Assessing Reliability and Validity Measures in Managed Care Studies

Isaac D Montoya

doi:10.29074/ascls.16.3.153

This article requires a subscription to view the full text. If you have a subscription you may use the login form below to view the article. Access to this article can also be purchased.

Isaac D Montoya, PhD CMC CLS(NCA)⇑
1. is Clinical Professor, College of Pharmacy, University of Houston, Houston TX

Address for correspondence: Isaac D Montoya, College of Pharmacy. University of Houston, 3104 Edloe, Suite 330, Houston TX 77027.

After completing this article, the reader will be able to:

define measurement, describing sources and types of measurement errors.
define reliability and validity.
cite numerical ranges for reliability and validity.
describe how reliability and validity are each calculated.
explain how reliability and validity relate to measurement error(s).
apply reliability and validity concepts to the evaluation of managed care and similar studies.
describe the relationship between a theoretical concept and its operationalization.
list and define the types of validity that apply to evaluation of managed care and similar studies, including method(s) of measurement.

Abstract

BACKGROUND: To review the reliability and validity literature and develop an understanding of these concepts as applied to managed care studies.

RESULTS: Reliability is a test of how well an instrument measures the same input at varying times and under varying conditions. Validity is a test of how accurately an instrument measures what one believes is being measured.

METHODS: A review of reliability and validity instructional material was conducted.

CONCLUSIONS: Studies of managed care practices and programs abound. However, many of these studies utilize measurement instruments that were developed for other purposes or for a population other than the one being sampled. In other cases, instruments have been developed without any testing of the instrument's performance. The lack of reliability and validity information may limit the value of these studies. This is particularly true when data are collected for one purpose and used for another. The usefulness of certain studies without reliability and validity measures is questionable, especially in cases where the literature contradicts itself.