Chapter 7 -- The Public-Use Microdata Sample (PUMS)

Last Modified 17 August 1998

Of the various census tabulations, the PUMS data set provides the most detail albeit with a coarser geographic filter. Because the PUMS data set contains a five-percent sample of housing units and persons in those housing units, it is possible to create customized tabulations that control for age, gender, income, and other factors that may influence the relationships between variables. Because data are at the individual level, it is possible to examine household relationships such as intermarriage and identified race of children of mixed-race parents as well characteristics of housing units such as year of construction or housing type occupied by specific racial groups. PUMS data, for example, could be used to explore the issue of income equity. Various minorities and women have asserted that they do not receive the same incomes as white men even when education, age, gender, and occupation are controlled. Using PUMS, all these factors could be controlled to see if indeed women or minorities are paid equitably.

A. Income Distribution Differences Among Ethnic Groups

The table below presents the income frequency distribution of households by race and income category within PUMA 5200 (Burbank and San Fernando). It is a cross-tabulation of selected race categories by defined income categories. The data are for households whose heads are civilian-employed persons aged 16 and over. Several groups are identified: non-Hispanic whites; blacks; Indians including Aleuts and Eskimos; Chinese and Taiwanese; Filipinos; Japanese; Asian Indians; and Koreans. Each cell contains the number of households, the column percentage, and the row percentage. The number of households has been inflated from the 5 percent sample so as to estimate the full number of households in each cell.

Table 16 shows the distribution of income among households of each of the race groups in terms of the percentage of households in each of the income categories. Of the two percentages shown in each cell, the lower one shows the percentage of the ethnic households in each income category. The advantage of an income distribution like this over an average measure (median or mean) is that groups may have important patterns that are not captured by a single figure. Graphing these distributions would make the different patterns stand out even more. Although in this case sampling error may be a problem, the table indicates American Indians, Chinese, Filipinos, and Japanese are all at least as well represented in the over $100,000 income households as are whites.

At the other extreme, notice that over half the black households have incomes of less than $25,000 - a much higher proportion than any other group shown. Indians, Chinese, Japanese have bi-modal distributions, which suggests that there may be two distinctive sets of households in two different social classes. In general, note the the very wide range of income distributions among white and Asian groups.


Table 16. Income Distribution within Ethnic Groups

Chapter 7 -- The Public-Use Microdata Sample (PUMS)

B. Occupational Differences Among Ethnic Groups

In this second PUMS example a selected set of occupations have been defined. The number of males and females of ethnic groups in each of the occupations has been tabulated. Do certain ethnic groups tend to predominate in certain types of occupations? The table shows the percent of all ethnic persons employed in each occupation. This proportion could further be compared to the proportion of all persons employed within the occupation to see if the ethnic group is overrepresented or underrepresented within that particular occupation.

For this particular Burbank-San Fernando PUMA, Japanese males are especially well represented as executives and post office workers. Chinese men are prominent in executive jobs and in food preparation and food services. Salvadoran men work as food preparers, in construction, and as laborers (helpers). Korean men are prominent in sales, construction and medical operations while Mexican men are overrepresented in the health services, machine operations, and as helpers. Mexican men living in this PUMA are more likely to be executives, administrators, or managers than are white men. This finding is not consistent with the results for the County as a whole. What do you think may be some reasons for this anomaly?

Among women Chinese are well represented in the category of executives, administrators, or managers and as laborers. Like male Japanese, Japanese women also are prominent in the former category. Cuban women are strongly represented as teachers and in technical sales. Black women are particularly strong in professional services, the post office, and health services. Filipino women are prominent in professional occupations and Mexican and Salvadoran women predominate as machine operators.

Table 17. Ethnic Employment for Males and Females in PUMA 5200

Chapter 7 -- The Public-Use Microdata Sample (PUMS)