Basic statistics Comparison with Kelenderis staters

Coin catalogue section:	Holmoi
Coin corpus datasets:	Holmoi, Group 1, Holmoi, Group 2

Basic statistics

Box plots1 and basic descriptive statistics are presented in Figure 1 and Table 1, respectively. In Group 1, the coin no. 2 (Type 1.1b) is distinguished from other coins by its very low weight of 10.02 g. According to the photograph in the auction catalogue, it appears to be well preserved and without signs of metal degradation. From Group 2, coin no. 1 (Type 2.1a) was excluded from the analysis because its low weight of 8.67 g seems to be significantly affected by corrosion.

Figure 1: Box plots

Statistics	Group 1	Group 2
Number of coins:	9	6
Mean:	10.55	10.04
Standard deviation:	0.22	0.14
Interquartile range:	0.18	0.16
Skewness:	-1.76	-0.13
Kurtosis:	5.01	1.88
Minimum:	10.02	9.84
25th percentile:	10.49	9.96
Median:	10.66	10.04
75th percentile:	10.66	10.12
Maximum:	10.74	10.22

Table 1: Descriptive statistics of coin groups

Figure 2 presents the relative frequency histograms. The bars represent the relative frequencies in both groups ranging from 9.80 to 10.80 g in increments of 0.10 g. Cumulative distributions are shown in Fig. 3.

Figure 2: Relative frequency histograms

Figure 3: Cumulative distributions

Comparison with Kelenderis staters

Kelenderis staters are divided into Groups 1, 2 and 3 (see page Coin Catalogue / Kelenderis / Overview), with Group 3 being divided into the following into the following three subgroups (see page Weight Analyses / Kelenderis, staters):

Group 3A:	Types 3.1–3 and 3.7–12, i.e. coins of Group 3 except Types 3.4–6 and 3.13–17;
Group 3B:	Types 3.13–14;
Group 3C:	Types 3.4–6 and 3.15–17.

A comparison of both types of Holmoi staters with individual groups of Kelenderis staters is shown in Figure 4. Holmoi Group 1 roughly corresponds to Kelenderis Group 3A, suggesting that these coins may have been minted around the same time period.2 Holmoi Group 2 shows a slightly higher weight standard than Kelenderis Group 3C, but the differences may be due to the lower number of observations.3 Thus, the production of both groups may again fall within approximately the same time period. Both these observations are confirmed by Figures 5 and 6, which present the relative frequency histograms and cumulative distributions.

Figure 4: Holmoi vs Kelenderis staters, box plots

Figure 5: Holmoi vs Kelenderis staters, relative frequency histograms

Figure 6: Holmoi vs Kelenderis staters, cumulative distributions