Matskási István (szerk.): A Magyar Természettudományi Múzeum évkönyve 94. (Budapest 2002)

Radoinova, D., Tenekedjiev, K. ; Yordanov, Y.: Stature estimation according to bone length in Hungarian population

The correlation coefficient between the regression parameters is -0.997. The estimated standard error is 1.19 cm within a 0.97 cm to 1.52 cm 95% confidence interval. R 1 - 0.946. The 95% confidence intervals of the model coefficients are respectively: from 88.87 cm to 99.57 cm and from 1.821 cm to 2.124 cm. The regression parameters are significant (t-tests with P-value'

s < 0.0005) and the model (3) is adequate (ANOVA with P-value < 0.0005). The three formulae (of TROTTER-GLESER, DUPERTUIS-HADDEN and BACH) did not describe adequately the sample (P-value = 0.000%). The nomogram on tibia for Hungarian females is shown on Fig. 3. 1.4. Maximal stature regression together for humerus and tibia - One outlier is rejected in the first loop (n = 83-1 = 82). A model of the maximal stature is built. Heteroskedasticity is not rejected only by one test (GOLDFELD-QUANDT). The other ten tests detect heteroskedasticity (P-value < 0.0058). Only the squared model of the residuals' module is acceptable and accepted: (4) e(H,T) = E[ I residuall ] = = 29.4- 2.164*H+ 0.4297*T+ 0.5374*H

2- 0.9505*HT+ 0.4409*T

2 (10.9) (2.0) (1.78) (0.14) (0.25) (0.11) Fig. 3. Nomogram for predicting the maximal stature of Hungarian females using the length of tibia with age correction according to GILES and BORCAN (bold line). Three confidence margins are plotted (95%- solid line, 99% dashed line and 99.9% dashdotted). The outliers are plotted with circles, and the experimental data is shown with dots