1 | <?xml version="1.0" encoding="ISO-8859-1"?> |
---|
2 | |
---|
3 | <HTML_CONTENT xmlns:ibis="http://www.ibisph.org"> |
---|
4 | |
---|
5 | <ibis:doc> |
---|
6 | <name>home/AARate</name> |
---|
7 | <summary>Epi Concepts Page</summary> |
---|
8 | <description> |
---|
9 | </description> |
---|
10 | |
---|
11 | <author>Garth Braithwaite</author> |
---|
12 | <company>Utah Department of Health/Software Technology Group</company> |
---|
13 | <versions> |
---|
14 | <version><number>1.2</number><date>Oct 16, 2008</date><who>Maria</who> |
---|
15 | <description>initial release (adapted from NM's XML page)</description></version> |
---|
16 | <version><number>1.1</number><date>Aug 5, 2008</date><who>Lois</who> |
---|
17 | <description>split out from count_rate page</description></version> |
---|
18 | <version><number>1.0</number><date>Jun 13, 2008</date><who>Lois</who> |
---|
19 | <description>initial release (adapted from Utah's html page)</description></version> |
---|
20 | </versions> |
---|
21 | </ibis:doc> |
---|
22 | |
---|
23 | <TITLE>Age-Adjusted Rates</TITLE> |
---|
24 | <CONTENT> |
---|
25 | <a name="TOP"></a><br/> |
---|
26 | |
---|
27 | An <text class="Bold">age-adjusted rate</text> is a |
---|
28 | measure that controls for the effects of age differences on health event rates. |
---|
29 | When comparing across geographic areas, some method of age-adjusting is typically |
---|
30 | used to control for the influence that different population age distributions might |
---|
31 | have on health event rates. <br/><br/> |
---|
32 | |
---|
33 | <a href="home/Rate.html">Crude rates</a> provide a useful summary measure to compare similar populations of |
---|
34 | different sizes, but crude rates are sensitive to differences in age compositions.<br/><br/> |
---|
35 | |
---|
36 | For example, a county with an older population will have a higher |
---|
37 | crude death rate due to cancer, even though its risk exposure levels and age-specific |
---|
38 | cancer rates may the same as those in other counties. One might incorrectly attribute |
---|
39 | the high cancer rate to some characteristic of the county other than age. Age-adjustment |
---|
40 | may also be used to control for age effects when comparing across several years of data, as the |
---|
41 | age distribution of the population changes over time. Calculating age-adjusted rates may be |
---|
42 | accomplished using direct, or indirect age standardization.<br/><br/> |
---|
43 | |
---|
44 | Click a bar below to expand or collapse its content.<br/><br/> |
---|
45 | |
---|
46 | <ibis:ExpandableContent titleLevel="2"><HIDE/> |
---|
47 | <TITLE>Direct Age-adjustment</TITLE> |
---|
48 | <CONTENT> |
---|
49 | <br/> |
---|
50 | <!--h1>Direct Age-adjustment</h1--> |
---|
51 | |
---|
52 | Direct age-adjustment (or age standardization) is the same as calculating a |
---|
53 | <a href="home/Glossary.html#W">weighted average</a>. It weights the |
---|
54 | <a href="home/Glossary.html#A">age-specific rates</a> observed in a |
---|
55 | population of interest by the proportion of each age group in a standard population |
---|
56 | (<a href="#Bib-5">Lilienfeld & Stolley</a>). |
---|
57 | <br/><br/> |
---|
58 | |
---|
59 | In 1999, the Centers for Disease Control and Prevention (CDC) replaced the 1940 U.S. standard population weights |
---|
60 | that had been used for the several previous decades with revised standard population weights |
---|
61 | for direct age-adjustment (<a href="#Bib-2">Klein & Schoenborn</a>). Table 1, below, |
---|
62 | contains the CDC standard population weights, which represent the proportion of |
---|
63 | the U.S. 2000 population in each age group, and sum to 1.0.<br/><br/> |
---|
64 | |
---|
65 | <div class="Note"> |
---|
66 | <img src="../contentfile/image/important_icon.gif" alt="important! icon" width="19" height="18" title="IMPORTANT!"/> |
---|
67 | Compare only age-adjusted rates that have been adjusted to the <text class="Bold">same</text> standard |
---|
68 | population. For instance, don't compare rates age-adjusted using the U.S. 1940 standard population |
---|
69 | with rates that were age-adjusted using the U.S. 2000 population.<br/><br/> |
---|
70 | <b>Unless otherwise noted, all age-adjusted rates in NJSHAD have been |
---|
71 | adjusted using the US 2000 population standard.</b><br/><br/> |
---|
72 | Age-adjusted rates should be viewed as <text class="Bold">relative indexes</text>, and used for comparison |
---|
73 | of populations. They are not actual measures of mortality risk, and do not convey the magnitude of the problem.<br/> |
---|
74 | </div><br/><br/> |
---|
75 | |
---|
76 | <h3>Table 1. U.S. 2000 Standard Population Weights for Age Standardization</h3> |
---|
77 | <br/> |
---|
78 | <table class="Info"> |
---|
79 | <tr> |
---|
80 | <th width="10%"><p align="center" style="font-weight:bold"></p></th> |
---|
81 | <th width="25%"><p align="center" style="font-weight:bold">Age Group</p></th> |
---|
82 | <th width="35%"><p align="center" style="font-weight:bold">U.S. 2000 Population Projection<br/>(in thousands)</p></th> |
---|
83 | <th width="30%"><p align="center" style="font-weight:bold">Weight</p></th> |
---|
84 | </tr> |
---|
85 | <tr> |
---|
86 | <td><p>1</p></td> |
---|
87 | <td><p style="padding-left:10px">Under 1 Year</p></td> |
---|
88 | <td><p align="right" style="padding-right:20px">3,795</p></td> |
---|
89 | <td><p align="center">0.013818</p></td> |
---|
90 | </tr> |
---|
91 | <tr> |
---|
92 | <td><p>2</p></td> |
---|
93 | <td><p style="padding-left:10px">1 - 4 Years</p></td> |
---|
94 | <td><p align="right" style="padding-right:20px">15,192</p></td> |
---|
95 | <td><p align="center">0.055317</p></td> |
---|
96 | </tr> |
---|
97 | <tr> |
---|
98 | <td><p>3</p></td> |
---|
99 | <td><p style="padding-left:10px">5 - 14 Years</p></td> |
---|
100 | <td><p align="right" style="padding-right:20px">39,977 </p></td> |
---|
101 | <td><p align="center">0.145565</p></td> |
---|
102 | </tr> |
---|
103 | <tr> |
---|
104 | <td><p>4</p></td> |
---|
105 | <td><p style="padding-left:10px">15 - 24 Years</p></td> |
---|
106 | <td><p align="right" style="padding-right:20px">38,077 </p></td> |
---|
107 | <td><p align="center">0.138646</p></td> |
---|
108 | </tr> |
---|
109 | <tr> |
---|
110 | <td><p>5</p></td> |
---|
111 | <td><p style="padding-left:10px">25 - 34 Years</p></td> |
---|
112 | <td><p align="right" style="padding-right:20px">37,233 </p></td> |
---|
113 | <td><p align="center">0.135573</p></td> |
---|
114 | </tr> |
---|
115 | <tr> |
---|
116 | <td><p>6</p></td> |
---|
117 | <td><p style="padding-left:10px">35 - 44 Years</p></td> |
---|
118 | <td><p align="right" style="padding-right:20px">44,659 </p></td> |
---|
119 | <td><p align="center">0.162613</p></td> |
---|
120 | </tr> |
---|
121 | <tr> |
---|
122 | <td><p>7</p></td> |
---|
123 | <td><p style="padding-left:10px">45 - 54 Years</p></td> |
---|
124 | <td><p align="right" style="padding-right:20px">37,030 </p></td> |
---|
125 | <td><p align="center">0.134834</p></td> |
---|
126 | </tr> |
---|
127 | <tr> |
---|
128 | <td><p>8</p></td> |
---|
129 | <td><p style="padding-left:10px">55 - 64 Years</p></td> |
---|
130 | <td><p align="right" style="padding-right:20px">23,962 </p></td> |
---|
131 | <td><p align="center">0.087247</p></td> |
---|
132 | </tr> |
---|
133 | <tr> |
---|
134 | <td><p>9</p></td> |
---|
135 | <td><p style="padding-left:10px">65 - 74 Years</p></td> |
---|
136 | <td><p align="right" style="padding-right:20px">18,136 </p></td> |
---|
137 | <td><p align="center">0.066037</p></td> |
---|
138 | </tr> |
---|
139 | <tr> |
---|
140 | <td><p>10</p></td> |
---|
141 | <td><p style="padding-left:10px">75 - 84 Years</p></td> |
---|
142 | <td><p align="right" style="padding-right:20px">12,315 </p></td> |
---|
143 | <td><p align="center">0.044842</p></td> |
---|
144 | </tr> |
---|
145 | <tr> |
---|
146 | <td><p>11</p></td> |
---|
147 | <td><p style="padding-left:10px">85 Years and Over</p></td> |
---|
148 | <td><p align="right" style="padding-right:20px">4,259 </p></td> |
---|
149 | <td><p align="center">0.015508</p></td> |
---|
150 | </tr> |
---|
151 | </table><br/><br/> |
---|
152 | |
---|
153 | <p align="right"><a href="#TOP">Back to Top</a></p> |
---|
154 | <br/> |
---|
155 | <h2>Calculating Age-Adjusted Rates Using the Direct Method</h2> |
---|
156 | <br/> |
---|
157 | To apply direct age-adjustment to a set of rates, the age-specific rate for each |
---|
158 | age group in the study population is multiplied by the appropriate weight in the |
---|
159 | standard population. The sum of these products is the directly age-adjusted, or |
---|
160 | age-standardized rate. The age-adjusted rate can be considered an average of each |
---|
161 | of the individual age-specific rates, but rather than being a simple average, it |
---|
162 | is a <a href="home/Glossary.html#W">weighted average</a> with each age-specific rate weighted |
---|
163 | by the proportion of people in the same age group in the standard population.<br/><br/> |
---|
164 | |
---|
165 | Tables 2a. and 2b. demonstrate the method used by NJSHAD in calculating age-adjusted rates. |
---|
166 | Notice that using crude death rates in Tables 2a. and 2b., one might conclude that whites have |
---|
167 | a higher underlying risk for heart disease death compared with blacks. How should the age-adjusted |
---|
168 | death rates be interpreted? You could use <a href="home/Glossary.html#C">confidence intervals</a> |
---|
169 | to assist in interpreting these data (NJSHAD automatically provides 95% confidence intervals for all rates).<br/><br/> |
---|
170 | |
---|
171 | <h3>Table 2a. Age-Adjusted Death Rate due to Heart Disease among Whites, New Jersey, 2004</h3> |
---|
172 | <br/> |
---|
173 | <table class="Info"> |
---|
174 | <tr> |
---|
175 | <th width="100"><p align="center" style="font-weight:bold">Age Group</p></th> |
---|
176 | <th> <p align="center" style="font-weight:bold">Number of Deaths<br/>(3-Year Sum)</p></th> |
---|
177 | <th> <p align="center" style="font-weight:bold">Population Counts<br/>(3-Year Sum) [1]</p></th> |
---|
178 | <th> <p align="center" style="font-weight:bold">Age- Specific Rate [2]</p></th> |
---|
179 | <th> <p align="center" style="font-weight:bold">U.S. 2000 Standard<br/>Population Weight</p></th> |
---|
180 | <th> <p align="center" style="font-weight:bold">Cross Products [3]</p></th> |
---|
181 | </tr> |
---|
182 | <tr> |
---|
183 | <td> Under 5 years </td> |
---|
184 | <td><p align="right"> 4 </p></td> |
---|
185 | <td><p align="right"> 307,139 </p></td> |
---|
186 | <td><p align="right"> 1.30 </p></td> |
---|
187 | <td><p align="right"> 0.069135 </p></td> |
---|
188 | <td><p align="right"> 0.090037 </p></td> |
---|
189 | </tr> |
---|
190 | <tr> |
---|
191 | <td> 5 - 14 years </td> |
---|
192 | <td><p align="right"> 3 </p></td> |
---|
193 | <td><p align="right"> 709,758 </p></td> |
---|
194 | <td><p align="right"> 0.42 </p></td> |
---|
195 | <td><p align="right"> 0.145565 </p></td> |
---|
196 | <td><p align="right"> 0.061527 </p></td> |
---|
197 | </tr> |
---|
198 | <tr> |
---|
199 | <td> 15 - 24 years </td> |
---|
200 | <td><p align="right"> 15 </p></td> |
---|
201 | <td><p align="right"> 634,256 </p></td> |
---|
202 | <td><p align="right"> 2.36 </p></td> |
---|
203 | <td><p align="right"> 0.138646 </p></td> |
---|
204 | <td><p align="right"> 0.327894 </p></td> |
---|
205 | </tr> |
---|
206 | <tr> |
---|
207 | <td> 25 - 34 years </td> |
---|
208 | <td><p align="right"> 35 </p></td> |
---|
209 | <td><p align="right"> 576,010 </p></td> |
---|
210 | <td><p align="right"> 6.08 </p></td> |
---|
211 | <td><p align="right"> 0.135573 </p></td> |
---|
212 | <td><p align="right"> 0.823780 </p></td> |
---|
213 | </tr> |
---|
214 | <tr> |
---|
215 | <td> 35 - 44 years </td> |
---|
216 | <td><p align="right"> 169 </p></td> |
---|
217 | <td><p align="right"> 883,005 </p></td> |
---|
218 | <td><p align="right"> 19.14 </p></td> |
---|
219 | <td><p align="right"> 0.162613 </p></td> |
---|
220 | <td><p align="right"> 3.112281 </p></td> |
---|
221 | </tr> |
---|
222 | <tr> |
---|
223 | <td> 45 - 54 years </td> |
---|
224 | <td><p align="right"> 542 </p></td> |
---|
225 | <td><p align="right"> 886,502 </p></td> |
---|
226 | <td><p align="right"> 61.14 </p></td> |
---|
227 | <td><p align="right"> 0.134834 </p></td> |
---|
228 | <td><p align="right"> 8.243639 </p></td> |
---|
229 | </tr> |
---|
230 | <tr> |
---|
231 | <td> 55 - 64 years </td> |
---|
232 | <td><p align="right"> 1,126 </p></td> |
---|
233 | <td><p align="right"> 647,215 </p></td> |
---|
234 | <td><p align="right"> 173.98 </p></td> |
---|
235 | <td><p align="right"> 0.087247 </p></td> |
---|
236 | <td><p align="right"> 15.178901 </p></td> |
---|
237 | </tr> |
---|
238 | <tr> |
---|
239 | <td> 65 - 74 years </td> |
---|
240 | <td><p align="right"> 2,109 </p></td> |
---|
241 | <td><p align="right"> 411,158 </p></td> |
---|
242 | <td><p align="right"> 512.94 </p></td> |
---|
243 | <td><p align="right"> 0.066037 </p></td> |
---|
244 | <td><p align="right"> 33.873118 </p></td> |
---|
245 | </tr> |
---|
246 | <tr> |
---|
247 | <td> 75 - 84 years </td> |
---|
248 | <td><p align="right"> 5,679 </p></td> |
---|
249 | <td><p align="right"> 353,102 </p></td> |
---|
250 | <td><p align="right"> 1,608.32 </p></td> |
---|
251 | <td><p align="right"> 0.044842 </p></td> |
---|
252 | <td><p align="right"> 72.120157 </p></td> |
---|
253 | </tr> |
---|
254 | <tr> |
---|
255 | <td> 85 yrs & over </td> |
---|
256 | <td><p align="right"> 7,621 </p></td> |
---|
257 | <td><p align="right"> 141,128 </p></td> |
---|
258 | <td><p align="right"> 5,400.06 </p></td> |
---|
259 | <td><p align="right"> 0.015508 </p></td> |
---|
260 | <td><p align="right"> 83.744167 </p></td> |
---|
261 | </tr> |
---|
262 | <tr> |
---|
263 | <td> All Ages </td> |
---|
264 | <td><p align="right"> 17,305 </p></td> |
---|
265 | <td><p align="right"> 5,549,273 </p></td> |
---|
266 | <td><p align="right"> 311.8 [a] </p></td> |
---|
267 | <td><p align="right"> 1 </p></td> |
---|
268 | <td><p align="right"><text class="Bold">217.6</text> [b]</p></td> |
---|
269 | </tr> |
---|
270 | </table><br/><br/> |
---|
271 | |
---|
272 | <h3>Table 2b. Age-Adjusted Death Rate due to Heart Disease among Blacks, New Jersey, 2004</h3> |
---|
273 | <br/> |
---|
274 | <table class="Info"> |
---|
275 | <tr> |
---|
276 | <th width="100"><p align="center" style="font-weight:bold">Age Group</p></th> |
---|
277 | <th> <p align="center" style="font-weight:bold">Number of Deaths<br/>(3-Year Sum)</p></th> |
---|
278 | <th> <p align="center" style="font-weight:bold">Population Counts<br/>(3-Year Sum) [1]</p></th> |
---|
279 | <th> <p align="center" style="font-weight:bold">Age- Specific Rate [2]</p></th> |
---|
280 | <th> <p align="center" style="font-weight:bold">U.S. 2000 Standard<br/>Population Weight</p></th> |
---|
281 | <th> <p align="center" style="font-weight:bold">Cross Products [3]</p></th> |
---|
282 | </tr> |
---|
283 | <tr> |
---|
284 | <td> Under 5 years </td> |
---|
285 | <td><p align="right"> 3 </p></td> |
---|
286 | <td><p align="right"> 91,279 </p></td> |
---|
287 | <td><p align="right"> 3.29 </p></td> |
---|
288 | <td><p align="right"> 0.069135 </p></td> |
---|
289 | <td><p align="right"> 0.227221 </p></td> |
---|
290 | </tr> |
---|
291 | <tr> |
---|
292 | <td> 5 - 14 years </td> |
---|
293 | <td><p align="right"> 2 </p></td> |
---|
294 | <td><p align="right"> 188,782 </p></td> |
---|
295 | <td><p align="right"> 1.06 </p></td> |
---|
296 | <td><p align="right"> 0.145565 </p></td> |
---|
297 | <td><p align="right"> 0.154215 </p></td> |
---|
298 | </tr> |
---|
299 | <tr> |
---|
300 | <td> 15 - 24 years </td> |
---|
301 | <td><p align="right"> 8 </p></td> |
---|
302 | <td><p align="right"> 178,727 </p></td> |
---|
303 | <td><p align="right"> 4.48 </p></td> |
---|
304 | <td><p align="right"> 0.138646 </p></td> |
---|
305 | <td><p align="right"> 0.620593 </p></td> |
---|
306 | </tr> |
---|
307 | <tr> |
---|
308 | <td> 25 - 34 years </td> |
---|
309 | <td><p align="right"> 24 </p></td> |
---|
310 | <td><p align="right"> 159,695 </p></td> |
---|
311 | <td><p align="right"> 15.03 </p></td> |
---|
312 | <td><p align="right"> 0.135573 </p></td> |
---|
313 | <td><p align="right"> 2.037479 </p></td> |
---|
314 | </tr> |
---|
315 | <tr> |
---|
316 | <td> 35 - 44 years </td> |
---|
317 | <td><p align="right"> 84 </p></td> |
---|
318 | <td><p align="right"> 186,190 </p></td> |
---|
319 | <td><p align="right"> 45.12 </p></td> |
---|
320 | <td><p align="right"> 0.162613 </p></td> |
---|
321 | <td><p align="right"> 7.336319 </p></td> |
---|
322 | </tr> |
---|
323 | <tr> |
---|
324 | <td> 45 - 54 years </td> |
---|
325 | <td><p align="right"> 205 </p></td> |
---|
326 | <td><p align="right"> 149,037 </p></td> |
---|
327 | <td><p align="right"> 137.55 </p></td> |
---|
328 | <td><p align="right"> 0.134834 </p></td> |
---|
329 | <td><p align="right"> 18.546381 </p></td> |
---|
330 | </tr> |
---|
331 | <tr> |
---|
332 | <td> 55 - 64 years </td> |
---|
333 | <td><p align="right"> 309 </p></td> |
---|
334 | <td><p align="right"> 98,175 </p></td> |
---|
335 | <td><p align="right"> 314.74 </p></td> |
---|
336 | <td><p align="right"> 0.087247 </p></td> |
---|
337 | <td><p align="right"> 27.460477 </p></td> |
---|
338 | </tr> |
---|
339 | <tr> |
---|
340 | <td> 65 - 74 years </td> |
---|
341 | <td><p align="right"> 470 </p></td> |
---|
342 | <td><p align="right"> 58,583 </p></td> |
---|
343 | <td><p align="right"> 802.28 </p></td> |
---|
344 | <td><p align="right"> 0.066037 </p></td> |
---|
345 | <td><p align="right"> 52.980199 </p></td> |
---|
346 | </tr> |
---|
347 | <tr> |
---|
348 | <td> 75 - 84 years </td> |
---|
349 | <td><p align="right"> 609 </p></td> |
---|
350 | <td><p align="right"> 32,097 </p></td> |
---|
351 | <td><p align="right"> 1,897.37 </p></td> |
---|
352 | <td><p align="right"> 0.044842 </p></td> |
---|
353 | <td><p align="right"> 85.082026 </p></td> |
---|
354 | </tr> |
---|
355 | <tr> |
---|
356 | <td> 85 yrs & over </td> |
---|
357 | <td><p align="right"> 3 </p></td> |
---|
358 | <td><p align="right"> 1,584 </p></td> |
---|
359 | <td><p align="right"> 189.45 </p></td> |
---|
360 | <td><p align="right"> 0.015508 </p></td> |
---|
361 | <td><p align="right"> 2.938097 </p></td> |
---|
362 | </tr> |
---|
363 | <tr> |
---|
364 | <td> All Ages </td> |
---|
365 | <td><p align="right"> 2,152 </p></td> |
---|
366 | <td><p align="right"> 1,153,392 </p></td> |
---|
367 | <td><p align="right"> 186.6 [a] </p></td> |
---|
368 | <td><p align="right"> 1 </p></td> |
---|
369 | <td><p align="right"><text class="Bold">256.5</text> [b]</p></td> |
---|
370 | </tr> |
---|
371 | </table><br/><br/> |
---|
372 | <table class="Info"> |
---|
373 | <tr><td>[1] New Jersey Department of Labor and Workforce Development, State Data Center</td></tr> |
---|
374 | <tr><td>[2] Rate per 100,000 = (Age-specific death count * 100,000) / Age-specific population count</td></tr> |
---|
375 | <tr><td>[3] Age-specific death rate * US2000 Std Pop Weight</td></tr> |
---|
376 | <tr><td>[a] Crude death rate</td></tr> |
---|
377 | <tr><td>[b] <text class="Bold">Age-adjusted rate.</text></td></tr> |
---|
378 | </table><br/><br/> |
---|
379 | |
---|
380 | Age adjustment is not appropriate if the age-specific death rates in the population of |
---|
381 | interest do not have a consistent relationship. For example, if the death rate among younger |
---|
382 | persons is increasing over time, but the death rate among older persons is decreasing over time, |
---|
383 | one would not want to age-adjust rates across years. One's conclusion of |
---|
384 | the trend in this death rate would be different, depending on which standard population is used. |
---|
385 | A younger standard population (such as the US 1940) would show an increase, whereas an older |
---|
386 | standard population (such as the US 2000) would show a decrease, or no change at all. Care |
---|
387 | should be taken so that the selection of the standard population does not affect the comparisons. |
---|
388 | For more information, see <a href="#Bib-3">Curtin & Klein</a>.<br/><br/> |
---|
389 | |
---|
390 | When reporting age-adjusted rates, always report the standard population used, and when |
---|
391 | comparing results to other data, be sure to document that those data were also age-adjusted |
---|
392 | and report the standard population. The age-adjusted rate is hypothetical, and is useful only |
---|
393 | for <text class="Bold">comparing</text> populations, either over time, by geographic area, |
---|
394 | by sex or by racial/ethnic subgroups. <br/><br/> |
---|
395 | |
---|
396 | <div class="Note"> |
---|
397 | <img src="../contentfile/image/important_icon.gif" alt="important! icon" width="19" height="18" title="IMPORTANT!"/> |
---|
398 | Although age-adjustment may be used with broad population age groups, such as adults (e.g., age 18+), |
---|
399 | it is not necessary (or meaningful) to age-adjust data for smaller age groups (e.g., age 18-24). |
---|
400 | </div><br/><br/> |
---|
401 | |
---|
402 | <p align="right"><a href="#TOP">Back to Top</a></p> |
---|
403 | <br/> |
---|
404 | <p><hr/></p> |
---|
405 | <br/> |
---|
406 | |
---|
407 | <h2>FAQs for Age-Adjustment:</h2><br/> |
---|
408 | |
---|
409 | <h3>Event Rates for a Subpopulation</h3> |
---|
410 | <text class="Bold">Q:</text>I am looking at death rates for female breast cancer. Which standard |
---|
411 | population should I use, females in US 2000 or all persons?<br/> |
---|
412 | <text class="Bold">A:</text>Theoretically, it doesn't matter, as long as you use the |
---|
413 | <text class="Bold">same</text> standard population for all your analyses. But the recommended |
---|
414 | standard population is now the U.S. 2000 total population, even for analyses that apply only |
---|
415 | to a particular sex, race, or other subgroup.<br/><br/> |
---|
416 | |
---|
417 | <h3>When NOT to Age-Adjust</h3> |
---|
418 | <text class="Bold">Q:</text>Are there times I should NOT age-adjust?<br/> |
---|
419 | <text class="Bold">A:</text>Yes. Do NOT use age-adjustment when... |
---|
420 | <div><ul> |
---|
421 | <li>You are comparing populations with similar age distributions, and age-adjustment does not |
---|
422 | produce a rate that is substantively different from the crude rate.</li> |
---|
423 | <li>You are comparing groups with the same, narrow, age range.</li> |
---|
424 | <li>Do not use Direct Age-Adjustment if you have too few cases (you should have a least 20 |
---|
425 | events across all age groups). Instead, use Indirect Age-Adjustment.</li> |
---|
426 | </ul></div> |
---|
427 | <br/> |
---|
428 | |
---|
429 | <h3>Age Subpopulations</h3> |
---|
430 | <text class="Bold">Q:</text> I am looking at adults, only. If I use the weights in Table 1, |
---|
431 | above, they will not sum to one. Is that okay?<br/> |
---|
432 | <text class="Bold">A:</text> No. The weights must always sum to one. Weights for certain age |
---|
433 | subgroups have been published by the CDC. But you may also recompute the proportions in Table 1, |
---|
434 | using only the age range that is relevant to your analysis.<br/><br/> |
---|
435 | |
---|
436 | <h3>Age/Sex Adjusted Rates</h3> |
---|
437 | <text class="Bold">Q:</text> I have a report that uses age AND SEX adjusted rates. What is this, |
---|
438 | and why doesn't NJSHAD produce age and sex adjusted rates?<br/> |
---|
439 | <text class="Bold">A:</text> It is sometimes appropriate to adjust by other variables besides age. |
---|
440 | Rates that have been adjusted by age and sex use age- and sex-specific rates, weighted by |
---|
441 | twice the number of weights (one set for males and one set for females), but the total of all |
---|
442 | the weights still must sum to 1.0. NJSHAD doesn't compute these rates because there is little |
---|
443 | demand for it.<br/><br/> |
---|
444 | |
---|
445 | <h3>Confidence Intervals for Age-Adjusted Rates</h3> |
---|
446 | <text class="Bold">Q:</text> Can I use the confidence interval for the crude rate with the |
---|
447 | age-adjusted rate?<br/> |
---|
448 | <text class="Bold">A:</text> No, a new confidence interval for the age-adjusted rate must be |
---|
449 | calculated. Methods for calculation of this confidence interval may be found in |
---|
450 | <a href="#Bib-3">Curtin & Klein</a>.<br/><br/> |
---|
451 | |
---|
452 | <p align="right"><a href="#TOP">Back to Top</a></p> |
---|
453 | </CONTENT> |
---|
454 | </ibis:ExpandableContent> |
---|
455 | |
---|
456 | <ibis:ExpandableContent titleLevel="2"><HIDE/> |
---|
457 | <TITLE>Indirect Age-adjustment</TITLE> |
---|
458 | <CONTENT> |
---|
459 | |
---|
460 | <!--h1>Indirect Age-Adjustment</h1--> |
---|
461 | <br/> |
---|
462 | In some cases, such as when there are too few cases to stratify by age, "indirect age standardization" |
---|
463 | may be used. Indirect standardization is based on standard mortality and morbidity ratios (SMR), and |
---|
464 | adjusts the age-specific rates found in the standard population to the age distribution of the smaller |
---|
465 | area or sub-population. According to <a href="#Bib-3">Curtin & Klein</a>, "One of the problems with |
---|
466 | [direct age adjustment] is that rates based on small numbers of deaths will exhibit a large amount of |
---|
467 | random variation. A very rough guideline is that there should be at least 25 total deaths over all age |
---|
468 | groups." NJSHAD follows NCHS's guideline of 20 total deaths. When fewer than 20 health events |
---|
469 | occurred over a time period, you may consider combining years, or using indirect age-adjustment.<br/><br/> |
---|
470 | |
---|
471 | The direct method can present problems when population sizes are particularly small. |
---|
472 | Calculating directly standardized rates requires calculating age-specific rates, |
---|
473 | and for small areas these age-specific rates may be based on only one or two events. In such |
---|
474 | cases, indirect standardization of rates may be used.<br/><br/> |
---|
475 | |
---|
476 | Indirectly standardized rates are based on the standard mortality or morbidity ratio (SMR) and the |
---|
477 | crude rate for a standard population. Indirect standardization adjusts the overall standard population |
---|
478 | death rate to the age distribution of the small area <a href="#Bib-5">(Lilienfeld & Stolley)</a>. It is technically |
---|
479 | appropriate to compare indirectly standardized rates only with the rate in the standard population, |
---|
480 | not with each other.<br/> |
---|
481 | <br/> |
---|
482 | <p align="right"><a href="#TOP">Back to Top</a></p> |
---|
483 | </CONTENT> |
---|
484 | </ibis:ExpandableContent> |
---|
485 | |
---|
486 | <ibis:ExpandableContent titleLevel="2"><HIDE/> |
---|
487 | <TITLE>Deciding Which Measure to Use</TITLE> |
---|
488 | <CONTENT> |
---|
489 | <br/> |
---|
490 | <!--h1>Deciding Which Measure to Use</h1--> |
---|
491 | The measure that best informs the question you are trying to answer is the one to use. |
---|
492 | This is a guideline, not a hard and fast rule, but generally: <br/><br/> |
---|
493 | <table class="Info"> |
---|
494 | <tr> |
---|
495 | <th width="100">If the question is:</th> |
---|
496 | <th width="100">Then use:</th> |
---|
497 | </tr> |
---|
498 | <tr> |
---|
499 | <td>MAGNITUDE: How big is the problem? </td> |
---|
500 | <td>Number of events (count)</td> |
---|
501 | </tr> |
---|
502 | <tr> |
---|
503 | <td>PROBABILITY: What is the underlying risk in a population? </td> |
---|
504 | <td>Crude rate and confidence interval</td> |
---|
505 | </tr> |
---|
506 | <tr> |
---|
507 | <td>DISPARITY: Is there a difference in risk after controlling for age?</td> |
---|
508 | <td>Age-adjusted rate and confidence interval</td> |
---|
509 | </tr> |
---|
510 | </table> |
---|
511 | <br/><br/> |
---|
512 | </CONTENT> |
---|
513 | </ibis:ExpandableContent> |
---|
514 | |
---|
515 | |
---|
516 | <p><hr/></p> |
---|
517 | <br/> |
---|
518 | <a name="Bib-1"></a>1. <a href="https://www.cdc.gov/nchs/data/nvsr/nvsr47/nvs47_03.pdf">Anderson RN, Rosenberg HM. |
---|
519 | Age Standardization of Death Rates: Implementation of the Year 2000 Standard.</a> National vital |
---|
520 | statistics reports; vol 47 no.3. Hyattsville, Maryland: National Center for Health Statistics. 1998.<br/><br/> |
---|
521 | |
---|
522 | <a name="Bib-2"></a>2. <a href="https://www.cdc.gov/nchs/data/statnt/statnt20.pdf">Klein RJ, Schoenborn CA. |
---|
523 | Age-Adjustment Using the 2000 Projected U.S. Population.</a> Healthy People Statistical Notes, no. 20. |
---|
524 | Hyattsville, Maryland: National Center for Health Statistics. January 2001.<br/><br/> |
---|
525 | |
---|
526 | <a name="Bib-3"></a>3. <a href="https://www.cdc.gov/nchs/data/statnt/statnt06rv.pdf">Curtin, LR, Klein, RJ. Direct |
---|
527 | Standardization (Age-Adjusted Death Rates).</a> Healthy People Statistical Notes, no. 6. Hyattsville, |
---|
528 | Maryland: National Center for Health Statistics. March 1995.<br/><br/> |
---|
529 | |
---|
530 | <a name="Bib-4"></a>4. <a href="http://www.wiley.com/WileyCDA/WileyTitle/productCd-0471526290.html">Fleiss, JL. |
---|
531 | Statistical methods for rates and proportions.</a> John Wiley and Sons, New York, 1973. As cited in Curtin |
---|
532 | and Klein, 1995.<br/><br/> |
---|
533 | |
---|
534 | <a name="Bib-5"></a>5. <a href="https://global.oup.com/academic/product/lilienfelds-foundations-of-epidemiology-9780195377675"> |
---|
535 | Lilienfeld, DE and Stolley, PD. Foundations of Epidemiology</a>, 3rd Ed. Oxford University Press, 1994. <br/><br/> |
---|
536 | </CONTENT> |
---|
537 | </HTML_CONTENT> |
---|