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

Evaluation of nonlinear regression with extended least squares: simulation study.

A H Thomson, A W Kelman, B Whiting

    Journal of Pharmaceutical Sciences
    |December 1, 1985
    PubMed
    Summary

    Extended least squares (ELS) offers a robust alternative for nonlinear regression analysis. This method demonstrates superior bias and precision compared to ordinary least squares (OLS) and weighted least squares (WLS) in simulations.

    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

    Evaluation of amoxicillin, metronidazole and gentamicin dosage regimens for use in antibiotic prophylaxis in colorectal surgery.

    The Journal of antimicrobial chemotherapy·2021
    Same author

    Pharmacokinetic/pharmacodynamic analysis of weight- and height-scaled tobramycin dosage regimens for patients with cystic fibrosis.

    The Journal of antimicrobial chemotherapy·2019
    Same author

    SU-E-I-23: Effective Estimation of Focal Spot Isocenter for Sinograms Obtained with Flying Focal Spot Scans for Filtered Back Projection.

    Medical physics·2017
    Same author

    Aminoglycosides: old friend…new foe?

    Journal of cystic fibrosis : official journal of the European Cystic Fibrosis Society·2016
    Same author

    Changing molecular profile of brain metastases compared with matched breast primary cancers and impact on clinical outcomes.

    British journal of cancer·2016
    Same author

    The efficacy of aerosol treatment with non-ionic surfactant vesicles containing amphotericin B in rodent models of leishmaniasis and pulmonary aspergillosis infection.

    Journal of controlled release : official journal of the Controlled Release Society·2012

    Area of Science:

    • Pharmacokinetics and Pharmacodynamics
    • Statistical Modeling
    • Biomathematics

    Background:

    • Nonlinear least-squares regression is crucial for analyzing complex biological data.
    • Conventional methods like Ordinary Least Squares (OLS) and Weighted Least Squares (WLS) have limitations with certain error structures.
    • Accurate parameter estimation is vital for reliable scientific conclusions.

    Purpose of the Study:

    • To introduce and evaluate a novel Extended Least Squares (ELS) approach for nonlinear regression analysis.
    • To compare the performance of ELS against OLS, WLS-1, and WLS-2 using simulated datasets.
    • To assess the bias and precision of parameter estimates under different error conditions.

    Main Methods:

    • Monte Carlo simulations generated 1200 datasets with constant proportional and additive errors.

    Related Experiment Videos

  • Two sampling strategies (17 and 10 time points) were utilized.
  • Parameter estimation bias and precision were evaluated for ELS, OLS, WLS-1, and WLS-2.

    • Main Results:

    • Extended Least Squares (ELS) performed comparably to the most appropriate weighting schemes (WLS-2 for proportional error, OLS for additive error).
    • ELS demonstrated superior performance in reducing bias and improving precision compared to less suitable methods.
    • The effectiveness of ELS was consistent across varying error magnitudes and sampling densities.

    Conclusions:

    • Extended Least Squares (ELS) provides a reliable and effective method for nonlinear regression analysis, particularly when dealing with proportional or additive errors.
    • ELS offers advantages in both bias reduction and precision over conventional methods in pharmacokinetic and statistical modeling.
    • This approach enhances the accuracy of parameter estimation in complex data analysis scenarios.