The purpose of this study was to predict placement and non-placement outcomes for mildly handicapped three through five year old children given knowledge of their developmental screening data. In order to do this, discrete discriminant analysis was used to demonstrate the prediction scheme and was modified for application to Child Find data. / Developmental screening data and placement outcomes were systematically retrieved from a longitudinal set (1982-1989) of Child Find records located at the Florida Diagnostic and Learning Resources System (FDLRS)/Sarasota network for 602 subjects. The independent variables included performance on developmental activities from the Comprehensive Identification Process (Zehrbach, 1975), including: (a) gross motor, (b) fine motor, (c) cognitive-verbal, (d) expressive language, (e) receptive language, (f) social-affective, and (g) the expressed concern of parents, guardians, or primary caregivers regarding observations of children's developmental performance. These independent variables were related to two outcome groups, namely, placement and non-placement. / In addition to the two outcome groups, placement and non-placement, 128 combinations of the seven developmental variables were specified. These combinations were statistically analyzed using discrete discriminant analysis, resulting in a prediction technique for estimating the outcomes of developmental screening efforts. The expected frequencies of subjects falling into the prescribed outcome groups were computed. Also, the relative costs of misclassification (prediction mistakes) of subjects into the wrong groups were determined. / For each cost function, a comparison was made between the predictions of the discriminant analysis and the observed outcomes for the 602 subjects. Chi-square tests were conducted to test the significance of the predictions for the placement groups with each of the cost functions. The null hypothesis, that the predictions using this technique were no better than what would be expected by chance, was rejected in each instance. / Source: Dissertation Abstracts International, Volume: 50-12, Section: A, page: 3844. / Major Professor: Andrew Oseroff. / Thesis (Ph.D.)--The Florida State University, 1989.
| Identifer | oai:union.ndltd.org:fsu.edu/oai:fsu.digital.flvc.org:fsu_78107 |
| Contributors | Boothby, Louise Helen., Florida State University |
| Source Sets | Florida State University |
| Language | English |
| Detected Language | English |
| Type | Text |
| Format | 148 p. |
| Rights | On campus use only. |
| Relation | Dissertation Abstracts International |
Page generated in 0.0019 seconds