source: main/adopters/nj/trunk/src/main/webapps/doh-shad-content/xml/html_content/home/ReliabilityValidity.xml @ 23267

Last change on this file since 23267 was 23267, checked in by GarthBraithwaite_STG, 14 months ago

nj - initial v3 webapp and content.

File size: 6.3 KB
1<?xml version="1.0" encoding="ISO-8859-1"?>
3<HTML_CONTENT xmlns:ibis="">
5        <ibis:doc>
6                <name>home/ReliabilityValidity</name>
7                <summary>Epi Concepts Page</summary>
8                <description>
9                </description>
11                <author>Garth Braithwaite</author>
12                <company>Utah Department of Health/Software Technology Group</company>
13                <versions>
14                        <version><number>2.3</number><date>Oct 20, 2016</date><who>Maria</who>
15                                <description>updated to DOH tile style</description></version>
16                        <version><number>1.1</number><date>Oct 20, 2008</date><who>Maria</who>
17                                <description>initial release (adapted from NM's reliability and validity page)</description></version>
18                        <version><number>1.0</number><date>Aug 6, 2008</date><who>Lois</who>
19                                <description>initial release (adapted from Crude Rate page)</description></version>
20                </versions>
21        </ibis:doc>
23        <TITLE>Reliability and Validity</TITLE>
24        <CONTENT>
25        <a name="TOP"></a>
26<!--            Reliability and validity are presented together because they are related, and are often
27                confused with one another.-->
28<div class="container clearfix" id="content">
29        <section id="content">
30                <div class="row" style="margin-top:-25px;">             
31                        <div class="col-md-9">
32                                <div class="panel green">
33                                        <div class="panel-heading">
34                                                <h10 class="panel-title">Reliability</h10>
35                                        </div>
36                                        <div class="panel-body">
37                                        <!--h1>Definitions</h1><br/>
38                                        <h2>Reliability</h2-->
39                                                Reliability is a property of a measure that refers to its <b>precision</b>, or the degree to
40                                                which multiple observations of a given phenomenon yield identical results. In public health,
41                                                measures such as death rates or birth outcomes are often used to indicate the true underlying
42                                                risk of illness or disability in a population. But sometimes these measures of risk fluctuate
43                                                when the true underlying risk of disease does not. The reasons for the variability usually
44                                                include one or more of the following factors: 1) the health event is relatively rare, 2)
45                                                the population size is relatively <a href="home/Glossary.html#S">small</a>, or
46                                                3) the health events do not occur at regular time intervals. <br/><br/>
48                                                Even for complete count datasets, such as birth and death certificate datasets, random
49                                                fluctuations over time can yield estimates that are not reliable. Consider the case of
50                                                low birth weight in a small community. In this community one low birth 
51                                                weight infant is born each month, on average. But low birth weight is a health event that does
52                                                not necessarily occur at regular intervals - there is randomness in the timing of low birth
53                                                weight occurrence. In our small community, if three mothers give birth to low birth weight infants
54                                                at the end of December of Year 1, and none do in January or February of Year 2, it may appear
55                                                as though the rate of low birth weight births has declined from Year 1 to Year 2.<br/><br/>
57                                                Fortunately, statistical techniques can be used to help assess whether there was a significant
58                                                difference in rates from Year 1 to Year 2. The <a href="home/Glossary.html#C">confidence
59                                                interval</a> is the statistical measure that conveys the reliability of an estimate. If an
60                                                estimate has a wide confidence interval, it decreases the likelihood that the difference
61                                                is statistically significant.<br/><br/>
63                                        <div class="Note">
64                                                <img src="../view/image/info_icon.gif" alt="info icon" width="15" height="15" title="Additional Information"/>
65                                                Rates that fluctuate over time, in the absence of changes in underlying risk, are considered
66                                                unreliable. Such rates are also commonly referred to as "unstable." Since the underlying risk
67                                                typically changes very slowly, the term, "unstable" is commonly used to refer to any rates
68                                                that fluctuate in a random pattern over relatively short timeframes.
69                                        </div> 
70                                        </div>
71                                </div>
72                        </div>
73                        <div class="col-md-3">
74                                <div class="panel blue">
75                                        <div class="panel-heading">
76                                                <h10 class="panel-title">Validity</h10>
77                                        </div>
78                                        <div class="panel-body">
79                                                <!--h2>Validity</h2-->
80                                                Validity is a property of a measurement that refers to its <b>accuracy</b>, or the degree to
81                                                which observations reflect the true value of a phenomenon. In public health, the validity
82                                                of most measures is quite good. The cause of death on a death certificate is certified by a
83                                                physician, survey measures have been tested to maximize validity, and birthweight is measured
84                                                and reported at the birth hospital. There are some measures that we question, for instance
85                                                self-reported drug and alcohol use, but on the whole, public health measures have a high
86                                                degree of validity.<br/><br/><br/>
87                                        </div>
88                                </div>
89                        </div>
90                </div>
91                <div class="row">               
92                        <div class="col-md-12">
93                                <div class="panel orange" style="margin-top:-15px;">
94                                        <div class="panel-heading">
95                                                <h10 class="panel-title">The Bulls-Eye Example</h10>
96                                        </div>
97                                        <div class="panel-body">
98                                                <!--h1>The Bulls-Eye Example</h1-->
100                                                        In the three figures below, the bulls-eye of the target represents the true underlying
101                                                        risk of disease in a population and the holes in the target represent multiple objective
102                                                        measurements of the risk. In the first figure, the measure is reliable - it measures nearly
103                                                        the same value each time. But the measure in Figure 1 is not valid - the average of the
104                                                        scores is not close to the true underlying risk. In the second figure, the scores are not
105                                                        very reliable - there is a lot of variability in the scores, but they center around the true
106                                                        risk value, so they are valid (at least on average). In the third figure, the
107                                                        measure is both reliable and valid. <br/><br/>
109                                                        <img src="view/image/reliability_validity.png" style="float:center" title="Bulls-eye showing reliability and validity concepts" alt="bullseyes"/>
111                                                        <br/><br/>
112                                                        The term "precision" is often used in relation to reliability, while the term, "accuracy" is used
113                                                        to describe validity.
114                                        </div>
115                                </div>
116                        </div>
117                </div>
118        </section>
121                <br/>   
122                <br/>                   
123        </CONTENT>
Note: See TracBrowser for help on using the repository browser.