Direct age-adjustment (or age standardization) is the same as calculating a weighted average. It weights the age-specific rates observed in a population of interest by the proportion of each age group in a standard population (Lilienfeld & Stolley).

In 1999, the Centers for Disease Control and Prevention (CDC) replaced the 1940 U.S. standard population weights that had been used for the several previous decades with revised standard population weights for direct age-adjustment (Klein & Schoenborn). Tables 1 and 2, in the next section below, contain the CDC standard population weights, which represent the proportion of the U.S. 2000 projected population in each age group, and sum to 1.0.

  Compare only age-adjusted rates that have been adjusted to the same standard population. For instance, don't compare rates age-adjusted using the U.S. 1940 standard population with rates that were age-adjusted using the U.S. 2000 population.

  Unless otherwise noted, all age-adjusted rates in NJSHAD have been adjusted using the US 2000 population standard.

  Age-adjusted rates should be viewed as relative indexes, and used for comparison of populations. They are not actual measures of mortality risk, and do not convey the magnitude of the problem.

Table 1. Age-Adjusted Weights for U.S. 2000 Standard Population (11 Age Groups)

Group #	Age Group	U.S. 2000 Population Projection (in thousands)	Weight
1	Under 1 Year	3,795	0.013818
2	1 - 4 Years	15,192	0.055317
3	5 - 14 Years	39,977	0.145565
4	15 - 24 Years	38,077	0.138646
5	25 - 34 Years	37,233	0.135573
6	35 - 44 Years	44,659	0.162613
7	45 - 54 Years	37,030	0.134834
8	55 - 64 Years	23,961	0.087247
9	65 - 74 Years	18,136	0.066037
10	75 - 84 Years	12,315	0.044842
11	85 Years and Over	4,259	0.015508
	All Ages	274,634	1.000000

Population estimates for municipalities are not available separately for Under 1 Year and 1-4 Years, so they are combined into an Under 5 Years age group when calculating age-adjusted death rates.

Table 2. Age-Adjusted Weights for U.S. 2000 Standard Population (10 Age Groups)

Group #	Age Group	U.S. 2000 Population Projection (in thousands)	Weight
1	Under 5 Years	18,987	0.069135
2	5 - 14 Years	39,977	0.145565
3	15 - 24 Years	38,077	0.138646
4	25 - 34 Years	37,233	0.135573
5	35 - 44 Years	44,659	0.162613
6	45 - 54 Years	37,030	0.134834
7	55 - 64 Years	23,961	0.087247
8	65 - 74 Years	18,136	0.066037
9	75 - 84 Years	12,315	0.044842
10	85 Years and Over	4,259	0.015508
	All Ages	274,634	1.000000

The National Cancer Institute's Surveillance, Epidemiology, and End Results (SEER) Program uses the 2000 U.S. Standard Population with 19 age groups for age-adjustment of cancer rates.

Other age groupings and weights are used when survey data are limited to certain age groups, such as cancer screenings, shingles vaccination, or falls. Those weights, as well more information about age adjustment in general, are available in the National Center for Health Statistics' Age Adjustment Using the 2000 Projected U.S. Population Statistical Note.

To apply direct age-adjustment to a set of rates, the age-specific rate for each age group in the study population is multiplied by the appropriate weight in the standard population. The sum of these products is the directly age-adjusted, or age-standardized, rate. The age-adjusted rate can be considered an average of each of the individual age-specific rates, but rather than being a simple average, it is a weighted average with each age-specific rate weighted by the proportion of people in the same age group in the standard population.

Tables 3a. and 3b. demonstrate the method used by NJSHAD to calculate age-adjusted rates. Notice that using crude death rates in Tables 3a. and 3b., one might conclude that whites have a higher underlying risk for heart disease death compared with blacks. However, the white population has a higher proportion of older persons and older persons are more likely to die due to heart disease than younger persons. Applying the standard population weights, gives older persons less weight in the calculation of age-adjusted rate, which ultimately shows that the risk is greater for the black population.

Table 3a. Age-Adjusted Death Rate due to Heart Disease among Whites, New Jersey, 2004

Age Group (years)	Number of Deaths in 2004	2004 Population Estimates1	Age-Specific Rate2	U.S. 2000 Standard Population Weight	Cross Products3
Under 5	4	307,139	1.30	0.069135	0.090037
5 - 14	3	709,758	0.42	0.145565	0.061527
15 - 24	15	634,256	2.36	0.138646	0.327894
25 - 34	35	576,010	6.08	0.135573	0.823780
35 - 44	169	883,005	19.14	0.162613	3.112281
45 - 54	542	886,502	61.14	0.134834	8.243639
55 - 64	1,126	647,215	173.98	0.087247	15.178901
65 - 74	2,109	411,158	512.94	0.066037	33.873118
75 - 84	5,679	353,102	1,608.32	0.044842	72.120157
85 +	7,621	141,128	5,400.06	0.015508	83.744167
All Ages	17,305	5,549,273	311.8*	1	217.6†

Table 3b. Age-Adjusted Death Rate due to Heart Disease among Blacks, New Jersey, 2004

Age Group (years)	Number of Deaths in 2004	2004 Population Estimates1	Age-Specific Rate2	U.S. 2000 Standard Population Weight	Cross Products3
Under 5	3	91,279	3.29	0.069135	0.227221
5 - 14	2	188,782	1.06	0.145565	0.154215
15 - 24	8	178,727	4.48	0.138646	0.620593
25 - 34	24	159,695	15.03	0.135573	2.037479
35 - 44	84	186,190	45.12	0.162613	7.336319
45 - 54	205	149,037	137.55	0.134834	18.546381
55 - 64	309	98,175	314.74	0.087247	27.460477
65 - 74	470	58,583	802.28	0.066037	52.980199
75 - 84	609	32,097	1,897.37	0.044842	85.082026
85 +	3	1,584	189.45	0.015508	2.938097
All Ages	2,152	1,153,392	186.6*	1	256.5†

Notes:
1. Source: New Jersey Department of Labor and Workforce Development, State Data Center
2. Rate per 100,000 = (Age-specific death count/Age-specific population estimate)* 100,000
3. Age-specific death rate * US 2000 Standard Population Weight
* Crude death rate
† Age-adjusted rate

Age adjustment is not appropriate if the age-specific death rates in the population of interest do not have a consistent relationship. For example, if the death rate among younger persons is increasing over time, but the death rate among older persons is decreasing over time, one would not want to age-adjust rates across years. One's conclusion of the trend in this death rate would be different, depending on which standard population is used. A younger standard population (such as the US 1940) would show an increase, whereas an older standard population (such as the US 2000) would show a decrease, or no change at all. Care should be taken so that the selection of the standard population does not affect the comparisons. For more information, see Curtin & Klein.

When reporting age-adjusted rates, always report the standard population used, and when comparing results to other data, be sure to document that those data were also age-adjusted and report the standard population. The age-adjusted rate is hypothetical, and is useful only for comparing populations, either over time, by geographic area, by sex or by racial/ethnic subgroups.

  Although age-adjustment may be used with broad population age groups, such as adults (e.g., age 18+), it is not necessary (or meaningful) to age-adjust data for smaller age groups (e.g., age 18-24).

Population Year

Q: Do I use the 2000 Decennial Census for age adjustment?
A: No. Use population estimates that match the same year as your health data. The "2000 standard population" is merely the standard set of weights used and is based on population projections for 2000 as of 1998.

Event Rates for a Subpopulation

Q: I am looking at death rates for female breast cancer. Which standard population should I use, females in US 2000 or all persons?
A: Theoretically, it doesn't matter, as long as you use the same standard population for all your analyses. But, as of 1999, the recommended standard population is the U.S. 2000 standard population, even for analyses that apply only to a particular sex, race, or other subgroup.

When NOT to Age-Adjust

Q: Are there times I should NOT age-adjust?
A: Yes. Do NOT use age-adjustment when...

Age Subpopulations

Q: I am looking at adults, only. If I use the weights in Table 1, above, they will not sum to one. Is that okay?
A: No. The weights must always sum to one. Weights for certain age subgroups have been published by the CDC. But you may also recompute the proportions in Table 1, using only the age range that is relevant to your analysis.

Age/Sex Adjusted Rates

Q: I have a report that uses age AND SEX adjusted rates. What is this, and why doesn't NJSHAD produce age and sex adjusted rates?
A: It is sometimes appropriate to adjust by other variables besides age. Rates that have been adjusted by age and sex use age- and sex-specific rates, weighted by twice the number of weights (one set for males and one set for females), but the total of all the weights still must sum to 1.0. NJSHAD doesn't compute these rates because there is little demand for it.

Confidence Intervals for Age-Adjusted Rates

Q: Can I use the confidence interval for the crude rate with the age-adjusted rate?
A: No, a new confidence interval for the age-adjusted rate must be calculated. Methods for calculation of this confidence interval may be found in Curtin & Klein.

In some cases, such as when there are too few cases to stratify by age, "indirect age standardization" may be used. Indirect standardization is based on standard mortality and morbidity ratios (SMR), and adjusts the age-specific rates found in the standard population to the age distribution of the smaller area or sub-population. According to Curtin & Klein, "One of the problems with [direct age adjustment] is that rates based on small numbers of deaths will exhibit a large amount of random variation. A very rough guideline is that there should be at least 25 total deaths over all age groups." NJSHAD follows NCHS's guideline of 20 total deaths. When fewer than 20 health events occurred over a time period, you may consider combining years, or using indirect age-adjustment.

The direct method can present problems when population sizes are particularly small. Calculating directly standardized rates requires calculating age-specific rates, and for small areas these age-specific rates may be based on only one or two events. In such cases, indirect standardization of rates may be used.

Indirectly standardized rates are based on the standard mortality or morbidity ratio (SMR) and the crude rate for a standard population. Indirect standardization adjusts the overall standard population death rate to the age distribution of the small area (Lilienfeld & Stolley). It is technically appropriate to compare indirectly standardized rates only with the rate in the standard population, not with each other.

The measure that best informs the question you are trying to answer is the one to use. This is a guideline, not a hard and fast rule, but generally:

If the question is:	Then use:
MAGNITUDE: How big is the problem?	Number of events (count)
PROBABILITY: What is the underlying risk in a population?	Crude rate and confidence interval
DISPARITY: Is there a difference in risk after controlling for age?	Age-adjusted rate and confidence interval