Variable selection with unbiased estimation: the CDF penalty

We propose a new SCAD-type penalty in general regression models. The new penalty can be considered a competitor of the LASSO, SCAD or MCP penalties, as it guarantees sparse variable selection, i.e., null regression coefficient estimates, while attenuating bias for the non-null estimates. In this work, the method is discussed, and some comparisons are presented.

Rehabilitative interventions for ischaemic digital ulcers, pain, and hand functioning in systemic sclerosis: a prospective before-after study

Abstract Background Systemic sclerosis (SSc) is a rare connective tissue disease characterised by immune dysfunction, vasculopathy, cellular inflammation, fibrosis of the skin associated with multiple internal organs involvement. Ischaemic digital ulcers (IDU) of the hands commonly occur in patients with SSc adversely affecting functional independence. Purpose Aim of the study is to investigate the effectiveness of a rehabilitation protocol based on the combined use of ultrasound (US) therapy and therapeutic exercise in terms of ulcers healing, pain relief, and hand functioning in patients affected by SSc with IDUs. Moreover, we also investigated the safety of the proposed intervention. Stu…

Adaptive P-splines via L1-type penalty in generalized additive models

Early Denosumab for the prevention of osteoporotic fractures in breast cancer women undergoing aromatase inhibitors: A case-control retrospective study

BACKGROUND: Aromatase inhibitors (AIs) might have a detrimental impact on bone health in breast cancer (BC) women. Denosumab has been shown to reduce the risk of fractures, but the appropriate time for starting is yet to be clearly defined. OBJECTIVE: To evaluate the effects of early treatment with Denosumab (⩽ 12 months after starting AIs) compared to a delayed treatment in BC women. METHODS: In this retrospective case-control study, we included medical records of BC post-menopausal women, treated with AIs therapy; they were divided as: study group (starting Denosumab ⩽ 12 months after AIs) and control group (> 12 months). At the baseline (T0) and at 18 months (T1), we evaluated the lum…

Effectiveness of Rehabilitative Intervention on Pain, Postural Balance, and Quality of Life in Women with Multiple Vertebral Fragility Fractures: A Prospective Cohort Study.

Patients with vertebral fragility fractures often experience chronic pain, postural and balance disorders, and poor quality of life (QoL). Although several studies have investigated the role of rehabilitation in severe osteoporosis, the effectiveness of this intervention in patients with multiple vertebral fractures is poorly known. The aim of our longitudinal cohort study is to evaluate the effectiveness of rehabilitation, including postural training, resistance exercises, and visual stabilization exercises, for a 7-week period, on the pain, postural balance, and QoL of subjects with at least two vertebral fragility fractures receiving denosumab and vitamin D. We investigated, before (T0) …

Women's career discrimination in the Italian Academia in the last 20 years

We examine discrimination against women in Italian universities in terms of career advancements for the last 20 years. Data is taken from the MUR archive. Two points are examined: the transition time from assistant professor to associate professor; and the transition time from associate professor to full professor.

On the Sampling Size for Inverse Sampling

In the Big Data era, sampling remains a central theme. This paper investigates the characteristics of inverse sampling on two different datasets (real and simulated) to determine when big data become too small for inverse sampling to be used and to examine the impact of the sampling rate of the subsamples. We find that the method, using the appropriate subsample size for both the mean and proportion parameters, performs well with a smaller dataset than big data through the simulation study and real-data application. Different settings related to the selection bias severity are considered during the simulation study and real application.

Variable Selection with Quasi-Unbiased Estimation: the CDF Penalty

We propose a new non-convex penalty in linear regression models. The new penalty function can be considered a competitor of the LASSO, SCAD or MCP penalties, as it guarantees sparse variable selection while reducing bias for the non-null estimates. We introduce the methodology and present some comparisons among different approaches.

Gender differences in career advancements in Italian universities over the last 20 years

This article deals with gender differences in Italian universities in the last 20 years in terms of career advancements. Data are taken from the MUR (Ministry of University and Research) archive. In Italy, career advancements are still much easier for men, even if the gender gap has slowly narrowed in the last decades. The novelty of this paper is the analysis through event-history analysis models on the time elapsed to receive a promotion (from assistant to associate professor and from associate to full professor). The event-history analysis applied to career advancements has revealed that women take, on average, about one and a half more years than men to advance, with some differences am…

Hybrid Hyaluronic Acid versus High Molecular Weight Hyaluronic Acid for the Treatment of Hip Osteoarthritis in Overweight/Obese Patients

Background: Obesity is the main risk factor for hip osteoarthritis, negatively affecting the outcome of the disease. We evaluated the effectiveness of viscosupplementation with hybrid hyaluronic acid compared to that with high molecular weight hyaluronic acid in overweight/obese patients with hip osteoarthritis (OA). Methods: 80 patients were divided into two groups: a treatment group received two ultrasound-guided intra-articular hip injections of hybrid HA 15 days apart; a control group received a single ultrasound-guided infiltration with medium-high molecular weight hyaluronic acid (1500–2000 kDa). We assessed the pain, functional and cardiovascular capacity of the patients at bas…

Risk Factors, Lifestyle and Prevention among Adolescents with Idiopathic Juvenile Scoliosis: A Cross Sectional Study in Eleven First-Grade Secondary Schools of Palermo Province, Italy.

Adolescent idiopathic scoliosis (AIS) has an incidence of 2–3% in the general population and a multifactorial etiology. The present study aims to analyze modifiable risk factors and their interactions in the development of AIS in order to increase knowledge about the disease and to prevent the evolution of AIS in young students with tailored public health strategies. A cross-sectional study was conducted over two consecutive school years among students attending 11 first-grade secondary schools in the province of Palermo, Italy. A self-administered questionnaire that investigated socio-demographical, physical and anamnestic characteristics and habits, focusing on possible risk factors…

Intra-Articular Hybrid Hyaluronic Acid Injection Treatment in Overweight Patients with Knee Osteoarthritis: A Single-Center, Open-Label, Prospective Study

Background: A BMI &gt

Adaptive smoothing spline using non-convex penalties

We propose a new adaptive penalty for smoothing via penalized splines. The new form of adaptive penalization is based on penalizing the differences of the coefficients of adjacent bases, using non-convex penalties. This makes possible to estimate curves with varying amounts of smoothness. Comparisons with respect to some competitors are presented.