Table 1 Descriptive statistics of the variables (N = 182)

From: Applying machine learning to analyse the layouts of Qing Dynasty forestland agreements in Fujian

Variables

Description

Mean

Range

Dependent variables

LR(A*-S)

Continuous variable, the margin ratio is defined as the distance from the margin S of content A to the corresponding margin of the agreement, divided by the length of the opposite margin of the agreement. Margin S can be categorised as upper (U), lower (D), left (L), or right (R).

0.463

0.173–0.930

AR(A*)

Continuous variable, the area ratio of content A to the total area of the agreement.

0.076

0.005–0.528

ARQ(A*-Q)

Continuous variable, the quadrant area ratio of content A to the area of the corresponding quadrant on the paper, where the quadrants are divided into I, II, III, and IV. Thus, the character “Q” in the variable can be replaced with the symbols I, II, III, and IV.

0.119

0.000–1.000

Independent variables

SEL

Dummy variable, 1 for the forestland with the selling agreement, 0 for additional agreement.

0.873

0–1

CLA

Categorical variable, agreements signed by different clans are coded as follows: 1 for Ke, 2 for Zhan, 3 for Zheng, 4 for Zhang, 5 for Lin, 6 for Xie, 7 for Chen, 8 for Su, 9 for Yang, 10 for Huang, 12 for Xiao, 13 for Ye, 14 for You and 15 for Ling.

6.203

0–15

REI

Ordinal variable, 1 for agreements signed during the Qianlong reign, 2 for the Jiaqing reign, 3 for the Daoguang reign, and 4 for the Guangxu reign.

2.610

1–4

YEA

Ordinal variable representing the specific year within the reigns of different Qing Dynasty emperors, with the minimum value set to 1, indicating the first year of an emperor's accession.

21.379

0–58

STO

Categorical variable, 1 for Nanshan (Xiaoyang) village, 2 for the agreement stored in Zhufeng village, 3 for Duitou village, and 4 for Gaifeng village.

1.198

0–2

  1. *The specific types of content “A” are presented in Table 2, including Text (T), Date (D), Signatures (S), and Blessings (B). Therefore, the character “A” in the variable can be replaced with T, D, S, and B, respectively.
  2. Definitions of variables involved in the study and statistical descriptions of their data.