Statistics of data grouped by factors

Source: R/tapply.stat.R

This process lies in finding statistics which consist of more than one variable, grouped or crossed by factors. The table must be organized by columns between variables and factors.

tapply.stat(y, x, stat = "mean")

Arguments

y

data.frame variables
x

data.frame factors
stat

Method

Value

Statistics of quantitative variables by categorical variables.

Examples


library(agricolae)
# case of 1 single factor
data(sweetpotato)
tapply.stat(sweetpotato[,2],sweetpotato[,1],mean)
#>   sweetpotato[, 1] sweetpotato[, 2]
#> 1               cc         24.40000
#> 2               fc         12.86667
#> 3               ff         36.33333
#> 4               oo         36.90000
with(sweetpotato,tapply.stat(yield,virus,sd))
#>   virus    yield
#> 1    cc 3.609709
#> 2    fc 2.159475
#> 3    ff 7.333030
#> 4    oo 4.300000
with(sweetpotato,tapply.stat(yield,virus,function(x) max(x)-min(x)))
#>   virus yield
#> 1    cc   6.8
#> 2    fc   4.3
#> 3    ff  13.8
#> 4    oo   8.3
with(sweetpotato,tapply.stat(yield,virus,
function(x) quantile(x,0.75,6)-quantile(x,0.25,6)))
#>   virus yield
#> 1    cc  3.40
#> 2    fc  2.15
#> 3    ff  6.90
#> 4    oo  4.15
# other case
data(cotton)
with(cotton,tapply.stat(yield,cotton[,c(1,3,4)],mean))
#>     site lineage epoca     yield
#> 1   Lima       1     1 12.500000
#> 2   Lima       1     2 18.666667
#> 3   Lima       2     1 12.333333
#> 4   Lima       2     2 17.333333
#> 5   Lima       3     1 11.000000
#> 6   Lima       3     2 13.333333
#> 7   Lima       4     1  8.833333
#> 8   Lima       4     2 11.500000
#> 9  Pisco       1     1 14.833333
#> 10 Pisco       1     2 20.166667
#> 11 Pisco       2     1 17.000000
#> 12 Pisco       2     2 21.166667
#> 13 Pisco       3     1 15.833333
#> 14 Pisco       3     2 21.166667
#> 15 Pisco       4     1 14.666667
#> 16 Pisco       4     2 20.000000
with(cotton,tapply.stat(yield,cotton[,c(1,4)],max))
#>    site epoca yield
#> 1  Lima     1    15
#> 2  Lima     2    26
#> 3 Pisco     1    26
#> 4 Pisco     2    27
# Height of pijuayo
data(growth)
with(growth,tapply.stat(height, growth[,2:1], function(x) mean(x,na.rm=TRUE)))
#>    slime place    height
#> 1      5    L1  8.433333
#> 2      6    L1 10.950000
#> 3      6    L2 11.350000
#> 4      7    L1  9.375000
#> 5      7    L2 12.000000
#> 6      9    L1 10.500000
#> 7      9    L2 12.400000
#> 8     10    L1 12.200000
#> 9     10    L2 10.600000
#> 10    11    L2 11.433333
#> 11    12    L2 12.500000
#> 12    13    L2 11.500000
#> 13    14    L2 11.500000
#> 14    15    L2 11.900000
#> 15    17    L1 11.233333
#> 16    18    L1 10.100000