Comparative Performance of Four Single Extreme Outlier Discordancy Tests from Monte Carlo Simulations

Figure 2

Determination of optimum simulation replication (𝑀) for Power of Test (Ω) as a function of replications for all tests N2, N8, N14, and N15; symbols are explained in each figure. (a) Sample size 𝑛=5 and contaminant parameter 𝛿=10; (b) 𝑛=5 and 𝛿=20; (c) 𝑛=15 and 𝛿=5; and (d) 𝑛=15 and 𝛿=10.

(a) 𝑛=5 and  𝛿=10

(b) 𝑛=5 and  𝛿=20

(c) 𝑛=15 and  𝛿=5

(d) 𝑛=15 and  𝛿=10