regularized regression models because they work well for “wide” data sets (ie, few observations, many predictors), eliminate irrelevant variables, and improve prediction accuracy. 32 These models also automatically perform variable selection, such that their outputs are also easy to interpret and provide
John R. Harry, John Krzyszkowski, Luke D. Chowning, and Kristof Kipp
Hyunjae Jeon, Melanie L. McGrath, Neal Grandgenett, and Adam B. Rosen
each questionnaire were used to identify factors that contribute the most to pain and dysfunction associated with PT. This was completed using a backward selection, linear regression to determine the most parsimonious, multifactorial model to predict each of the pain and function scales. Models were
Jessa M. Buchman-Pearle and Stacey M. Acker
the accuracy in which global (ie, whole body) and local (ie, thigh) measures of participant anthropometry could predict soft tissue artifact for marker clusters localized to different areas of the thigh in high knee flexion. Backward stepwise linear regressions were performed between measures of
Jeffrey J. VanWormer, Jennifer A. Linde, Lisa J. Harnack, Steven D. Stovitz, and Robert W. Jeffery
Some evidence suggests that physical activity programs mainly attract employees who are already active. This study examined the degree to which baseline physical activity was associated with enrollment in worksite walking clubs.
All variables were measured at baseline. Walking club participation was measured over 2 years. There were 642 individuals from 3 worksites with complete data available for logistic regression analyses.
Baseline physical activity [OR (95% CI) = 1.00 (0.99, 1.01)] was not a significant predictor of walking club participation. Participants who were older [OR = 1.03 (1.01, 1.04)] or indicated more social support for physical activity [OR = 1.13 (1.02, 1.25)] had significantly higher odds of participation relative to those who were younger or indicated less social support, respectively. In addition, men [OR = –0.25 (0.18, 0.36)] and employees from the second worksite [OR = –0.41 (0.25, 0.67)] had significantly lower odds of participation relative to women and employees from the first or third worksites, respectively. Sensitivity analyses arrived at similar conclusions.
Worksite walking clubs were appealing across varying levels of physical activity. Future research should improve marketing and program design to engage harder-to-reach segments of the workforce, particularly young men and those with limited social support.
Christopher M. Saliba, Allison L. Clouthier, Scott C.E. Brandon, Michael J. Rainbow, and Kevin J. Deluzio
not necessarily result in a decrease in the medial contact force, likely due to a corresponding increase in the knee flexion moment. 12 , 13 Without in vivo data from instrumented knee replacements, feedback of the medial contact force relies on model estimates. Regression models have been used to
Adam Karg, Jeremy Nguyen, and Heath McDonald
) presents a logical extension but requires a sample larger than one season. Finally, while the most common approach to analysis in demand studies have been regression based, other analysis techniques are evident in other attendance studies (e.g., random forest, artificial neural networks, adaptive
Francisco Luis Pestaña-Melero, G. Gregory Haff, Francisco Javier Rojas, Alejandro Pérez-Castilla, and Amador García-Ramos
be compromised in free-weight exercises. 7 , 14 The load–velocity relationship has been used to predict 1RM with both linear 6 , 7 , 13 and polynomial regression models. 10 , 15 However, to the authors knowledge, no study has determined which of these 2 regression models provides the most reliable
In modern societies there is strong belief in scientific progress, but, unfortunately, a parallel partial regress occurs because of often avoidable mistakes. Mistakes are mainly forgetting, erroneous theories, errors in experiments and manuscripts, prejudice, selected publication of “positive” results, and fraud. An example of forgetting is that methods introduced decades ago are used without knowing the underlying theories: Basic articles are no longer read or cited. This omission may cause incorrect interpretation of results. For instance, false use of actual base excess instead of standard base excess for calculation of the number of hydrogen ions leaving the muscles raised the idea that an unknown fixed acid is produced in addition to lactic acid during exercise. An erroneous theory led to the conclusion that lactate is not the anion of a strong acid but a buffer. Mistakes occur after incorrect application of a method, after exclusion of unwelcome values, during evaluation of measurements by false calculations, or during preparation of manuscripts. Co-authors, as well as reviewers, do not always carefully read papers before publication. Peer reviewers might be biased against a hypothesis or an author. A general problem is selected publication of positive results. An example of fraud in sports medicine is the presence of doped subjects in groups of investigated athletes. To reduce regress, it is important that investigators search both original and recent articles on a topic and conscientiously examine the data. All co-authors and reviewers should read the text thoroughly and inspect all tables and figures in a manuscript.
Kinda A. Khalaf, Mohamad Parnianpour, and Tasos Karakostas
The majority of existing normative torque generation capability (torque capability for short) databases are reported in the form of torque as a function of joint angle. although it is well recognized that torque capability is a function of both the joint angular position and angular velocity. The main objective of this study was to develop the methodology of 3-D dynamic representation of torque capability using the ankle joint as an example. The ankle torque capability of 20 males and females was assessed at 5 levels of ankle joint angular positions and velocities in each direction of plantar and dorsi flexion. The ANOVA results indicated significant main effects of joint angular position, angular velocity, direction, and gender, in addition to the interaction effect of angular position and velocity (p < .003) on the torque capability of the ankle joint. The regression analysis indicated that an individualized quadratic surface response performed significantly belter than the models developed for each gender or the whole population using the coefficient of determination and standard error of the regression as criteria. Such 3-D representation of torque capability has a broad spectrum of applications ranging from rehabilitation and ergonomic to biomechanical applications.
Robert Glenn Weaver, Rafael M. Tassitano, Maria Cecília M. Tenório, Keith Brazendale, and Michael W. Beets
regression. To account for the fact that effects were nested within study, the robumeta command was used to estimate robust SEs. 54 All models included MVPA as the dependent variable and year as the independent variable. Where appropriate, squared or root terms were included for time. All models included