Polychoric Correlation With Ordinal Data in Nursing Research.
Frank Kiwanuka, Juho Kopra, Natalia Sak-Dankosky and 2 others
PMID 35997708WHAT IT FOUND
A different way of checking a family-support questionnaire fit the data better than the common method.
This is about analysis, not evidence that nurses gave better support.
Key findings
01800 family-member responses were included in the analysis.
02The polychoric CFA fit the family-support questionnaire data better than the Pearson CFA.
03Perceived emotional and cognitive support differed by family members' education and relationship to the patient.
STILL TO COME
How it was doneWhat they foundWhat it means for RNs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The sample was a convenience sample from two hospitals in Uganda, so it may not represent other settings. The questionnaire was translated and used in a new setting, and the authors did not pre-predict item response frequencies. The study is mainly a statistical comparison, not a test of a nursing intervention. Chi-square tests were significant, and RMSEA was unsatisfactory for both methods, so model fit was not perfect. The design was cross-sectional, so it does not show change over time.
Declared interests
The authors reported no conflicts of interest. The paper is tagged as supported by NIH extramural and non-U.S. government research support.
The easy way to misread this
Do not read this as evidence that nurses in Uganda provided better family support than nurses elsewhere, or that the statistical method improves patient care. The study compares analysis methods on a questionnaire sample and does not test a nursing intervention.