Nonparametric models and methods for designs with dependent censored data: part I.

We consider a nonparametric (NP) approach to the analysis of repeated measures designs with censored data. Using the NP model of Akritas and Arnold (1994, Journal of the American Statistical Association 89, 336-343) for marginal distributions, we present test procedures for the NP hypotheses of no main effects, no interaction, and no simple effects. This extends the existing NP methodology for such designs (Wei and Lachin, 1984, Journal of the American Statistical Association 79, 653-661). The procedures do not require any modeling assumptions and should be useful in cases where the assumptions of proportional hazards or location shift fail to be satisfied. The large-sample distribution of the test statistics is based on an i.i.d. representation for Kaplan-Meier integrals. The testing procedures apply also to ordinal data and to data with ties. Useful small-sample approximations are presented, and their performance is examined in a simulation study. Finally, the methodology is illustrated with two real life examples, one with censored and one with missing data. It is indicated that one of the data sets does not conform to any set of assumptions underlying the available methods and also that the present method provides a useful additional analysis even when data sets conform to modeling assumptions.

Neuropathic gait shows only trends towards increased variability of sagittal plane kinematics during treadmill locomotion.

Patients with diabetes mellitus (DM) and peripheral neuropathy (PN) are at greater risk of falling and of suffering injuries during falls. It has been hypothesized that PN leads to changes in gait variability that may account for this increased risk. The purpose of this investigation was to analyze the variability of the sagittal plane kinematics of diabetic neuropathic (NP), diabetic non-neuropathic (NNP) and age- and weight-matched control subjects (Control) during motorized treadmill walking at constant speed. While there were distinct trends towards increased variability within the three diagnostic groups (NP > NNP > Control) for several measures of gait variability, most of these trends were not statistically significant. We hypothesize that motorized treadmill walking may be inherently less variable than overground walking and that statistical measures of variability may not be sufficient to fully characterize stride-to-stride variability in human locomotion.

Chronic hormone replacement therapy alters thermoregulatory and vasomotor function in postmenopausal women.

This investigation examined effects of chronic (>/=2 yr) hormone replacement therapy (HRT), both estrogen replacement therapy (ERT) and estrogen plus progesterone therapy (E+P), on core temperature and skin blood flow responses of postmenopausal women. Twenty-five postmenopausal women [9 not on HRT (NO), 8 on ERT, 8 on E+P] exercised on a cycle ergometer for 1 h at an ambient temperature of 36 degrees C. Cutaneous vascular conductance (CVC) was monitored by laser-Doppler flowmetry, and forearm vascular conductance (FVC) was measured by using venous occlusion plethysmography. Iontophoresis of bretylium tosylate was performed before exercise to block local vasoconstrictor (VC) activity at one skin site on the forearm. Rectal temperature (Tre) was approximately 0.5 degrees C lower for the ERT group (P < 0.01) compared with E+P and NO groups at rest and throughout exercise. FVC: mean body temperature (Tb) and CVC: Tb curves were shifted approximately 0.5 degrees C leftward for the ERT group (P < 0.0001). Baseline CVC was significantly higher in the ERT group (P < 0.05), but there was no interaction between bretylium treatment and groups once exercise was initiated. These results suggest that 1) chronic ERT likely acts centrally to decrease Tre, 2) ERT lowers the Tre at which heat-loss effector mechanisms are initiated, primarily by actions on active cutaneous vasodilation, and 3) addition of exogenous progestins in HRT effectively blocks these effects.