Handbook for Using the Intensive Time-Series Design

Abstract

Work on the development of the intensive time-series design was initiated because of the dissatisfaction with existing research designs. This dissatisfaction resulted from the paucity of data obtained from designs such as the pre-post and randomized posttest-only designs. All have the common characteristic of yielding data from only one or two points in time. In addition, true experimental designs require random selection of subjects from a population and random assignment of subjects between control and experimental groups. Since such conditions seldom materialize in school situations, a design in which the same group could perform functions of both experimental and control groups would be advantageous for school-based research. The time-series design, with its potential adaptation of baseline, intervention, and followup states, has such potential. Areas addressed in this handbook include background/rationale for the time-series design, instrument development (developing item pools, generating daily instruments, constructing multiple item instruments), administration and collection of data, and analysis procedures. Example items, sample coding sheet, and Rasch item calibration heuristic are provided in appendices. (JN)