kg_nchs: A command for Korn-Graubard confidence intervals and National Center for Health Statistics' Data Presentation Standards for Proportions

In August 2017 the National Center for Health Statistics (NCHS), part of the U.S. Federal Statistical System, published new standards for determining the reliability of proportions estimated using their data. These standards require an individual to take the Korn-Graubard confidence interval (CI), a...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The Stata journal Ročník 19; číslo 3; s. 510
Hlavní autor: Ward, Brian W
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 01.09.2019
Témata:
health survey data
Clopper-Pearson confidence interval
effective sample size
survey design
complex sample design
exact confidence interval
National Ambulatory Medical Care Survey
health care
ISSN:1536-867X
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In August 2017 the National Center for Health Statistics (NCHS), part of the U.S. Federal Statistical System, published new standards for determining the reliability of proportions estimated using their data. These standards require an individual to take the Korn-Graubard confidence interval (CI), along with CI widths, sample size, and degrees of freedom, to assess reliability of a proportion and determine if it can be presented. The assessment itself involves determining if several conditions are met. This manuscript presents , a postestimation command that is used following . It allows Stata users to (a) calculate the Korn-Graubard CI and associated statistics used in applying the NCHS presentation standards for proportions, and (b) display a series of three dichotomous flags that show if the standards are met. The empirical examples provided show how can be used to easily apply the standards and prevent Stata users from needing to perform manual calculations. While developed for NCHS survey data, this command can also be used with data that stems from any survey with a complex sample design.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1536-867X
DOI:10.1177/1536867X19874221