A Convolution Estimator for the Density of Nonlinear Regression Observations

Abstract. The problem of estimating an unknown density function has been widely studied. In this article, we present a convolution estimator for the density of the responses in a nonlinear heterogenous regression model. The rate of convergence for the mean square error of the convolution estimator is of order n ^?1 under certain regularity conditions. This is faster than the rate for the kernel density method. We derive explicit expressions for the asymptotic variance and the bias of the new estimator, and further a data‐driven bandwidth selector is proposed. We conduct simulation experiments to check the finite sample properties, and the convolution estimator performs substantially better than the kernel density estimator for well‐behaved noise densities.     

Comparison of heart-rate and blood-pressure increases during isokinetic eccentric versus isometric exercise in older adults

The authors compared heart-rate and blood-pressure responses to typical isometric (ISO) and isokinetic (90 degrees /s) eccentric (ECC) resistance-training protocols in older adults. Twenty healthy older adults (74 +/- 5 years old) performed randomly ordered ISO and isokinetic ECC exercise (3 sets of 10 repetitions) at a target intensity of 100 % of their peak ISO torque value. Heart rate and systolic (SBP) and diastolic (DBP) blood pressures were recorded continuously, and mean arterial pressure (MAP) and rate-pressure product (RPP) were calculated. ECC peak torque (139 +/- 33 N. m) was significantly greater than ISO peak torque (115 +/- 26 N. m; p <.001). All variables increased significantly (p <.001) during both ISO and ECC exercise. Changes in SBP, DBP, MAP, and RPP were significantly greater during ISO exercise than during ECC exercise (p <.001). Clinically, an isokinetic ECC exercise program enables older adults to work at the same torque output with less cardiovascular stress than ISO exercise.     

Reliability of isokinetic and isometric knee-extensor force in older women

Because of the need for efficient, consistent strength measurements, the test-retest reliability of concentric, isometric, and eccentric strength; concentric work; and concentric power was determined in older women without a familiarization session. The reliability of measures derived from a single peak score were compared with those derived from an averaged score. On 2 occasions 25 older women with a mean age of 72 +/- 6 years performed 3 submaximal knee extensions and 5 maximal contractions on an isokinetic dynamometer at 90 degrees/s (CON), 0 degrees/s, and -90 degrees/s on both lower limbs. Statistical analyses for peak and averaged values (best 3 contractions of 5) exhibited good relative reliability (ICCs > .88), except for CON power. Typical error as a coefficient of variation and ratio limits of agreement for peak and averaged score values were larger than desired, with CON power scores demonstrating unacceptable error ranges. Although relative reliability of this 1-session assessment protocol was acceptable, further research is needed to determine whether additional practice trials could enhance absolute reliability.     

A critical survey on the status of multiple criteria decision making theory and practice

This paper seeks to review and to contrast the main streams of thought in Multiple Criteria Decision Making (MCDM) theory and practice, without attempting to review all MCDM methods in detail. The main purpose is to identify pitfalls in the usage of various approaches, and to suggest approaches which are most robustly and effectively useable, especially by the non-expert in MCDM methodology. Problem areas in MCDM still requiring further research are also discussed.     

Reliability and validity of responses to submaximal all-extremity semirecumbent exercise in older adults

Although popular in clinical settings, little is known about the utility of all-extremity semirecumbent exercise machines for research. Twenty-one community-dwelling older adults performed two exercise trials (three 4-min stages at increasing workloads) to evaluate the reliability and validity of exercise responses to submaximal all-extremity semirecumbent exercise (BioStep). Exercise responses were measured directly (Cosmed K4b2) and indirectly through software on the BioStep. Test-retest reliability (ICC2,1) was moderate to high across all three stages for directly measured METs (.92, .87, and .88) and HR (.91, .83, and .86). Concurrent criterion validity between the K4b2 and BioStep MET values was moderate to very good across the three stages on both Day 1 (r = .86, .71, and .83) and Day 2 (r = .73, .87, and .72). All-extremity semirecumbent submaximal exercise elicited reliable and valid responses in our sample of older adults and thus can be considered a viable exercise mode.