  <0.001
#> 11        D2     C    4.90(0.26)   [4.38;5.42]  <0.001
#> 12                                                    
#> 13        D3     A    1.78(0.19)   [1.40;2.16]  <0.001
#> 14        D3     B    3.81(0.24)   [3.33;4.29]  <0.001
#> 15        D3     C    5.07(0.27)   [4.54;5.61]  <0.001
#> 16                                                    
#> 17        D4     A    1.83(0.20)   [1.44;2.22]  <0.001
#> 18        D4     B    3.80(0.24)   [3.32;4.28]  <0.001
#> 19        D4     C    5.17(0.27)   [4.64;5.71]  <0.001
#> 20                                                    
#> 21        D5     A    2.27(0.19)   [1.89;2.65]  <0.001
#> 22        D5     B    3.64(0.24)   [3.18;4.11]  <0.001
#> 23        D5     C    4.43(0.26)   [3.91;4.95]  <0.001
#> 
#> ############################################
#> 


# LM model with specific contrast

warp.lm <- lm(breaks ~ wool+tension+wool:tension, data = warpbreaks)
warp.emm <- emmeans(warp.lm, ~ tension | wool)
contr=contrast(warp.emm, "trt.vs.ctrl", ref = "M")
report.lsmeans(lsm=contr,at="wool")
#> 
#> ############################################
#> LS-Means table of: breaks
#> ############################################
#> 
#>   wool    Statistics          L - M          H - M
#> 1    A Estimate (SE)    20.56(5.16)     0.56(5.16)
#> 2    A        95% CI   [8.74;32.37] [-11.26;12.37]
#> 3    A       P-value         <0.001          0.990
#> 4                                                 
#> 5    B Estimate (SE)    -0.56(5.16)   -10.00(5.16)
#> 6    B        95% CI [-12.37;11.26]  [-21.81;1.81]
#> 7    B       P-value          0.990          0.110
#> 
#> ############################################
#> 


# Display statistics in columns

report.lsmeans(lsm=contr,at="wool",transpose=TRUE)
#> 
#> ############################################
#> LS-Means table of: breaks
#> ############################################
#> 
#>   wool contrast Estimate (SE)         95% CI P-value
#> 1    A    L - M   20.56(5.16)   [8.74;32.37]  <0.001
#> 2    A    H - M    0.56(5.16) [-11.26;12.37]   0.990
#> 3                                                   
#> 4    B    L - M   -0.56(5.16) [-12.37;11.26]   0.990
#> 5    B    H - M  -10.00(5.16)  [-21.81;1.81]   0.110
#> 
#> ############################################
#> 


# Cox model

library(survival)

data(time_to_cure)

fit <- coxph(Surv(time, status) ~ Group, data = time_to_cure)
em=emmeans(fit,~Group,type="response")
pairs=pairs(em,adjust="none",exclude="Untreated")
pairs
#>  contrast          ratio    SE df z.ratio p.value
#>  Group A / Group B 0.657 0.251 NA -1.098  0.2723 
#>  Group A / Group C 0.487 0.188 NA -1.866  0.0620 
#>  Group B / Group C 0.740 0.269 NA -0.829  0.4071 
#> 
#> Tests are performed on the log scale 

report.lsmeans(pairs)
#> 
#> ############################################
#> LS-Means comparisons of: time
#> ############################################
#> 
#>      Statistics Group A / Group B Group A / Group C Group B / Group C
#> 1 Estimate (SE)        0.66(0.25)        0.49(0.19)        0.74(0.27)
#> 2        95% CI       [0.31;1.39]       [0.23;1.04]       [0.36;1.51]
#> 3       P-value             0.270             0.060             0.410
#> 
#> ############################################
#> 

# Display statistics in columns

report.lsmeans(pairs,transpose=TRUE)
#> 
#> ############################################
#> LS-Means comparisons of: time
#> ############################################
#> 
#>            contrast Estimate (SE)      95% CI P-value
#> 1 Group A / Group B    0.66(0.25) [0.31;1.39]   0.270
#> 2 Group A / Group C    0.49(0.19) [0.23;1.04]   0.060
#> 3 Group B / Group C    0.74(0.27) [0.36;1.51]   0.410
#> 
#> ############################################
#>