Measurement Error and Equating Error in Power Analysis
Saved in:
| Title: | Measurement Error and Equating Error in Power Analysis |
|---|---|
| Language: | English |
| Authors: | Phillips, Gary W., Jiang, Tao |
| Source: | Practical Assessment, Research & Evaluation. Aug 2016 21(9). |
| Availability: | Center for Educational Assessment. 813 North Pleasant Street, Amherst, MA 01002. e-mail: pare@umass.edu; Tel: 413-577-2180; Web site: https://scholarworks.umass.edu/pare |
| Peer Reviewed: | Y |
| Page Count: | 12 |
| Publication Date: | 2016 |
| Document Type: | Journal Articles Reports - Research |
| Descriptors: | Error of Measurement, Statistical Analysis, Equated Scores, Sample Size, Probability, Statistics, Error Correction, Correlation, True Scores |
| ISSN: | 1531-7714 |
| Abstract: | Power analysis is a fundamental prerequisite for conducting scientific research. Without power analysis the researcher has no way of knowing whether the sample size is large enough to detect the effect he or she is looking for. This paper demonstrates how psychometric factors such as measurement error and equating error affect the power of statistical tests. The overall finding is that measurement error and equating error reduce power and inflate sample size requirements. It is recommended that researchers, where appropriate, incorporate these sources of error in conducting power analysis. If either of these two sources of error are present in the data but not accounted for in the power analysis, then power will be underestimated and sample size requirements will be underestimated. |
| Abstractor: | As Provided |
| Entry Date: | 2016 |
| Accession Number: | EJ1110578 |
| Database: | ERIC |
| Abstract: | Power analysis is a fundamental prerequisite for conducting scientific research. Without power analysis the researcher has no way of knowing whether the sample size is large enough to detect the effect he or she is looking for. This paper demonstrates how psychometric factors such as measurement error and equating error affect the power of statistical tests. The overall finding is that measurement error and equating error reduce power and inflate sample size requirements. It is recommended that researchers, where appropriate, incorporate these sources of error in conducting power analysis. If either of these two sources of error are present in the data but not accounted for in the power analysis, then power will be underestimated and sample size requirements will be underestimated. |
|---|---|
| ISSN: | 1531-7714 |
