A PREDICTION INTERVAL FOR SCORE ON A PARALLEL TEST FORM

1978 ◽  
Vol 1978 (1) ◽  
pp. i-8
Author(s):  
Frederic M. Lord
1998 ◽  
Vol 51 (1) ◽  
pp. 193-208 ◽  
Author(s):  
CATHERINE S. CLAUSE ◽  
MORELL E. MULLINS ◽  
MARGUERITE T. NEE ◽  
ELAINE PULAKOS ◽  
NEAL SCHMITT

2020 ◽  
Author(s):  
Kurt D Shulver ◽  
Nicholas A Badcock

We report the results of a systematic review and meta-analysis investigating the relationship between perceptual anchoring and dyslexia. Our goal was to assess the direction and degree of effect between perceptual anchoring and reading ability in typical and atypical (dyslexic) readers. We performed a literature search of experiments explicitly assessing perceptual anchoring and reading ability using PsycInfo (Ovid, 1860 to 2020), MEDLINE (Ovid, 1860 to 2019), EMBASE (Ovid, 1883 to 2019), and PubMed for all available years up to June (2020). Our eligibility criteria consisted of English-language articles and, at minimum, one experimental group identified as dyslexic - either by reading assessment at the time, or by previous diagnosis. We assessed for risk of bias using an adapted version of the Newcastle-Ottawa scale. Six studies were included in this review, but only five (n = 280 participants) were included in the meta-analysis (we were unable to access the necessary data for one study).The overall effect was negative, large and statistically significant; g = -0.87, 95% CI [-1.47, 0.27]: a negative effect size indicating less perceptual anchoring in dyslexic versus non-dyslexic groups. Visual assessment of funnel plot and Egger’s test suggest minimal bias but with significant heterogeneity; Q (4) = 9.70, PI (prediction interval) [-2.32, -0.58]. The primary limitation of the current review is the small number of included studies. We discuss methodological limitations, such as limited power, and how future research may redress these concerns. The variability of effect sizes appears consistent with the inherent variability within subtypes of dyslexia. This level of dispersion seems indicative of the how we define cut-off thresholds between typical reading and dyslexia populations, but also the methodological tools we use to investigate individual performance.


2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
P Sansilvestri-Morel ◽  
F Bertin ◽  
I Lapret ◽  
B Neau ◽  
V Blanc-Guillemaud ◽  
...  

Abstract   Pulmonary embolism (PE) is the third leading cause of cardiovascular death in western countries. The enhancement of fibrinolysis constitutes a promising approach to treat thrombotic diseases. In patients, venous thrombosis and thromboembolism risks are associated with increased plasma levels of TAFI (Thrombin Activatable Fibrinolysis Inhibitor) antigen as well as the active form TAFIa. S62798 is a competitive, selective and potent human TAFIa inhibitor (IC50±SD=11.2±0.4nM). It is however less potent on mouse TAFIa (IC50±SD=270±39nM). Here, we tested the ability of S62798 to enhance endogenous fibrinolysis in a mouse model of pulmonary thromboembolism. Human Tissue Factor (TF) was injected in C57Bl6 male mice. Ten minutes later, mice (n=4 to 14 per group) were treated (IV) with S62798 (from 0.01 to 100mg/kg) or vehicle (0.9% NaCl). Ten or twenty minutes (min) later, mice were anesthetized and lungs were collected, homogenized and pulmonary fibrin was quantified by ELISA. Results are expressed as ratio of geometric mean of pulmonary fibrin (μg/mL): tested treatment/ vehicle [95% confidence interval (CI)]. Ten minutes after S62798 treatment, pulmonary fibrin deposition was dose-dependently decreased with a Minimal Effective Dose of 0.04mg/kg [90% prediction interval 0.037 - 0.051] and an ED50 of 0.03mg/kg [95% CI: 0.01; 0.06]. Mice were then treated with 0.1mg/kg S62798 or vehicle (10 min after TF induction) and fibrin deposition in lungs was quantified 10 and 20 minutes post S62798 treatment. The level of pulmonary fibrin deposition was significantly decreased (p<0.0001) compared to vehicle group (ratio 0.31 [0.21; 0.45] at 10 min; 0.35 [0.24; 0.51] at 20 min). Finally, the effect of S62798 (1mg/kg) in combination with heparin was evaluated (n=10/group). When administered 10 min before TF injection, heparin (2000IU/kg) significantly (p<0.0001) decreased pulmonary fibrin level (20 min post TF: ratio 0.03 [0.01; 0.05]). When treatment was done in a curative setting (10 min post TF), heparin alone had no effect (p=0.85) on fibrin deposition (ratio 0.96 [0.65; 1.43]) whereas a similar significant (p<0.0001) decreased pulmonary fibrin deposition was observed in response to S62798 alone or associated with heparin (ratio 0.27 [0.18; 0.40] (S62798 alone) and 0.29 [0.20; 0.43] (S62798+heparin)). In this model, curative S62798 treatment, alone or associated to heparin, accelerated clot degradation by potentiating endogenous fibrinolysis and thus decreased pulmonary fibrin deposition. Due to its capacity to enhance endogenous fibrinolysis, S62798, which has completed phase I studies, is expected to be a therapeutic option for intermediate high risk PE patients on top of anticoagulants. With early recanalization, S62798 should rapidly reduce pulmonary artery pressure and resistance, with concomitant improvement in right ventricular function, preserving cardiac function, and reducing acute PE-related morbidity and mortality in these patients. Funding Acknowledgement Type of funding source: None


2021 ◽  
Vol 11 (4) ◽  
pp. 1728
Author(s):  
Hua Zhong ◽  
Li Xu

The prediction interval (PI) is an important research topic in reliability analyses and decision support systems. Data size and computation costs are two of the issues which may hamper the construction of PIs. This paper proposes an all-batch (AB) loss function for constructing high quality PIs. Taking the full advantage of the likelihood principle, the proposed loss makes it possible to train PI generation models using the gradient descent (GD) method for both small and large batches of samples. With the structure of dual feedforward neural networks (FNNs), a high-quality PI generation framework is introduced, which can be adapted to a variety of problems including regression analysis. Numerical experiments were conducted on the benchmark datasets; the results show that higher-quality PIs were achieved using the proposed scheme. Its reliability and stability were also verified in comparison with various state-of-the-art PI construction methods.


Sign in / Sign up

Export Citation Format

Share Document