APPENDIX F
Special Case: Estimates for Puerto Rico
Puerto Rico is included in the Title I fund allocations. Since the commonwealth has no administrative subdivisions, the Department of Education treats it as a single unit (equivalent to a U.S. county) for the allocation of these funds. In order to incorporate Puerto Rico in the fiscal 1997 fund allocation, estimates of its number and proportion of related children aged 5–17 living in poverty are needed for 1993.
If the fiscal 1997 allocations were based on 1990 census estimates (which the panel does not recommend), the estimates for Puerto Rico could be obtained straightforwardly from the commonwealth's 1990 decennial census. From that census it is estimated that Puerto Rico had about 558,000 poor related children aged 5–17 in 1989, 66.4 percent of all related children in this age range. However, the panel recommends that the fiscal 1997 allocations be based in part on estimates of the number and proportion of school-age children in poverty in 1993, and it is not straightforward to develop such estimates for Puerto Rico. The Puerto Rico Bureau of Labor Statistics conducts a periodic labor force survey, but that survey does not collect CPS-type income information on a regular basis. In addition, the specific model-based estimation procedures developed by the Census Bureau for U.S. states and counties cannot be applied to Puerto Rico since they are based on tax return and food stamp participation data for which there are no precise equivalents for Puerto Rico.
The only data source that appears to be available for updating estimates of poor school-age children in Puerto Rico is an experimental March 1995 income survey modeled after the CPS March Income Supplement.1 The Census Bureau
has based its 1993 estimates of poor school-age children on data from this survey, together with data for Puerto Rico from the decennial census and updated population estimates.
The derivation of the estimates of poor school-age children in Puerto Rico in 1993 from these data sources required a number of adjustments, for several reasons: (1) the March 1995 experimental survey did not collect information on the ages of family members under 18 (so that related children aged 5–17 could not be identified among those aged under 18); (2) the updated Puerto Rico population estimates are for all children in the resident population, not for related children only; and (3) the survey, which was conducted in 1995, obtained information on 1994 income, not 1993 income. In making the adjustments, the Census Bureau assumed that certain relationships observed in 1990 census data still applied and that the change in the number of Puerto Rico school-age children in poverty between 1989 and 1994 was linear.
The panel does not have any data with which to test the validity of these assumptions. It has only limited information about the sample design, sampling and nonsampling errors, response rates, and other features of the experimental survey. The sample size of about 3,200 households should be large enough to provide a direct estimate of the number of poor school-age children with adequate precision. However, only limited information is available about other key aspects of data quality, including response rates for households to the income questions and the editing or imputation procedures used.2
The approach adopted by the Census Bureau for producing updated estimates of poor school-age children in Puerto Rico seems appropriate, given the data available. However, at this time the panel is unable to make a firm recommendation on how estimates of the number and proportion of children in poverty in 1993 in Puerto Rico should be made. If, on further examination, the assumptions seem reasonable and the data quality appears adequate, the panel would endorse the Census Bureau's approach. Under those conditions, the panel would then recommend that the Census Bureau's proposed estimates for Puerto Rico be treated as equivalent to 1993 U.S. county estimates in determining the fiscal 1997 Title I allocations, as discussed in Section 5 of the report.