National Household Education Survey, 2005 (ICPSR 4599)

Version Date: Mar 13, 2007 View help for published

Principal Investigator(s): View help for Principal Investigator(s)
United States Department of Education. National Center for Education Statistics


Version V1

The National Household Education Survey (NHES) reports on the condition of education in the United States by collecting data at the household level rather than using a traditional, school-based data collection system. The surveys attempt to address many current issues in education, such as preprimary education, school safety and discipline, adult education, and activities related to citizenship.

This survey included three topical survey components.

  • The Early Childhood Program Participation Survey addressed the nonparental care and program participation of preschool children, that is, children from birth through age six and not yet enrolled in kindergarten or higher grades. The survey collected information on all of the child's current, regular care arrangements, such as care by a relative or by someone not related to the child, in a private home as well as at a day care center or preschool, including Head Start. Information was collected about the number of hours per week or per month that the child received nonparental care, as well as parental perceptions of the factors associated with choosing such care. Other information was collected on topics such as educational activities at home, emerging literacy and numeracy, the child's characteristics (including health and disability status), and parent/guardian and household characteristics. Interviews were completed with parents of 7,209 preschool children.

  • The After-School Programs and Activities Survey focused on children enrolled in kindergarten through eighth grade who were aged 15 years or younger. Parents reported on the after-school arrangements in which their children participated, including care by relatives or nonrelatives in a private home, after-school programs in schools or centers, activities that might provide adult supervision in the after-school hours, and children's self-care. Other information includes reasons for choosing parental care, the child's characteristics (including health and disability status), and parent/guardian and household characteristics. Interviews were conducted with the parents of 11,684 students.

  • The Adult Education Survey measured participation in the following types of formal educational activities: English as a Second Language (ESL), basic skills and General Education Development (GED) preparation courses, college or university degree or certificate programs, vocational or technical diploma programs, apprenticeship programs, courses or training for work-related reasons, and personal-interest classes or courses. In addition, information was collected on participation in informal learning activities for personal interest. The survey also gathered information on employer support for educational activities. Detailed information about educational attainment, employment, and household characteristics was also collected from both participants and nonparticipants. Adults aged 16 and older who were not enrolled in twelfth grade or below, who were noninstitutionalized, and who were not serving on active military duty were eligible for this survey. Interviews were completed with 8,904 respondents, 4,732 of whom had participated in formal educational activities in the past year and 4,172 of whom had not.

United States Department of Education. National Center for Education Statistics. National Household Education Survey, 2005. [distributor], 2007-03-13.

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote
2005-01 -- 2005-04

National sample of households.

National sample of household members in the United States.

Early Childhood Program Participation: Parents of infants, toddlers, or preschoolers.

After-School Programs and Activities: Parents of children in kindergarten through eighth grade.

Adult Education: Adult respondents.

The overall unit response rates for the Screener, the ECPP Survey, the ASPA Survey, and the AE Survey are 66.9 percent, 56.4 percent, 56.3 percent, and 47.6 percent, respectively.



2018-02-15 The citation of this study may have changed due to the new version control system that has been implemented. The previous citation was:
  • U.S. Dept. of Education, National Center for Education Statistics. NATIONAL HOUSEHOLD EDUCATION SURVEY, 2005. ICPSR04599-v1. Washington, DC: U.S. Dept. of Education, Institute of Education Sciences [producer], 2006. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2007-03-13.

Since no data intended for analysis were collected at the household level only, household-level weights were calculated solely for use as a basis for computing person-level weights for the analysis of the extended interview data.

Weights for Early Childhood Program Participation (ECPP) and After-School Programs and Activities (ASPA) Data

The same methodology was used for creating person-level weights for the ECPP data as for the ASPA data. The first step in developing the person weights for the ECPP and ASPA surveys was to account for the probability of sampling the child's domain in the given household. The second adjustment accounted for the probability of sampling the child from among all eligible children in the given domain. The application of these two adjustments to the household weight created a person-level base weight for the ECPP and the ASPA interviews.

The next step involved adjusting the person-level base weight for nonresponse to the ECPP or ASPA interviews. Nonresponse adjustment cells were created using age/grade combinations: children aged 0, children aged 1, children aged 2, unenrolled children aged 3 through 6, preschoolers, kindergartners, and children enrolled in each single grade for first grade through eighth grade. Enrolled children with no grade equivalent were included in the cell containing the modal grade for their age, that is, they were assigned to the grade in which most children their age are enrolled. For each cell, the ratio of the weighted number of eligible sampled children to the weighted number of responding children was then computed. This ratio was multiplied by the person-level base weight to create the nonresponse-adjusted, person-level ECPP and ASPA interview weight.

The final stage of weighting for the ECPP and ASPA data was a raking adjustment. The raking procedure is carried out in a sequence of adjustments. First, the weights are adjusted to sum to the totals on one marginal distribution (or dimension) and then the adjusted weights are further adjusted to sum to the totals on the second marginal distribution, and so on. One sequence of adjustments to the marginal distributions is known as a cycle or iteration. The procedure is repeated until convergence of weighted totals is achieved.

Weights for Adult Education (AE) Data

Four adjustments were made to the household-level weight to compute the person-level weight for the AE data. The first adjustment accounted for the probability of sampling adults in the household. The second adjustment was used to account for the probability of selecting the adult from among all adults in the household in the sampled educational attainment by participation domain (e.g., adult education participants with less than a high school diploma). The application of these two adjustments to the household weight created a person-level base weight for the AE data.

The third adjustment for the AE interview person-level weights was the nonresponse adjustment. The nonresponse-adjusted weight was adjusted in the final step to national totals using a raking procedure. The control totals for raking the AE weights were obtained from the March 2004 Current Population Survey (CPS). The four dimensions for the raking cells were (1) a cross of the adult's race/ethnicity (Black/non-Hispanic alone/Hispanic/other) and household income ($10,000 or less/$10,001-$25,000/$25,001 or more), (2) a cross of age (16-29 years/30-49 years/50 years or more) and sex, (3) a cross of Census region (Northeast/Midwest/South/West) and urbanicity (urban/rural), and (4) a cross of home tenure (rent/own or other) and highest educational attainment (less than high school diploma/high school diploma or equivalent/some college). These raking dimensions were used because they include important analysis variables (e.g., educational attainment) and characteristics that have been shown to be associated with telephone coverage (e.g., race/ethnicity).



  • The public-use data files in this collection are available for access by the general public. Access does not require affiliation with an ICPSR member institution.

CFDA logo

This study is maintained and distributed by the Child and Family Data Archive (CFData). CFData hosts datasets about young children, their families and communities, and the programs that serve them. CFData is supported by Office of Planning, Research and Evaluation (OPRE), an office of the Administration for Children and Families (ACF) in the U.S. Department of Health and Human Services.