Lilliefors Distribution

Lilliefors distribution approximation

The following polynomial function provides an approximation, accurate to about two decimals places, for the Lilliefors distribution.

Lilliefors distribution

where image9195

image9196

image9197

image9198

Worksheet Functions

Real Statistics Functions: The following functions are provided in the Real Statistics Resource Pack to implement the approximation of the Lilliefors distribution:

LDIST(x, n) = the p-value of the Lilliefors distribution at x for samples of size n

LINV(p, n, iter) = the critical value of the Lilliefors distribution at p for samples of size n; i.e. LINV(p, n, iter) = x where LDIST(x, n) = p, based on iter iterations (default 40)

For Example 2 of Kolmogorov Test for Normality, p-value = LDIST(0.184, 15) = .180996, which is similar to the estimate from LPROB(0.184, 15) = .182858. Similarly, Dn,α = LINV(.05, 15) = .218698 is similar to the estimate from LCRIT(15, .05, 2) = .2196.

LTEST function

The following function is provided in the Real Statistics Resource Pack to calculate the value of the Kolmogorov-Smirnov statistic Dn

LTEST(R1) = Dn for the data in range R1

For Example 2 of Kolmogorov Test for Normality, referring to Figure 4 of Kolmogorov Test for Normality, LTEST(B4:B18) = .184117 (same as cell H20).

In fact, LTEST can be used as an array function which outputs a 2 × 1 column range containing and p-value (based on the LDIST approximation). The array function LTEST takes an optional second argument lab (default FALSE). When lab = TRUE then a column of labels is appended to the output.

Thus, referring to the input range in Figure 4 of Kolmogorov Test for Normality, the output from LTEST(B4:B18,TRUE) is as shown in Figure 1.

Lilliefors Test

Figure 1 – Lilliefors Test

Examples Workbook

Click here to download the Excel workbook with the examples described on this webpage.

Reference

Lilliefors, H. W. (1967) On the Kolmogorov-Smirnov Test for Normality with Mean and Variance Unknown, Journal of the American Statistical Association, Vol. 62, No. 318, pp. 399-402.
https://pdfs.semanticscholar.org/4aad/1756e88dba86399a75891895e00b160f5460.pdf

Leave a Comment