Generalized lambda distribution for flexibly testing differences beyond the mean in the distribution of a dependent variable such as body mass index.
Generalized lambda distribution for flexibly testing differences beyond the mean in the distribution of a dependent variable such as body mass index.
复制标题
DOI:
10.1038/ijo.2017.262
复制
发表时间:
2018-04
期刊:
影响因子:
--
通讯作者:
Allison DB
中科院分区:
文献类型:
--
作者:
Ejima K;Pavela G;Li P;Allison DB
Conventional statistical methods often test for group differences in a single parameter of a distribution, usually the conditional mean (e.g., differences in mean body mass index [BMI; kg/m2] by education category) under specific distributional assumptions. However, parameters other than the mean may of be interest, and the distributional assumptions of conventional statistical methods may be violated in some situations. We describe an application of the generalized lambda distribution (GLD), a flexible distribution that can be used to model continuous outcomes; and simultaneously describe a likelihood ratio test [LRT] for differences in multiple distribution parameters, including measures of central tendency, dispersion, asymmetry, and steepness. We demonstrate the value of our approach by testing for differences in multiple parameters of the BMI distribution by education category using the Health and Retirement Study (HRS) dataset. Our proposed method indicated that at least one parameter of the BMI distribution differed by education category in both the complete dataset (N=13571) (P<0.001) and a randomly resampled dataset (N=300 from each category) to assess the method under circumstances of lesser power (P=0.044). Similar method using normal distribution alternative to GLD indicated the significant difference among the complete dataset (P<0.001) but not in the smaller randomly resampled dataset (P=0.968). Moreover, the proposed method allowed us to specify which parameters of the BMI distribution significantly differed by education category for both the complete and the random subsample, respectively. Our method provides a flexible statistical approach to compare the entire distribution of variables of interest, which can be a supplement to conventional approaches that frequently require unmet assumptions and focus only on a single parameter of distribution.
登录
查看更多内容
影响因子:
3.3
作者:
Ng M;Liu P;Thomson B;Murray CJ
通讯作者:
Murray CJ
DOI:
10.1098/rsta.1933.0009
发表时间:
1933-03-01
影响因子:
--
作者:
Neyman, J
通讯作者:
Neyman, J
影响因子:
2.5
作者:
Jolliffe, Dean
通讯作者:
Jolliffe, Dean
影响因子:
4.5
作者:
Hermann S;Rohrmann S;Linseisen J;May AM;Kunst A;Besson H;Romaguera D;Travier N;Tormo MJ;Molina E;Dorronsoro M;Barricarte A;Rodríguez L;Crowe FL;Khaw KT;Wareham NJ;van Boeckel PG;Bueno-de-Mesquita HB;Overvad K;Jakobsen MU;Tjønneland A;Halkjær J;Agnoli C;Mattiello A;Tumino R;Masala G;Vineis P;Naska A;Orfanos P;Trichopoulou A;Kaaks R;Bergmann MM;Steffen A;Van Guelpen B;Johansson I;Borgquist S;Manjer J;Braaten T;Fagherazzi G;Clavel-Chapelon F;Mouw T;Norat T;Riboli E;Rinaldi S;Slimani N;Peeters PH
通讯作者:
Peeters PH
影响因子:
6.9
作者:
Beyerlein, Andreas;Toschke, Andre M.;von Kries, Ruediger
通讯作者:
von Kries, Ruediger