Search

Modeling correlated or highly stratified multiple-response data is a common data analysis task in many applications, such as those in large epidemiological studies or multisite cohort studies. The generalized estimating equations method is a popular statistical method used to analyze these kinds of data, because it can manage many types of unmeasured dependence among outcomes. Collecting large amounts of highly stratified or correlated response data is time-consuming; thus, the use of a more aggressive sampling strategy that can accelerate this process-such as the active-learning methods found in the machine-learning literature-will always be beneficial. In this study, we integrate adaptive sampling and variable selection features into a sequential procedure for modeling correlated response data. Besides reporting the statistical properties of the proposed procedure, we also use both synthesized and real data sets to demonstrate the usefulness of our method., (© 2019 The International Biometric Society.)

In this paper, a sequential multiplicative extended Kalman filter (SMEKF) is proposed for attitude estimation using vector observations. In the proposed SMEKF, each of the vector observations is processed sequentially to update the attitude, which can make the measurement model linearization more accurate for the next vector observation. This is the main difference to Murrell’s variation of the MEKF, which does not update the attitude estimate during the sequential procedure. Meanwhile, the covariance is updated after all the vector observations have been processed, which is used to account for the special characteristics of the reset operation necessary for the attitude update. This is the main difference to the traditional sequential EKF, which updates the state covariance at each step of the sequential procedure. The numerical simulation study demonstrates that the proposed SMEKF has more consistent and accurate performance in a wide range of initial estimate errors compared to the MEKF and its traditional sequential forms.

This study aimed (1) to profile the plantar loading characteristics when performing the basketball lay-up in a realistic setting and (2) to determine the number of trials necessary to establish a stable mean for plantar loading variables during the lay-up. Thirteen university male basketball players [age: 23.0 (1.4) years, height: 1.75 (0.05) m, mass: 68.4 (8.6) kg] performed ten successful basketball lay-ups from a stationary position. Plantar loading variables were recorded using the Novel Pedar-X in-shoe system. Loading variables including peak force, peak pressure, and pressure-time integral were extracted from eight foot regions. Performance stability of plantar loading variables during the take-off and landing steps were assessed using the sequential averaging technique and intra-class correlation coefficient (ICC). High plantar loadings were experienced at the heel during the take-off steps, and both the heel and forefoot regions upon landing. The sequential estimation technique revealed a five-eight trial range to achieve a stable mean across all plantar loading variables, whereas ICC analysis was insensitive to inter-trial differences of repeated lay-up performances. Future studies and performance evaluation protocols on plantar loading during basketball lay-ups should include at least eight trials to ensure that the measurements obtained are sufficiently stable.