Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Residuals in multiple regression analysis.

Y J Jeng, A Martin

    Journal of Pharmaceutical Sciences
    |October 1, 1985
    PubMed
    Summary
    This summary is machine-generated.

    Residual analysis is a valuable statistical technique for selecting the best multiple-regression models. This method, though common in other fields, is underutilized in pharmaceutical sciences but offers significant benefits for model evaluation.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Use of compounds naturally labeled with stable isotopes for the study of the metabolism of glycoprotein neutral sugars by gas-liquid chromatography-isotope-ratio mass spectrometry. Technical validation in the rat.

    Carbohydrate research·1992
    Same author

    Potent gp120-like neurotoxic activity in the cerebrospinal fluid of HIV-infected individuals is blocked by peptide T.

    Brain research·1992
    Same author

    Lateralized mediation of arousal and habituation: differential bilateral electrodermal activity in unilateral temporal lobectomy patients.

    Neuropsychologia·1992
    Same author

    Transfusion-associated graft-versus-host disease, monoclonal gammopathy and PCR.

    British journal of haematology·1992
    Same author

    What do patients want to know about their inflammatory bowel disease?

    The Italian journal of gastroenterology·1992
    Same author

    Phosphatidate phosphohydrolases in liver, heart and adipose tissue of the JCR:LA corpulent rat and the lean genotypes: implications for glycerolipid synthesis and signal transduction.

    International journal of obesity and related metabolic disorders : journal of the International Association for the Study of Obesity·1992

    Area of Science:

    • Pharmaceutical Sciences
    • Statistics
    • Medicinal Chemistry

    Background:

    • Multiple-regression analysis is crucial for modeling complex data in various scientific disciplines.
    • Traditional model selection relies on metrics like R2 and Fisher F ratio.
    • Residual analysis, a robust statistical technique, is underrepresented in pharmaceutical research.

    Purpose of the Study:

    • To highlight the utility of residual analysis in pharmaceutical sciences.
    • To demonstrate how residual analysis can improve model selection in drug-related studies.
    • To encourage the adoption of comprehensive residual analysis in pharmaceutical research.

    Main Methods:

    • Review of statistical principles of residual analysis.
    • Application of residual analysis to two distinct pharmaceutical science datasets.

    Related Experiment Videos

  • Comparison of results obtained through residual analysis versus traditional methods.

    • Main Results:

    • Residual analysis effectively identified model bias and improved equation selection in pharmaceutical contexts.
    • The technique provided deeper insights beyond standard R2 and F-ratio values.
    • Demonstrated practical utility in fitting physicochemical, biological, and psychosociological data relevant to pharmaceuticals.

    Conclusions:

    • Residual analysis is a powerful, yet underutilized, tool for enhancing model selection in pharmaceutical research.
    • Incorporating residual analysis can lead to more accurate and reliable models in drug discovery and development.
    • Further adoption of this statistical method is recommended for pharmaceutical scientists.