在Cramer's V中处理应变表中的零

Question

我正在关注在assocstats调用数据框的多个子集时调用xtable的vcd文档。但是，我得到了具有特定子集的NaN，因为许多情况的预期观察值为0：

        factor.2
factor.1  0  1  2  3  4 5 or more
      0   0 12  7  1  0         1
      1   0  2  1  1  0         0
      2   0  8  2  1  0         0
      3   0  5  4  0  0         0
      4   0  1  2  2  0         0
      5   0  6  8  0  0         0
      6   0  5  3  0  0         0
      7   0  5  1  0  0         0
      8   0  5  4  0  1         0
      9   0  1  1  0  1         0
      10  0  5  6  0  0         1

temp.table <- structure(c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 12L, 
2L, 8L, 5L, 1L, 6L, 5L, 5L, 5L, 1L, 5L, 7L, 1L, 2L, 4L, 2L, 8L, 
3L, 1L, 4L, 1L, 6L, 1L, 1L, 1L, 0L, 2L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 1L), .Dim = c(11L, 6L), .Dimnames = structure(list(
    factor.1 = c("0", "1", "2", "3", "4", "5", "6", "7", "8", 
    "9", "10"), factor.2 = c("0", "1", "2", "3", "4", "5 or more"
    )), .Names = c("factor.1", "factor.2")), class = c("xtabs", 
"table"), call = xtabs(data = cases.limited, na.action = na.omit))

library(vcd)

assocstats(temp.table)

                    X^2 df P(> X^2)
Likelihood Ratio 35.004 50  0.94676
Pearson             NaN 50      NaN

Phi-Coefficient   : NA 
Contingency Coeff.: NaN 
Cramer's V        : NaN

有没有办法快速有效地避免在分析中包含这些案例，而不会对assocstats或xtable的某些内容进行大量重写？我知道可以说统计能力较低，但Cramer的V已经是一个乐观的估算器，所以结果对我来说仍然有用。