Estimating Methods
Under the estimating methods used in the CPS, all of the results for a given month become available simultaneously and are based on returns from the entire panel of respondents. The estimation procedure involves weighting the data from each sample person by the inverse of the probability of the person being in the sample. This gives a rough measure of the number of actual persons that the sample person represents. Since 1985, most sample persons within the same State have had the same probability of selection. Some selection probabilities may differ within a State due to the sample design or for operational reasons. Field subsampling, for example, which is carried out when areas selected for the sample are found to contain many more households than expected, may cause probabilities of selection to differ for some sample areas within a State. Through a series of estimation steps (outlined below), the selection probabilities are adjusted for noninterviews and survey undercoverage; data from previous months are incorporated into the estimates through the composite estimation procedure.
1. Noninterview adjustment. The weights for all interviewed households are adjusted to account for occupied sample households for which no information was obtained because of absence, impassable roads, refusals, or unavailability of the respondents for other reasons. This noninterview adjustment is made separately for clusters of similar sample areas that are usually, but not necessarily, contained within a State. Similarity of sample areas is based on Metropolitan Statistical Area (MSA) status and size. Within each cluster, there is a further breakdown by residence. Each MSA cluster is split by "central city" and "balance of the MSA." Each non-MSA cluster is split by "urban" and "rural" residence categories. The proportion of sample households not interviewed varies from 6 to 7 percent, depending on weather, vacation, etc.
2. Ratio estimates.> The distribution of the population selected for the sample may differ somewhat, by chance, from that of the population as a whole in such characteristics as age, race, sex, and State of residence. Because these characteristics are closely correlated with labor force participation and other principal measurements made from the sample, the survey estimates can be substantially improved when weighted appropriately by the known distribution of these population characteristics. This is accomplished through two stages of ratio adjustment, as follows:
a. First-stage ratio estimation. The purpose of the first-stage ratio adjustment is to reduce the contribution to variance that results from selecting a sample of PSU's rather than drawing sample households from every PSU in the Nation. This adjustment is made to the CPS weights in two race cells: Black and nonblack; it is applied only to PSU's that are not self-representing and for those States that have a substantial number of black households. The procedure corrects for differences that existed in each State cell at the time of the 1990 census between 1) the race distribution of the population in sample PSU's and 2) the race distribution of all PSU's (both 1 and 2 exclude self-representing PSU's).
b. Second-stage ratio estimation. This procedure substantially reduces the variability of estimates and corrects, to some extent, for CPS undercoverage. The CPS sample weights are adjusted to ensure that sample-based estimates of population match independent population controls. Three sets of controls are used:
1) 51 State controls of the civilian noninstitutional population 16 years of age and older.
2) National civilian noninstitutional population controls for 14 Hispanic and 5 non-Hispanic age-sex categories.
3) National civilian noninstitutional population controls for 66 white, 42 black, and 10 "other" age-sex categories.
The independent population controls are prepared by projecting forward the resident population as enumerated on April 1, 1990. The projections are derived by updating demographic census data with information from a variety of other data sources that account for births, deaths, and net migration. Estimated numbers of resident Armed Forces personnel and institutionalized persons reduce the resident population to the civilian noninstitutional population. Estimates of net census undercount, determined from the Post Enumeration Survey, are added to the population projections. Prior to January 1994, the projections were based on earlier censuses, and there was no correction for census undercount. A summary of the current procedures used to make population projections is given in "Revisions in the Current Population Survey Effective January 1994," appearing in the February 1994 issue of this publication.
3. Composite estimation procedure. The last step in the preparation of most CPS estimates makes use of a composite estimation procedure. The composite estimate consists of a weighted average of two factors: The two-stage ratio estimate based on the entire sample from the current month and the composite estimate for the previous month, plus an estimate of the month-to-month change based on the six rotation groups common to both months. In addition, a bias adjustment term is added to the weighted average to account for relative bias associated with month-in-sample estimates. This month-in-sample bias is exhibited by unemployment estimates for persons in their first and fifth months in the CPS being generally higher than estimates obtained for the other months.
The composite estimate results in a reduction in the sampling error beyond that which is achieved after the two stages of ratio adjustment. For some items, the reduction is substantial. The resultant gains in reliability are greatest in estimates of month-to-month change, although gains are also usually obtained for estimates of level in a given month, change from year to year, and change over other intervals of time.
Rounding of estimates
The sums of individual items may not always equal the totals shown in the same tables because of independent rounding of totals and components to the nearest thousand. Similarly, sums of percent distributions may not always equal 100 percent because of rounding. Differences, however, are insignificant.
Reliability of the estimates
There are two types of errors possible in an estimate based on a sample survey--sampling and nonsampling. The standard errors provided indicate primarily the magnitude of the sampling error. They also incorporate the effect of some nonsampling errors in response and enumeration but do not account for any systematic biases in the data. Nonsampling error. The full extent of nonsampling error is unknown, but special studies have been conducted to quantify some sources of nonsampling error in the CPS, as discussed below. The effect of nonsampling error should be small on estimates of relative change, such as month-to-month change. Estimates of monthly levels would be more severely affected by the nonsampling error. Nonsampling errors in surveys can be attributed to many sources, e.g., the inability to obtain information about all persons in the sample; differences in the interpretation of questions; inability or unwillingness of respondents to provide correct information; inability to recall information; errors made in collecting and processing the data; errors made in estimating values for missing data; and failure to represent all sample households and all persons within sample households (undercoverage). Nonsampling errors occurring in the interview phase of the survey are studied by means of a reinterview program. This program is used to estimate various sources of error as well as to evaluate and control the work of the interviewers. A random sample of each interviewer's work is inspected through reinterview at regular intervals. The results indicate, among other things, that the data published from the CPS are subject to moderate systematic biases. A description of the CPS reinterview program and some of the other results may be found in The Current Population Survey Reinterview Program, January 1961 through December 1966, Technical Paper No. 19, Bureau of the Census, U.S. Department of Commerce.
The effects of some components of nonsampling error in the CPS data can be examined as a result of the rotation plan used for the sample, since the level of the estimates varies by rotation group. A description of these effects appears in "The Effects of Rotation Group Bias on Estimates From Panel Surveys," by Barbara A. Bailar, Journal of the American Statistical Association, Volume 70, No. 349, March 1975.
Undercoverage in the CPS results from missed housing units and missed persons within sample households. The CPS covers about 92 percent of the decennial census population (adjusted for census undercount). It is known that the CPS undercoverage varies with age, sex, race, and Hispanic origin. Generally, undercoverage is larger for men than for women and larger for blacks, Hispanics, and other races than for whites. Ratio adjustment to independent age-sex-race-origin population controls, as described previously, partially corrects for the biases due to survey undercoverage. However, biases exist in the estimates to the extent that missed persons in missed households or missed persons in interviewed households have different characteristics than interviewed persons in the same age-sex-race-origin group.
Additional information on nonsampling error in the CPS appears in An Error Profile: Employment as Measured by the Current Population Survey, by Camilla Brooks and Barbara Bailar, Statistical Policy Working Paper 3, U.S. Department of Commerce, Office of Federal Statistical Policy and Standards; in "The Current Population Survey: An Overview," by Marvin Thompson and Gary Shapiro, Annals of Economic and Social Measurement, Vol. 2, April 1973; and in The Current Population Survey, Design and Methodology, Technical Paper No. 40, Bureau of the Census, U.S. Department of Commerce. This last document includes a comprehensive discussion of various sources of errors and describes attempts to measure them in the CPS.
Sampling error. When a sample rather than the entire population is surveyed, estimates differ from the true population values that they represent. This difference, or sampling error, occurs by chance, and its variability is measured by the standard error of the estimate. Sample estimates from a given survey design are unbiased when an average of the estimates from all possible samples would yield, hypothetically, the true population value. In this case, the sample estimate and its standard error can be used to construct approximate confidence intervals, or ranges of values, that include the true population value with known probabilities. If the process of selecting a sample from the population were repeated many times and an estimate and its standard error calculated for each sample, then:
1. Approximately 68 percent of the intervals from one standard error below the estimate to one standard error above the estimate would include the true population value.
2. Approximately 90 percent of the intervals from 1.6 standard errors below the estimate to 1.6 standard errors above the estimate would include the true population value.
3. Approximately 95 percent of the intervals from two standard errors below the estimate to two standard errors above the estimate would include the true population value.
Although the estimating methods used in the CPS do not produce unbiased estimates, biases for most estimates are believed to be small enough so that these confidence interval statements are approximately true.
Since it would be too costly to develop standard errors for all CPS estimates, generalized variance function techniques are used to calculate sets of standard errors for various types of labor force characteristics. It is important to keep in mind that standard errors computed from these methods reflect contributions from sampling errors and some kinds of nonsampling errors and indicate the general magnitude of an estimate's standard error rather than its precise value. The generalized variance functions and standard errors provided here are based on the sample design and estimation procedures as of 1987 and have been adjusted to reflect the population levels and sample size as of 1996. Standard errors for years prior to 1996 may be roughly approximated by adjusting, as follows, the standard errors presented here.
For the years 1967 through 1995, multiply the standard errors by 0.96.
For the years 1956 through 1966, multiply the standard errors by 1.17.
For years prior to 1956, multiply the standard errors by 1.44.
More accurate standard error estimates for historical CPS data may be found in previous issues of this publication.
Tables 1-B through 1-H are provided so that approximate standard errors of estimates can be easily obtained. These tables are briefly summarized here; details illustrating the proper use of each table follow.
Tables 1-B and 1-C show standard errors for estimated monthly levels and rates for selected employment status characteristics; these tables also provide standard errors for consecutive month-to-month changes in the estimates. These standard errors are based on levels of recent estimates and can be determined directly by finding the characteristic of interest.
Tables 1-D and 1-E show standard errors for monthly levels and consecutive monthly changes in levels for general employment status characteristics. The standard errors are calculated using linear interpolation based on the size of the monthly estimates.
Tables 1-F and 1-G give parameters that can be used with formulas to calculate a standard error on nearly any specified level, unemployment rate, percentage, or consecutive month-to-month change. For monthly levels and consecutive month-to-month changes in levels, tables 1-F and 1-G are preferred to tables 1-D and 1-E, since the formulas provide more accurate results than linear interpolation.
Table 1-H presents factors used to convert standard errors of monthly levels and rates determined from tables 1-B, 1-C, 1-D, and 1-F to standard errors pertaining to quarterly and yearly averages, consecutive year-to-year changes of monthly estimates, and changes in quarterly and yearly averages.
The standard errors for estimated changes from 1 month to the next, 1 year to the next, etc., depend more on the monthly levels for characteristics than on the size of the changes. Accordingly, tables 1-E, 1-G, and 1-H use monthly levels (not the magnitude of the changes) for approximating standard errors of change. Standard errors for estimated change between nonconsecutive months are not provided (except for year-to-year change); however, these may be assumed to be higher than the standard errors for consecutive monthly change.
Use of tables 1-B and 1-C. These tables provide a quick reference for standard errors of major characteristics. Table 1-B gives approximate standard errors for estimates of monthly levels and consecutive month-to-month changes in levels for major employment status categories.Table 1-C gives approximate standard errors for estimates of monthly unemployment rates and consecutive month-to-month changes in unemployment rates for some demographic, industrial, and occupational categories. For characteristics not given in tables 1-B and 1-C, refer to either tables 1-D and 1-E or tables 1-F and 1-G.
Illustration. Suppose that for a given month the number of women 20 years and over in the civilian labor force is estimated to be 54,000,000. For this characteristic, the approximate standard error of 219,000 is given in table 1-B in the row, "Total, 16 years and over: Women, 20 years and over: Civilian labor force." A 90-percent confidence interval as shown by these data, would then be the interval from 53,650,000 to 54,350,000. Concluding that the true labor force level lies within this interval would be correct for roughly 90 percent of all possible samples.
Use of tables 1-D and 1-E. From these tables, approximate standard errors can be calculated for estimates of monthly levels and month-to-month changes in levels for major labor force characteristics by race and Hispanic origin. For major categories not shown, such as male or female, tables 1-F and 1-G can be used. Standard errors for intermediate values not shown in the tables may be approximated by linear interpolation. For table 1-E, which applies to estimates of consecutive month-to-month change, the average of the two monthly levels (not the change) is used to select the appropriate row in the table.
Illustration. Assume that between 2 consecutive months the estimated number of employed persons changed from 115,600,000 to 116,700,000, an apparent increase of 1,100,000. The approximate standard error on this month-to-month change estimate is based on the average level of the estimate for the 2 months, 116,150,000. Using the table 1-E column titled "Labor force data other than agricultural employment and unemployment, Total," it is necessary to find the standard errors corresponding to the two monthly level entries between which the value 116,150,000 lies. The standard error corresponding to 100,000,000 is given as 274,000, and the standard error corresponding to 120,000,000 is given as 246,000. Use linear interpolation to find the approximate standard error on month-to-month change corresponding to the level 116,150,000; one method of calculation is given below. .
Thus, a 90-percent confidence interval for the true month-to-month change would be approximately the interval from 698,000 to 1,502,000.
Use of tables 1-F and 1-G. These tables can be used to find approximate standard errors for a wide range of estimated monthly levels, proportions, rates, and estimates of consecutive monthly change. Instead of displaying standard errors, these tables provide parameters to be used with the formulas given below that allow the user to calculate standard errors.
Table 1-G, which applies to estimates of consecutive monthly change, lists parameters for some characteristics classified by a measure of correlation between monthly estimates. Estimates of the number of persons employed full time, for example, change relatively little from one month to the next, and the two monthly estimates are said to be highly correlated. Consecutive monthly estimates of part-time employment, by contrast, have low correlation, since these estimates are relatively volatile.
Major characteristics for which consecutive monthly estimates are known to have high or low correlation are indicated in table 1-G. Not all categories in table 1-G, however, are broken down into low or high correlation characteristics. When high or low correlation is not specified in table 1-G, the parameters in table 1-G should be selected from the rows labeled "Most characteristics" or from rows not specifying correlation.
Standard errors of estimated levels. The approximate standard error, sx, of an estimated monthly level, x, can be obtained using the formula below, where a and b are the parameters from table 1-F associated with the particular characteristic. The same formula can be used to approximate the standard error of an estimated month-to-month change in level; simply average the levels for the 2 consecutive months and use the parameters from table 1-G.
Illustration. Assume that in a given month there are an estimated 6 million unemployed men in the civilian labor force (x = 6,000,000). Obtain the appropriate a and b parameters from table 1-F ("Unemployment: Total or white"). Use the formula to compute an approximate standard error on the estimate of 6,000,000.
a = -0.000017962 b = 2957.13
Suppose that in the next month the estimated number of unemployed men increases by 200,000 to 6,200,000. The average of the monthly levels is x = 6,100,000. Obtain the appropriate a and b parameters from table 1-G ("Unemployment: Total or white: Total, men, women"). Use the formula to compute an approximate standard error on the estimated change of 200,000.
a = -0.000093662 b = 4191.84
An approximate 90-percent confidence interval for the true month-to-month change would be the interval from -38,000 to 438,000. Because this interval covers zero, one cannot assert at this level of confidence that any real change has occurred in the unemployment level. This result can also be expressed by saying that the apparent change of 200,000 is not significant at a 90-percent confidence level.
Standard errors of estimated percentages and rates. Generally, percentages and rates are not published unless the monthly base (denominator) is greater than 75,000 persons, the quarterly average base is greater than 60,000 persons, or the annual average base is greater than 35,000 persons.
The reliability of an estimated percentage or rate depends upon the magnitude of the percentage or rate and its base. When the numerator and base are in different categories, use the parameters from table 1-F or 1-G relevant to the numerator. The approximate standard error, sy,p, of an estimated percentage or rate, p, can be obtained using the following formula, where y is the estimated number of persons in the base.
Illustration. For a given month, suppose that 5,600,000 women, 20 to 24 years of age, are estimated to be employed. Of this total, 1,800,000 or 32 percent are classified as part-time workers. To estimate the standard error on this percentage, proceed as follows. Obtain the parameter b = 2529.99 from table 1-F ("Labor force and not-in-labor-force data other than agricultural employment and unemployment: Total: Women"). Apply the formula to obtain:
Suppose that in the next month 5,700,000 women in this same age group are reported employed and that 1,950,000 or 34 percent are part-time workers. To estimate the standard error on the observed month-to-month change of 2 percentage points, first average the values for p and y over the 2 months to get p = 33 percent and y = 5,650,000. Next, obtain the parameter b = 2690.59 from table 1-G ("Labor force and not-in-labor-force data other than agricultural employment and unemployment: Total or white: Women: Low correlation characteristics") and apply the formula as follows.
It should be noted that the numerator of the percentage (part-time employed) determined the choice of correlation. If the example had illustrated percentages of women employed full time, the numerator would have been a high correlation characteristic. Table 1-G, however, does not explicitly list high correlation parameters for employed women; thus, the row labeled "Women: Most characteristics" would have been used.
Had the example dealt with teenage women employed part time, either of two rows in table 1-G could have been applied ("Women: Low correlation characteristics" or "Both sexes, 16 to 19 years"). In situations like this, where it is not clear which row applies, a general rule to follow is to choose the row with the largest b parameter. This gives a more conservative estimate of standard error.
Use of table 1-H. Use this table with table 1-B, 1-C, 1-D, or 1-F to calculate approximate standard errors for quarterly or yearly averages, changes in consecutive quarterly or yearly averages, and consecutive year-to-year changes in monthly estimates. Table 1-H gives factors that can be used to convert standard errors for monthly levels into standard errors for other time periods and changes over time. Follow these three basic steps:
Step 1. Average estimates appropriately. For quarterly estimates, average the 3 monthly estimates. For yearly estimates, average the 12 monthly estimates. For changes in consecutive averages, average over the 2 quarters or 2 years. For consecutive year-to-year changes in monthly estimates, average the 2 months involved.
Step 2. Obtain a standard error on a monthly estimate using table 1-B or 1-C, or apply the procedures for table 1-D or 1-F to the average calculated in step 1, as if the average were an estimate for a single month.
Step 3. Determine the standard error on the average or on the estimate of change. Multiply the result from step 2 by the appropriate factor from table 1-H.
Illustration. Suppose that standard errors are desired for a quarterly average of black employment levels and for the change in averages from 1 quarter to the next. For each successive month of the first quarter, suppose the levels are observed to be 11,500,000, 11,600,000, and 11,700,000.
Step 1. The quarterly average is 11,600,000.
Step 2. Obtain the a and b parameters from table 1-F ("Labor force and not-in-labor-force data other than agricultural employment and unemployment: Black"). Use the formula for sx to compute an approximate standard error for a monthly estimate of 11,600,000.
a = -0.000125300 b = 3139.26
Step 3. Multiply this result by the factor .87 from table 1-H (column labeled "Quarterly averages" and row labeled "Labor force and not-in-labor-force data other than agricultural employment and unemployment: Black"). This gives an approximate standard error of 122,000 on the quarterly average of 11,600,000.
Proceed to obtain the approximate standard error on the change in consecutive quarterly average estimates of black employment. Assume that black employment estimates for the months in the second quarter are observed to be 11,100,000, 11,200,000, and 11,300,000.
Step 1. The average for the second quarter is 11,200,000. The average of the 2 quarters is 11,400,000.
Step 2. Obtain the a and b parameters as above and use the formula for sx to compute an approximate standard error for the estimate of 11,400,000, treating it as an estimate for a single month.
Step 3. Multiply this result by the factor .84 from table 1-H (column labeled "Change in quarterly averages" and row labeled "Labor force and not-in-labor-force data other than agricultural employment and unemployment: Black"). This gives an approximate standard error of 118,000 on the estimated change of 400,000 from 1 quarter to the next.
The estimated change clearly exceeds 2 standard errors; therefore, one could conclude from these data that the change in quarterly averages is significant.
Table 1-B. Standard errors for major employment status categories
(In thousands)
____________________________________________________________________
| |
Category | Monthly | Consecutive-
| level | month change
________________________________________|____________|______________
| |
Total, 16 years and over: | |
Civilian labor force ............| 293 | 216
Employed ........................| 312 | 235
Unemployed ......................| 145 | 161
Men, 20 years and over: | |
Civilian labor force ............| 194 | 164
Employed ........................| 206 | 174
Unemployed ......................| 97 | 113
Women, 20 years and over: | |
Civilian labor force ............| 219 | 165
Employed ........................| 224 | 171
Unemployed ......................| 91 | 105
Both sexes, 16 to 19 years: | |
Civilian labor force ............| 97 | 95
Employed ........................| 96 | 95
Unemployed ......................| 62 | 81
Black, 16 years and over: | |
Civilian labor force ............| 138 | 101
Employed ........................| 140 | 105
Unemployed ......................| 66 | 76
Men, 20 years and over: | |
Civilian labor force ............| 78 | 69
Employed ........................| 81 | 72
Unemployed ......................| 43 | 50
Women, 20 years and over: | |
Civilian labor force ............| 98 | 73
Employed ........................| 97 | 74
Unemployed ......................| 44 | 51
Both sexes, 16 to 19 years: | |
Civilian labor force ............| 40 | 42
Employed ........................| 35 | 37
Unemployed ......................| 32 | 37
Hispanic origin, 16 years and over: | |
Civilian labor force ............| 130 | 91
Employed ........................| 134 | 107
Unemployed ......................| 63 | 73
________________________________________|____________|______________
Table 1-C. Standard errors for unemployment rates by major characteristics
___________________________________________________________________________
| |
Characteristic | Monthly | Consecutive-
| level | month change
___________________________________________|____________|__________________
| |
Total, 16 years and over ...............| 0.11 | 0.13
Men, 16 years and over ....................| .15 | .18
Men, 20 years and over ....................| .14 | .17
Women, 16 years and over ..................| .16 | .19
Women, 20 years and over ..................| .16 | .19
Both sexes, 16 to 19 years ................| .74 | .97
White workers .............................| .11 | .13
Black workers .............................| .45 | .53
Hispanic-origin workers ...................| .50 | .59
Married men, spouse present ...............| .15 | .18
Married women, spouse present .............| .18 | .22
Women who maintain families ...............| .54 | .64
| |
Occupation | |
| |
Executive, administrative, and managerial .| .20 | .24
Professional specialty ....................| .20 | .23
Technicians and related support ...........| .45 | .54
Sales .....................................| .30 | .36
Administrative support, including clerical.| .25 | .30
Private household .........................| 1.75 | 2.08
Protective service ........................| .67 | .80
Service, except private household and | |
protective service ......................| .38 | .45
Precision production, craft, and repair ...| .34 | .40
Machine operators, assemblers, and | |
inspectors ..............................| .49 | .58
Transportation and material moving ........| .55 | .66
Handlers, equipment cleaners, helpers, | |
and laborers ............................| .73 | .87
Farming, forestry, and fishing ............| .73 | .87
| |
Industry | |
| |
Nonagricultural private wage and salary | |
workers .................................| .13 | .15
Goods-producing industries ..............| .25 | .30
Mining ................................| 1.39 | 1.65
Construction ..........................| .68 | .81
Manufacturing .........................| .26 | .31
Durable goods .......................| .32 | .38
Nondurable goods ....................| .42 | .50
Service-producing industries ............| .15 | .18
Transportation, communications, and | |
public utilities ....................| .42 | .50
Wholesale and retail trade ............| .27 | .32
Finance and services ..................| .19 | .23
Government workers ........................| .21 | .25
Agricultural wage and salary workers ......| 1.18 | 1.40
___________________________________________|____________|__________________
Table 1-D. Standard errors for estimates of monthly levels
(In thousands)
________________________________________________________________________________________________________________
Characteristic
________________________________________________________________________________________________________________
| | |
| Agricultural | | Labor force data other than agricultural
| employment | Unemployment | employment and unemployment
|__________________|_____________________________|____________________________________________________
Estimated | | | | | | | | |
monthly | | | | | | | | | Hispanic origin
level | | | | | | | | |____________________________
| Total or | Black | Total or | Black | Hispanic | Total | White | Black | |
| white | | white | | origin | | | | | Civilian labor
| | | | | | | | | Employed | force or not
| | | | | | | | | | in labor force
_________ |__________|_______|__________|_______|__________|_______|_______|_______|____________|_______________
| | | | | | | | | |
50 .......| 12 | 13 | 12 | 13 | 13 | 12 | 12 | 13 | 14 | 14
100 ......| 18 | 18 | 17 | 18 | 19 | 17 | 17 | 18 | 20 | 20
500 ......| 41 | 39 | 38 | 39 | 42 | 39 | 39 | 39 | 44 | 44
1,000 ....| 62 | 55 | 54 | 54 | 59 | 54 | 54 | 55 | 61 | 61
2,000 ....| 96 | 76 | 76 | 74 | 82 | 77 | 77 | 76 | 83 | 83
4,000 ....| 157 | | 107 | 96 | 113 | 108 | 108 | 103 | 111 | 111
6,000 ....| 216 | | 131 | 106 | | 131 | 131 | 120 | 126 | 126
8,000 ....| 273 | | 150 | 108 | | 151 | 150 | 131 | 134 | 134
10,000 ...| 330 | | 167 | 101 | | 168 | 167 | 137 | 135 | 135
15,000 ...| | | 201 | | | 202 | 201 | 137 | 110 | 110
20,000 ...| | | 228 | | | 229 | 227 | 113 | |
30,000 ...| | | | | | 271 | 267 | | |
40,000 ...| | | | | | 302 | 296 | | |
50,000 ...| | | | | | 324 | 315 | | |
60,000 ...| | | | | | 340 | 327 | | |
70,000 ...| | | | | | 350 | 333 | | |
80,000 ...| | | | | | 354 | 333 | | |
100,000 ..| | | | | | 349 | 313 | | |
120,000 ..| | | | | | 322 | 264 | | |
140,000 ..| | | | | | 267 | 159 | | |
160,000 ..| | | | | | | | | |
180,000 ..| | | | | | | | | |
_________ |__________|_______|__________|_______|__________|_______|_______|_______|____________|_______________
Table 1-E. Standard errors for estimates of month-to-month change in levels
(In thousands)
________________________________________________________________________________________________________________
Characteristic
________________________________________________________________________________________________________________
| | |
| Agricultural | | Labor force data other than agricultural
| employment | Unemployment | employment and unemployment
|__________________|_____________________________|____________________________________________________
Estimated | | | | | | | | |
monthly | | | | | | | | | Hispanic origin
level | | | | | | | | |____________________________
| Total or | Black | Total or | Black | Hispanic | Total | White | Black | |
| white | | white | | origin | | | | | Civilian labor
| | | | | | | | | Employed | force or not
| | | | | | | | | | in labor force
_________ |__________|_______|__________|_______|__________|_______|_______|_______|____________|_______________
| | | | | | | | | |
50 .......| 14 | 12 | 14 | 15 | 16 | 10 | 10 | 10 | 12 | 10
100 ......| 19 | 17 | 20 | 21 | 22 | 14 | 14 | 15 | 17 | 14
500 ......| 43 | 37 | 46 | 46 | 50 | 32 | 32 | 32 | 37 | 31
1,000 ....| 59 | 52 | 64 | 63 | 69 | 45 | 45 | 45 | 51 | 43
2,000 ....| 78 | 72 | 89 | 84 | 95 | 63 | 63 | 62 | 70 | 59
4,000 ....| 95 | | 124 | 104 | 127 | 88 | 88 | 84 | 93 | 78
6,000 ....| 94 | | 148 | 106 | | 108 | 108 | 97 | 105 | 89
8,000 ....| 73 | | 166 | 92 | | 123 | 123 | 104 | 110 | 94
10,000 ...| | | 180 | 47 | | 137 | 137 | 108 | 110 | 95
15,000 ...| | | 204 | | | 165 | 165 | 100 | 79 | 76
20,000 ...| | | 215 | | | 187 | 187 | 58 | |
30,000 ...| | | | | | 221 | 221 | | |
40,000 ...| | | | | | 245 | 245 | | |
50,000 ...| | | | | | 262 | 262 | | |
60,000 ...| | | | | | 274 | 274 | | |
70,000 ...| | | | | | 281 | 281 | | |
80,000 ...| | | | | | 283 | 283 | | |
100,000 ..| | | | | | 274 | 274 | | |
120,000 ..| | | | | | 246 | 246 | | |
140,000 ..| | | | | | 188 | 188 | | |
160,000 ..| | | | | | | | | |
180,000 ..| | | | | | | | | |
_________ |__________|_______|__________|_______|__________|_______|_______|_______|____________|_______________
Table 1-F. Parameters for computation of standard errors for estimates of
monthly levels
___________________________________________________________________________
| |
Characteristic | a | b
_____________________________________________ |______________|_____________
| |
| |
Labor force and not-in-labor-force data other | |
than agricultural employment and | |
unemployment: | |
| |
Total 1 ....................................| -0.000017682 | 2985.26
Men 1.....................................| -0.000032770 | 2764.05
Women ....................................| -0.000029553 | 2529.99
Both sexes, 16 to 19 years ...............| -0.000171805 | 2544.62
| |
White 1...................................| -0.000020028 | 2984.72
Men 1 ..................................| -0.000036840 | 2766.67
Women ..................................| -0.000033710 | 2526.82
Both sexes, 16 to 19 years .............| -0.000204195 | 2549.88
| |
Black ....................................| -0.000125300 | 3139.26
Men ....................................| -0.000302096 | 2930.79
Women ..................................| -0.000182509 | 2637.41
Both sexes, 16 to 19 years .............| -0.001294516 | 2949.48
| |
Hispanic origin ..........................| -0.000206380 | 3895.71
| |
| |
Not in labor force, total or white, | |
excluding women and 16-to-19 year olds ...| 0.000005931 | 828.79
| |
| |
Agricultural employment: | |
| |
Total or white .............................| 0.000782035 | 3048.57
Men ......................................| 0.000858136 | 2825.09
Women or both sexes, 16 to 19 years ......| -0.000024885 | 2582.39
| |
Black ......................................| -0.000134884 | 3154.76
| |
Hispanic origin: | |
Total or women ...........................| 0.011857446 | 2894.85
Men or both sexes, 16 to 19 years ........| 0.015736341 | 1702.50
| |
| |
Unemployment: | |
| |
Total or white .............................| -0.000017962 | 2957.13
Black ......................................| -0.000212109 | 3149.77
Hispanic origin ............................| -0.000101820 | 3576.47
______________________________________________|______________|_ ___________
1 Excludes not-in-labor-force data.
Table 1-G. Parameters for computation of standard errors for estimates of
month-to-month change in levels
_______________________________________________________________________________
| |
Characteristic | a | b
_________________________________________________|______________|______________
| |
| |
Labor force and not-in-labor-force data other | |
than agricultural employment and unemployment: | |
| |
Total or white: | |
Most characteristics ........................| -0.000012482 | 2001.12
High correlation characteristics1 ...........| -0.000009288 | 1564.84
Low correlation characteristics1 ............| -0.000016162 | 2550.56
| |
Men: | |
Most characteristics ......................| -0.000022599 | 1921.13
High correlation characteristics ..........| -0.000016814 | 1500.99
Low correlation characteristics ...........| -0.000058387 | 2668.56
| |
Women: | |
Most characteristics ......................| -0.000021229 | 1689.99
Low correlation characteristics ...........| -0.000059785 | 2690.59
| |
Both sexes, 16 to 19 years ..................| -0.000186555 | 2616.54
| |
Black: | |
Most characteristics ........................| -0.000098960 | 2147.36
Low correlation characteristics .............| -0.001928030 | 6513.82
| |
Men: | |
Most characteristics ......................| -0.000234427 | 2280.03
Low correlation characteristics ...........| -0.002881467 | 5829.60
| |
Women: | |
Most characteristics ......................| -0.000156363 | 1860.78
Low correlation characteristics ...........| -0.002311407 | 5420.13
| |
Both sexes, 16 to 19 years .......... .......| -0.001288452 | 3131.77
| |
Hispanic origin: | |
Total .......................................| -0.000157201 | 2774.53
Civilian labor force and not in labor force .| -0.000102898 | 1930.51
Low correlation characteristics .............| -0.002624078 | 8620.43
Men, civilian labor force and not in labor | |
force .....................................| -0.000248038 | 2347.42
Men, 16 years and over; 20 years and over; | |
and both sexes, 16 to 19 years ............| -0.000398909 | 3615.62
Women, 16 years and over and 20 years and | |
over ......................................| -0.000338741 | 2569.69
Table 1-G. Parameters for computation of standard errors for estimates of
month-to-month change in levels--Continued
_______________________________________________________________________________
| |
Characteristic | a | b
_________________________________________________|______________|______________
| |
| |
Agricultural employment: | |
| |
Total or white: | |
Total .......................................| -0.000395757 | 3838.04
Men .........................................| -0.000672985 | 3959.25
Women or both sexes, 16 to 19 years .........| 0.000130289 | 2367.00
| |
Black: | |
Total or women ..............................| -0.000122355 | 2861.72
Men or both sexes, 16 to 19 years ...........| -0.019110769 | 5876.77
| |
Hispanic origin: | |
Total or women ..............................| 0.002872129 | 4640.81
Men or both sexes, 16 to 19 years ...........| 0.002884390 | 4028.10
| |
Self-employed .................................| -0.000245791 | 2091.57
| |
Unemployment: 2 | |
| |
Total or white: | |
Total, men, women ...........................| -0.000093662 | 4191.84
Both sexes, 16 to 19 years and low | |
correlation characteristics ...............| -0.000071624 | 5121.75
| |
Black: | |
Total, men, women, and both sexes, | |
16 to 19 years ............................| -0.000414217 | 4361.16
High correlation characteristics ............| 0.000048170 | 3088.91
| |
Hispanic origin: | |
Total, men, women ...........................| -0.000252897 | 5054.25
Both sexes, 16 to 19 years and low | |
correlation characteristics ...............| -0.000996431 | 7037.75
| |
_________________________________________________|______________|______________
1 High correlation characteristics include employed full-time, manufacturing, service workers, and
not in the labor force. Low correlation characteristics include all part-time workers; employed,
with a job, but not at work; unpaid family workers; and precision production, craft, and
repair occupations.
2 High correlation characteristics include full-time jobseekers; job losers; manufacturing workers;
and operators, fabricators, and laborers. Low correlation characteristics include part-time
jobseekers, reentrants, persons unemployed for less than 5 weeks and from 5 to 14 weeks.
Table 1-H. Factors to be used with tables 1-B, 1-C, 1-D, and 1-F to compute the approximate standard errors for levels, rates, and percentages for year-to-yea
________________________________________________________________________________________________
|
| Factor
|________________________________________________________________
Characteristic | | | | |
| Year-to-year | | Change in | | Change in
|change of monthly| Quarterly | quarterly | Yearly | yearly
| estimate | averages | averages | averages | averages
_______________________________|_________________|___________|___________|__________|___________
| | | | |
Agricultural employment: | | | | |
| | | | |
Total or men ................| 1.30 | 0.92 | 0.70 | 0.79 | 0.70
Women .......................| 1.30 | .82 | .84 | .57 | .70
Both sexes, 16 to 19 years ..| 1.30 | .78 | .88 | .49 | .70
Part time ...................| 1.40 | .80 | .80 | .59 | .70
| | | | |
Unemployment: | | | | |
| | | | |
Total .......................| 1.40 | .74 | .88 | .46 | .65
Part time ...................| 1.40 | .67 | .88 | .42 | .54
| | | | |
Labor force and not-in-labor- | | | | |
force data other than agri- | | | | |
cultural employment and | | | | |
unemployment: | | | | |
| | | | |
Total or white ..............| 1.30 | .87 | .85 | .65 | .70
Black .......................| 1.30 | .87 | .84 | .65 | .70
Hispanic origin .............| 1.30 | .87 | .80 | .65 | .70
Both sexes, 16 to 19 years ..| 1.30 | .79 | .88 | .54 | .70
Part time ...................| 1.40 | .82 | .90 | .51 | .60
_______________________________|_________________|___________|___________|__________|___________
CPS Publications - Employment and Earnings (publication) Articles/Explanatory Notes Page
CPS Main Page