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

Statistical modelling of Poisson/log normal data.

Guthrie Miller1

  • 1Los Alamos National Laboratory MS-G761, Los Alamos, NM 87545, USA. guthrie@lanl.gov

Radiation Protection Dosimetry
|January 16, 2007
PubMed
Summary
This summary is machine-generated.

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

Modeling Plutonium Decorporation in a Female Nuclear Worker Treated with Ca-DTPA after Inhalation Intake.

Health physics·2024
Same author

Chelation Modeling of a Plutonium-238 Inhalation Incident Treated with Delayed DTPA.

Radiation research·2023
Same author

Chelation Model Validation: Modeling of a Plutonium-238 Inhalation Incident Treated with DTPA at Los Alamos National Laboratory.

Health physics·2023
Same author

Use of Nasal Swab Activity to Estimate Intake in Internal Dosimetry.

Health physics·2023
Same author

Alternate Analysis of an In Vitro Solubility Study on the Lung Dissolution Rate of 238PuO2 Material Involved in the 2020 Incident at Los Alamos National Laboratory.

Health physics·2022
Same author

Dose Assessment Following a 238 Pu Inhalation Incident at Los Alamos National Laboratory.

Health physics·2022
Same journal

A proposal for a differentiated radiation protection program for the decommissioning of nuclear power plants compared to the operation of nuclear power plants.

Radiation protection dosimetry·2026
Same journal

A three-dimensional neutron localization method based on double-scattering imaging and reconstruction algorithm.

Radiation protection dosimetry·2026
Same journal

Effect of 131I biodistribution on measurements using a scanning whole-body counter.

Radiation protection dosimetry·2026
Same journal

Activity concentration of 137Cs and natural radionuclides in soil around the Belarusian nuclear power plant in the pre-commissioning period.

Radiation protection dosimetry·2026
Same journal

Novel passive-adaptive exoskeleton-supported radiation protection equipment with enhanced shielding and reduced perceived weight.

Radiation protection dosimetry·2026
Same journal

Feasibility of kV dose measurement in IGRT using MV-calibrated ionization chambers.

Radiation protection dosimetry·2026
See all related articles

This study proposes and evaluates new methods for calculating standard deviation in statistical data fitting, particularly for Poisson/log-normal distributions. Two preferred alternatives improve uncertainty estimation, especially with limited replicate data.

Area of Science:

  • Statistics
  • Data Analysis
  • Scientific Computing

Background:

  • Statistical data fitting relies on chi-squared/NDF for self-consistency.
  • Calculating chi-squared requires accurate standard deviation expressions.
  • Existing methods for Poisson/log-normal distributions have limitations.

Purpose of the Study:

  • To propose and evaluate alternative expressions for standard deviation.
  • To address uncertainty estimation issues with limited replicate data.
  • To modify log-normal approximations for hypothesis testing.

Main Methods:

  • Monte Carlo simulations were used to evaluate proposed standard deviation expressions.
  • Analysis focused on data following Poisson/log-normal distributions.

Related Experiment Videos

  • A correction method for replicate data uncertainty was developed.

    • Main Results:

    • Two alternative expressions for standard deviation were identified as preferred.
    • The proposed method improves uncertainty estimation with few replicates.
    • A modified log-normal approximation facilitates testing for a true value of zero.

    Conclusions:

    • Accurate standard deviation estimation is crucial for reliable statistical data fitting.
    • The proposed methods offer improved solutions for Poisson/log-normal data.
    • These advancements enhance the robustness of statistical hypothesis testing.