This is a population data from a small school of faculty members where I am working. This is intended to present baseline data pertinent to the problem experienced in school, basis for an action plan. I have it correlated but I establish first descriptive statistics of the variables. I consider having having a separate thematic analysis and furnish it with related studies to make my Results and Discussions substantial. Any suggestions for the design for improvements? Currently, it is descriptive-correlational in a mixed method approach.
Based on the information you provided, it seems like you have a good plan in place for analyzing your population data and using it to inform an action plan.
Descriptive statistics can provide valuable information about your population data, but it may be useful to use more advanced statistical techniques to establish more robust relationships between the variables you are investigating. Consult with a statistician or an expert in your field to determine what type of analysis would be most appropriate for your research question and data.
A theoretical framework may provide a conceptual basis for your research and help you make sense of your findings. Consider using an established theoretical framework in your field or developing your own based on your research question and data.
This number is not enough to run correlation or regression, for it is difficult to be normalized, In general you need around 50 to 60 pairs minimum to do what you want. Regards.
Because you sample is so small, your correlation will have a very large standard error, which will almost guarantee that it will not be significant.
For mixed methods research, you need to have a strategy for integrating the results from both your quantitative and qualitative research questions. If you have only descriptive quantitative data, that would probably not be enough to qualify as mixed methods research.
Calculating a correlation coefficient with only ten pairs of data is possible. However, the reliability of the correlation will depend on several factors, such as the strength of the relationship between the variables, the variability of the data, and the purpose of the analysis. If the relationship is very strong and the data are not highly dispersed, a small number of pairs may be sufficient, but if the relationship is weak or moderate, or if the analysis requires making important decisions or predictions, a larger sample size is generally recommended. Here is a book discussing sample size's importance in correlation analysis.
Hardin, J. W., & Hilbe, J. M. (2018). Generalized linear models and extensions (4th ed.). Stata Press. https://www.routledge.com/Generalized-Linear-Models-and-Extensions-Fourth-Edition/Hardin-Hilbe/p/book/9781597182256#
Good luck,
- Badges
- Science topic
- Similar topics
- Statistics
- Survey