PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 8732911

Sample sizes for experiments with multivariate repeated measures.

X Guo·W D Johnson
View original source ↗Export metadata ↓

Abstract

Procedures for determining sample size in multivariate repeated measures experiments are discussed. The focus is on designs with either one group or two independent groups of subjects, the point of departure being multivariate repeated measures. Determination of the minimum sample size required is based on power considerations associated with Hotelling's T2 and the F-test. We first consider procedures for determining sample size assuming an arbitrary covariance matrix. The special case where we assume that the transformed data have a multivariate spherical covariance matrix is also considered. Tables of the minimum sample sizes required for several hypotheses from multivariate analysis are presented.

Explore related subjects

Mathematical ComputingMultivariate AnalysisStatistics as TopicJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

X Guo, W D Johnson. 1996. Sample sizes for experiments with multivariate repeated measures.. https://doi.org/10.1080/10543409608835130

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2000

Heteronuclear diatomic force constants clarified through perturbation theory II.

A simple relationship between the heteronuclear diatomic force constant (K(AB)) and the homonuclear diatomic force constants (K(AA), K(BB)), which was proposed in a previous report, has been improved through the second-order perturbation theory as K(AB) = zeta3(K(AA) x K(BB))(1/2); zeta = (R(AA) x R(BB))(1/2)/R(AB) where zeta denotes the correction factor in which R(AB), R(AA), and R(BB) are the equilibrium internuclear distances of diatomic molecules AB, AA, and BB, respectively. To test the above expression, a large number of heteronuclear diatomic force constants have been calculated and compared with those obtained from normal coordinate analyses as well as ab initio quantum mechanical methods (Gaussian 98W). We have found that the above modified expression better reproduces the force constants of most heteronuclear diatomic molecules than the previous expression. It is therefore expected that the expression may also be applied to the prediction of stretching force constants between heteronuclear diatomics in various polyatomic molecules.

Mathematical Computing↗
PubMed1999

Calculation of NMR relaxation, covolume, and scattering-related properties of bead models using the SOLPRO computer program.

The hydrodynamic properties of macromolecules and bioparticles, represented by bead models, can be calculated using methods implemented in the computer routine HYDRO. Recently, a new computer routine, SOLPRO, has been presented for the calculation of various SOLution PROperties. These include (1) time-dependent electro-optic and spectroscopic properties related to rotational diffusion, (2) non-dynamic properties like scattering curves, and (3) dimensionless quantities that combine two or more solution properties in a form which depends on the shape of the macromolecule but not on its size. In the present work we describe the inclusion of more of those types of properties in a new version of SOLPRO. Particularly, we describe the calculation of relaxation rates in nuclear magnetic resonance (NMR). For dipolar coupling, given the direction of the dipole the program calculates values of the spectral density, from which the NMR relaxation times can be obtained. We also consider scattering-related properties, namely the distribution of distances for the bead model, which is directly related to the angular dependence of scattered intensity, and the particle's longest distance. We have devised and programmed a procedure to calculate the covolume of the bead model, related to the second virial coefficient and, in general, to the concentration dependence of solution properties. Various shape-dependent dimensionless quantities involving the covolume are calculated. In this paper we also discuss some aspects, namely bead overlapping and hydration, that are not explicitly included in SOLPRO, but should be considered by the user.

Mathematical Computing↗
PubMed1998

Analysis of domain motions by approximate normal mode calculations.

The identification of dynamical domains in proteins and the description of the low-frequency domain motions are one of the important applications of numerical simulation techniques. The application of these techniques to large proteins requires a substantial computational effort and therefore cannot be performed routinely, if at all. This article shows how physically motivated approximations permit the calculation of low-frequency normal modes in a few minutes on standard desktop computers. The technique is based on the observation that the low-frequency modes, which describe domain motions, are independent of force field details and can be obtained with simplified mechanical models. These models also provide a useful measure for rigidity in proteins, allowing the identification of quasi-rigid domains. The methods are validated by application to three well-studied proteins, crambin, lysozyme, and ATCase. In addition to being useful techniques for studying domain motions, the success of the approximations provides new insight into the relevance of normal mode calculations and the nature of the potential energy surface of proteins.

Mathematical Computing↗