We need to compare the ranking based on S&P rating (rating from 1 to 5) with the performance of the said company (ie gross margin ratio) for 50 Companies. Kindly suggest which statistical analysis will help us.
If you only want to compare "S&P ratings" with" the performance (ie gross margin ratio)" for each company you can calculate the Spearman correlations.
You can compare correlations pairwise online:
http://vassarstats.net/rdiff.html
or:
https://www.psychometrica.de/correlation.html
Chethan Jayantha can you clarify your analysis objectives?
Are you wanting to measure how well the rating and performance? If so, then you might consider correlation analysis (e.g., Spearman, Kendall).
Are you wanting to compare/predict the performance based on rank (assuming rank is integer/discrete)? If so, then you might consider analysis of variance (ANOVA) or one of its non-parametric counterparts.
Are you wanting to predict the rank (assuming rank is integer/discrete) from performance? If so, you might consider linear discriminant analysis.
Maybe it's something else entirely, but clarifying what you would like to know about your data after the analysis is complete can help point you in the right direction.
Rank regression can be used
You may check the following paper:
Tian CHEN, Wan TANG, Ying LU, and Xin TU, Rank regression: an alternative regression approach for data with outliers, Shanghai Arch Psychiatry. 2014 Oct; 26(5): 310–315.
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis