Comparability of results from canonical discriminant analysis based on different input data

Abstract

Introduction. Canonical discriminant analysis, based on the mean values of the traits, is widely used by anthropologists. These analyses use standard deviation means, as well as standard correlation coefficients. The question of the comparability of the results of such analysis with the results based on individual values remains open. Moreover, the existing intergroup variability in correlation coefficients can lead to altered analysis results when applying the correlation matrix calculated for the specific under analysis groups.

This study compares the results of three variants of the canonical discriminant analysis: based on individual data, based on average values and a generalized (species-specific) correlation matrix, and based on average values and a regional (calculated for a certain region) correlation matrix.

Materials and methods. Data from 48 ethno-territorial groups from the Old World were used. The series are dated close to modern times, from the 16th to the 20th century. Twenty-five craniometric linear features have been measured. For canonical analysis on individual data we used the R language package, and for average data analysis the MultiCan software was used.

Results. The results of the two analyses performed on individual data and on average data turned out to be quite similar.

A comparison of the results of a series of discriminant analyses carried out on samples of the three major races using different correlation matrices reveals some small differences in the mutual arrangement of groups. In general, the distribution of samples in the scatter plots, as well as the standardized coefficients of discriminant functions coincide, regardless of the type of initial data.

Conclusion. In general, it may be concluded that the use of both individual values and sample averages in most cases leads to the same results. When individual values are used, the results may be distorted as a result of a strong reduction in the number of samples. Also, sample differentiation in this case is strongly influenced by a higher real intra-group variability. © 2023. This work is licensed under a CC BY 4.0 license.

References

Alekseev V.P. Debec G.F. Kraniometriya. Metodika antropologicheskih issledovanij [Craniometry. Anthropological research methodology]. M.: Nauka, 1964. 128 p. (In Russ.).

Benevolenskaya Yu.D. Gruppovaya izmenchivost' kraniometricheskih korrelyacij [Group variability in craniometric correlations]. In Problemy etnicheskoj antropologii i morfologii cheloveka [Problems of ethnic anthropology and human morphology], 1974, pp. 158—165. (In Russ.).

Bunak V.V. Crania armenica. Issledovaniya po antropologii Perednej Azii [Studies on the anthropology of West Asia]. Moskva, 1927, 314 p. (In Russ.).

Bunak V.V. Korrelyacii priznakov. Proiskhozhdenie i etnicheskaya istoriya russkogo naroda [The correlation of traits. The origin and ethnic history of the Russian people]. Trudy instituta etnografii [Proceedings of the Institute of Ethnography], 1965, 88, pp. 139–151. (In Russ.).

Goncharov I.A., Goncharova N.N. Programma MultiCan dlya analiza mnogomernykh massivov dannykh s ispol'zovaniem statistik vyborok i parametrov general'noi sovokupnosti (MultiCan) [The MultiCan program for the analysis of multidimensional data arrays using statistics of samples and parameters of the general population (MultiCan)]. Svidetel'stvo o registratsii prav na PO №2016610803. Moscow, 2016. (In Russ.).

Debec G.F. K unifikacii kraniologicheskih issledovanij [Towards the unification of craniological research]. Antropologicheskij zhurnal [Journal of Anthropology], 1, 1935, pp. 118–124. (In Russ.).

Debec G.F. Paleoantropologiya drevnih eskimosov (Ipiutak, Tigara) [Paleoanthropology of ancient Eskimos (Ipiutak, Tigara)]. In Etnicheskie svyazi narodov severa Azii i Ameriki po dannym antropologii [Ethnic relations of the peoples of the North of Asia and America]. 1986, pp. 6–149. (In Russ.).

Deryabin V.E. Kurs lekcij po tradicionnoj biometrii dlya antropologov [A course of lectures on traditional biometry for anthropologists]. Moskva, 2007, 331 p. (In Russ.).

Efimova S.G. Paleoantropologiya Povolzh'ya i Priural'ya [Paleoanthropology of the Volga and Ural regions]. Moscow, MGU Publ., 1991. 95 p. (In Russ.).

Ismagulov O. Naselenie Kazakhstana ot ehpokhi bronzy do sovremennosti (paleoantropologicheskoe issledovanie) [The population of Kazakhstan from the Bronze Age to the present (paleoanthropological study).]. Alma-Ata, Nauka Publ., 1970. 241 p. (In Russ.).

Kozincev A.G. O nekotoryh aspektah statisticheskogo analiza v kraniometrii [On some aspects of statistical analysis in craniometry]. Radlovskij sbornik: Nauchnye issledovaniya i muzejnye proekty MAE RAN v 2015 g. [Radloff Collection: Scientific research and museum projects of the MAE RAS in 2015], 2016, pp. 381–390. (In Russ.).

Malinovsky A.A. Elementarnye korrelyacii chelovecheskogo organizma [Elementary correlations of the human body]. Trudy instituta citologii, gistologii i embriologi [Proceedings of the Institute of Cytology, Histology and Embryologists], 1948, 2, pp. 136–198. (In Russ.).

Roginskii Ya.Ya. Velichina izmenchivosti izmeritel'nykh priznakov cherepa i nekotorye zakonomernosti ikh korrelyatsii u cheloveka [The magnitude of the variability of the measuring signs of the skull and some patterns of their correlation in humans]. Uchenye zapiski [Scientific notes], 1954, 166, pp. 68–90. (In Russ.).

Roginskii Ya.Ya. Zakonomernosti svyazei mezhdu priznakami v antropologii [Patterns of relationships between signs in anthropology]. Sovetskaya ehtnografiya [Soviet Ethnography], 1962, 5, pp. 15–29. (In Russ.).

Pezhemskij D. V., Fedorchuk O. A. K probleme korrelyacionnyh vzaimosvyazej obshchih razmerov cherepa cheloveka [To the problem of correlation relationships of the craniometric traits of a human cranium]. Moscow University Anthropology Bulletin Anthropology [Vestnik Moskovskogo universiteta. Seriya 23: Antropologiya], 2020, 2. pp. 126–137. doi: 10.32521/2074-8132.2020.2.126-137

Tihonov A.G. Sravnenie razlichnyh algoritmov kanonicheskogo analiza primenitel'no k antropologicheskim dannym [Comparison of different canonical analysis algorithms as applied to anthropological data]. Vestnik antropologii [Bulletin of Anthropology], 2001, 7. pp. 156–165. (In Russ.).

Shirobokov I.G. O primenenii usrednennoj matricy korrelyacij v kraniometrii [On the application of the averaged correlation matrix in craniometry]. Camera praehistorica [Camera praehistorica] 2021, 1 (6), pp. 141–149. (In Russ.).

Benington R.C., Pearson K. A Study of the Negro Skull with Special Reference to the Congo and Gaboon Crania. Biometrika, 1912, 8 (3/4), pp. 292–339.

G. von Bonin. Beitrag Zur Kraniologie von Ost-Asien. Biometrika, 1931a, 23, (1/2), pp. 52–113.

G. von Bonin. A Contribution to the Craniology of the Easter Islanders. Biometrika, 1931b, 23 (3/4), pp. 249–270.

G. von Bonin. On the Craniology of Oceania. Crania from New Britain. Biometrika, 1936, 28, (1/2), pp. 123–148.

Drontschilow K. Metrische Studien an 93 Schädeln aus Kamerun. Archiv für antropologie, 1913, 12, pp. 161–183.

Friendly M., Fox J. Candisc: Visualizing Generalized Canonical Discriminant and Canonical Correlation Analysis. R package version 0.8-6, 2021 https://CRAN.R-project.org/package=heplots.

Fisher R.A. Frequency distribution of the values of the correlation coefficient in samples of an indefinitely large population. Biometrika, 1915, 10 (4), pp. 507–521. doi:10.2307/2331838

Fisher R.A. On the ’Probable Error’ of a Coefficient of Correlation Deduced from a Small Sample. Metron, 1921, 1, pp. 3–32.

Górny S. Crania africana: Uganda. Cztowiek w Czasie i Przestrzeni: kwartalnik Polskiego. Towarzystwa Antropologicznego, 1957, 1 (1), p. 56.

Hambly W.D. Craniometry of New Guinea. Chicago, 1940, 338 р.

Harrower G.A. Study of the Hokien and Tamil Skull. Biometrika, 1924.

Kitson E.A. Study of the Negro Skull with Special Reference to the Crania from Kenya Colony. Biometrika, 1931, 23 (3), pp. 271–314.

Martin R. Lehrbuch der Anthropologie. 2-te Aufl. Bd. II, 1928.

Morant G.M. A Study of Certain Oriental Series of Crania Including the Nepalese and Tibetan Series in the British Museum (Natural History). Biometrika, 1924, 16 (1/2), pp. 1–10.

Relethford J.H. Apportionment of global human genetic diversity based on craniometrics and skin color. Am. J. Phys. Anthropol., 2002, 118, pp. 393–398.

Sergi S. Crania habessinica: contributo all’antropologia dell’Africa orientale. Loescher. Roma, 1912, 519 р.

Shrubsall F. Crania of African Bush Races. J. Anthropol. Inst. G.B. and Ireland, 1898, 27, pp. 263–292.

Shrubsall F. A Study of A-Bantu Skulls and Crania. J. Anthropol. Inst. G.B. and Ireland, 1899, 28 (1/2), pp. 55–94.

Tildesley M.L. A First Study of the Burmese Skull. Biometrika, 1921, 13 (2/3), pp. 176–262.

Wickham H. ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York, 2016. https://ggplot2.tidyverse.org.

Wicklin R. Fisher's transformation of the correlation coefficient, 2017. Электронный ресурс. URL: https://blogs.sas.com/content/iml/2017/09/20/fishers-transformation-correlation.html (дата обращения 18.11.2022).

Winterbottom A. A Note on the Derivation of Fisher's Transformation of the Correlation Coefficient. The American Statistician, 1979, 33 (3), pp. 142-143, doi: 10.1080/00031305.1979.10482682.