Most phenomena of interest to nurses have complex causes, such as readmission for heart failure, exclusive breastfeeding up to 6 months postpartum, and adherence to psychotropic medications. This week you will gain insight into when it is appropriate to use bivariate and multivariate inferential statistical tests. The decision is often based on the complexity of the problem or outcome of interest. Review the following definitions and examples:
Bivariate: Bivariate tests involve two variables in a study to determine if there is a relationship. An example of a bivariate test is analyzing the relationship of age and compassion fatigue in nurses. Multivariate: Multivariate tests involve more than two variables in a study to observe the relationship among the variables. Test of multiple regression that includes many independent variables (e.g., age, adherence to medications, educational level) and their combined effects on days to readmission. Interpretation:
When interpreting results, the description is of analysis, not general conclusions. Here’s an example of an interpretation that could be used if the bivariate test example above had the following findings: The Pearson correlation was used to test the relationship between age and compassion fatigue. The r value for the relationship was .42 indicating a positive, moderate-strength relationship. Before data were collected, the statistical significance was set at α = .05. The p value for the correlation was p = .01 indicating a significant relationship. This means that the older the nurse, the greater the compassion fatigue, and the likelihood the relationship could occur by chance was 1 in 100 samples. Select an article you have already found in a previous week. Respond to the following in a minimum of 175 words: Identify the problem, purpose, research question, and/or hypothesis stated in the article.
Identify the statistical test (i.e., descriptive or inferential) that was used to answer the research question and/or test the hypothesis. Did the authors use the appropriate statistical test to answer the research question or test the hypothesis?
How do you know? Support your answer. Provide at least 1 current, peer-reviewed reference for the initial post. Cite your reference(s) according to current APA guidelines.
