A Practical Variable Selection for Linear Models

Noguchi, Hidehisa; Ojima, Yoshikazu; Yasui, Seiichi

doi:10.1007/978-3-7908-2846-7_23

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To manage the second problem, Chipman et al (1997) extended Bayesian variable selection, and Nam et al (2010) and Noguchi et al (2012) extended the Lasso. Both the extensions of these techniques were accomplished by incorporating the effect heredity principle, which governs the relationship between an interaction and its corresponding main effects.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Lasso with Effect Heredity Principle

Noguchi

Ojima

Yasui

2015

Frontiers in Statistical Quality Control 11

Self Cite

View full text Add to dashboard Cite

The Bayesian Lasso is a variable selection method that can be applied in situations where there are more variables than observations; thus, both main effects and interaction effects can be considered in screening experiments. To apply the Bayesian framework to experiments involving the effect heredity principle, which governs the relationships between interactions and their corresponding main effects, several initial tunings of the Bayesian framework are required. However, it is rather unnatural to specify these tuning values before running an experiment. In this paper, we propose models that do not require the initial tuning values to be specified in advance. The proposed methods are demonstrated with screening examples such as Plackett-Burman and mixed-level design.

show abstract

Section: Introductionmentioning

confidence: 99%

Bayesian Lasso with Effect Heredity Principle

Noguchi

Ojima

Yasui

2015

Frontiers in Statistical Quality Control 11

Self Cite

View full text Add to dashboard Cite

show abstract

Risk Assessment Integrated QbD Approach for Development of Optimized Bicontinuous Mucoadhesive Limicubes for Oral Delivery of Rosuvastatin

2018

View full text Add to dashboard Cite

Statins are widely prescribed for hyperlipidemia, cancer, and Alzheimer's disease but are facing some inherent challenges such as low solubility and drug loading, higher hepatic metabolism, as well as instability at gastric pH. So, relatively higher circulating dose, required for exerting the therapeutic benefits, leads to dose-mediated severe toxicity. Furthermore, due to low biocompatibility, high toxicity, and other regulatory caveats such as product conformity, reproducibility, and stability of conventional formulations as well as preferentially higher bioabsorption of lipids in their favorable cuboidal geometry, enhancement in in vivo biopharmaceutical performance of Rosuvastatin could be well manifested in Quality by Design (QbD) integrated cuboidal-shaped mucoadhesive microcrystalline delivery systems (Limicubes). Here, quality-target-product-profile (QTPPs), critical quality attributes (CQAs), Ishikawa fishbone diagram, and integration of risk management through risk assessment matrix for failure mode and effects analysis (FMEA) followed by processing of Plackett-Burman design matrix using different statistical test for the first time established an approach to substantiate the claims that controlling levels of only these three screened out independent process variables, i.e., Monoolein (B = 800-1100 μL), Poloxamer (C = 150-200 mg), and stirring speed (F = 700-1000 rpm) were statistically significant to modulate and improve the biopharmaceutical performance affecting key attributes, viz., average particle size (Y = 1.40-2.70 μ), entrapment efficiency (Y = 62.60-88.80%), and drug loading (Y = 0.817-1.15%), in QbD-enabled process. The optimal performance of developed Limicubes exhibited an average particle size of 1.8 ± 0.2 μ, entrapment efficiency 80.32 ± 2.88%, and drug loading 0.93 ± 0.08% at the level of 1100 μL (+ 1), 200 mg (+ 1), and 700 rpm (- 1) for Monoolein, Poloxamer, and stirring speed, respectively.

show abstract

A Practical Variable Selection for Linear Models

Cited by 2 publications

References 10 publications

Bayesian Lasso with Effect Heredity Principle

Bayesian Lasso with Effect Heredity Principle

Risk Assessment Integrated QbD Approach for Development of Optimized Bicontinuous Mucoadhesive Limicubes for Oral Delivery of Rosuvastatin

Contact Info

Product

Resources

About