Using Multilevel Modeling to Investigate Predictors of Literacy in theNational Adult Literacy Survey.
Recent advances in statistical methodology and computing power have mademore sophisticated data analytic tools such as hierarchical linear modeling (HLM) readilyavailable. This methodological tool is well suited for research using national databasessince (a) they often involve very large sample sizes and (b) complex sampling designs areoften used. The intent of this study was to investigate the use of these tools, with anemphasis on HLM, for use in investigating substantive problems of interest in the National Adult Literacy Survey (NALS).The
(Kirsch et al., 1993) is the most recent and comprehensive surveyconducted of American adults’ literacy skills and practices. The NALS
gathered on a nationally representative sample of 26,091 adults, ages 16 and older between January and August, 1992. The sampling design for the NALS survey is amultistage cluster sample in which counties or groups of counties, i.e., probabilitysampling units (PSUs), are first randomly selected. From the PSUs census blocks or groups of census blocks, i.e., segments, are randomly selected. At this stage, segmentsthat were identified as high minority were over-sampled in order to ensure reliableestimates of Blacks’ and Hispanics’ literacy proficiencies. Households were thenrandomly selected from the segments, and one or two adults from each household wereselected for the survey. Further details regarding data collection are found in Kirsch et al.(1993).