Page 78 |
Save page Remove page | Previous | 78 of 136 | Next |
|
small (250x250 max)
medium (500x500 max)
Large (1000x1000 max)
Extra Large
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
|
70
responses. Sum of all 1’s becomes the raw score. The exam is scored a second time
through a different scoring system generating a second raw score. The two raw
scores are then compared and if they match they are sent to the next phase of scoring.
The second phase of the scoring uses a mathematically based statistical scoring
program based on the Rasch model. This program uses the difficulties of the test
items and the number of correct responses to determine the examinee’s proficiency
measure. The rationale for this process is that it gives more credit to individuals who
took a harder version of the exam and prevents unfair advantage to individuals who
took the easier version.
Once the proficiency measure is obtained the scores are re-scaled so that they
can be more easily interpreted. A base reference group serves a benchmark for re-scaling.
The reference group has a mean score of 500 with a standard deviation of
100. Scores usually range from 200 to 800, occasionally individuals score above
800. The proficiency level required to pass the test is determine by the “cutscore”.
The minimal passing score to pass the examination is a score of 350. Individuals
need 55% - 65% correct responses to pass the test, depending on the difficulty of the
exam version.
Data Analysis
Data will be coded into SPSS 16.0 version computer program. Data analysis
will occur in two phases. The initial phase of data analysis will be a univariate
correlation between predictor variables scores with criterion scores (Table 7) to
determine correlation coefficients.
Object Description
| Title | A predictive valdity study: correlation of admission variables with program completion and student performance on the National Certification Examination in a physician assistant program |
| Author | Middleton, Delores E. |
| Author email | delores.middleton@rcc.edu; lolokinard@yahoo.com |
| Degree | Doctor of Education |
| Document type | Dissertation |
| Degree program | Education |
| School | Rossier School of Education |
| Date defended/completed | 2008-08-29 |
| Date submitted | 2008 |
| Restricted until | Unrestricted |
| Date published | 2008-10-18 |
| Advisor (committee chair) | Jimenez y West, Ilda |
| Advisor (committee member) |
Cole, Darnell Hocevar, Dennis J. |
| Abstract | The purpose of this investigation was to examine the reliability and predictive validity of the of admission data in predicting student success in completing a community college-based physician assistant program and their performance on the National Certification Examination (NCE). The files of 170 graduates were reviewed and the following data was complied: 1) science grade point average (GPAsci), 2) cumulative grade point average (GPAcum), 3) reference letter ratings, 4) personal statement ratings, and 5) work experience -- each identified as a predictor measure in this study. The criterion measures identified in the study were 1) program completion, 2) performance on the NCE, and 3) skills. Findings demonstrated variations in the degree of relationship among predictor measures and criterion measures. The GPAsci demonstrated the greatest degree of correlation with student outcome in comparison with other predictor measures, which is consistent with previous research. Overall, the research demonstrated that there was practical significance or potentially significance correlations between the majority of the predictor measures. |
| Keyword | admission variable; criterion measures; national certification examination; criterion related evidence; reliability and predictive validy; prior academic achievement; letters of reference; personal statement; work experience |
| Coverage date | 1999/2005 |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Provenance | Electronically uploaded by the author |
| Type | texts |
| Legacy record ID | usctheses-m1678 |
| Contributing entity | University of Southern California |
| Rights | Middleton, Delores E. |
| Repository name | Libraries, University of Southern California |
| Repository address | Los Angeles, California |
| Repository email | cisadmin@lib.usc.edu |
| Filename | etd-Middleton-2420 |
| Archival file | uscthesesreloadpub_Volume32/etd-Middleton-2420.pdf |
Description
| Title | Page 78 |
| Contributing entity | University of Southern California |
| Repository email | cisadmin@lib.usc.edu |
| Full text | 70 responses. Sum of all 1’s becomes the raw score. The exam is scored a second time through a different scoring system generating a second raw score. The two raw scores are then compared and if they match they are sent to the next phase of scoring. The second phase of the scoring uses a mathematically based statistical scoring program based on the Rasch model. This program uses the difficulties of the test items and the number of correct responses to determine the examinee’s proficiency measure. The rationale for this process is that it gives more credit to individuals who took a harder version of the exam and prevents unfair advantage to individuals who took the easier version. Once the proficiency measure is obtained the scores are re-scaled so that they can be more easily interpreted. A base reference group serves a benchmark for re-scaling. The reference group has a mean score of 500 with a standard deviation of 100. Scores usually range from 200 to 800, occasionally individuals score above 800. The proficiency level required to pass the test is determine by the “cutscore”. The minimal passing score to pass the examination is a score of 350. Individuals need 55% - 65% correct responses to pass the test, depending on the difficulty of the exam version. Data Analysis Data will be coded into SPSS 16.0 version computer program. Data analysis will occur in two phases. The initial phase of data analysis will be a univariate correlation between predictor variables scores with criterion scores (Table 7) to determine correlation coefficients. |
