What are the possible ways to distinguish the behaviour of the data other than developing a scatter graph?
Well you could fit various equations to the data and test how linear the fit is. See tests of parallel regression lines to get an idea about that. Graphs are IMO your best bet to start with anyway. Best, D. Booth
David Eugene Booth Thank you sir for your feedback.
My data set is large in number. If I go for the graphical representation it won't fit for paper write up. Although from naked eye and scattered graph the data shows nonlinear behaviour but is there any particular test you can name by which I simply quote the behaviour as linear or nonlinear.
Muhammad Ali if it doesn't look linear on a graph it's not linear. Here is a link: you could look at:
https://www.dummies.com/education/math/business-statistics/use-scatter-plots-to-identify-a-linear-relationship-in-simple-regression-analysis/
Now if data set size is a problem use ggplot2 the best plotting program on the planet. References to its use can be found here: https://www.amazon.com/s?k=ggplot2+elegant+graphics+for+data+analysis&i=stripbooks&crid=WYTV2O1Q36RR&sprefix=ggplot2%2Cstripbooks%2C306&ref=nb_sb_ss_i_2_7 and here:
https://www.amazon.com/Everyone-Advanced-Analytics-Graphics-Addison-Wesley/dp/013454692X and even here:
https://www.google.com/search?rlz=1C1CHBF_enUS874US874&ei=gKEJXuXmD8yPtAaO5KaoDA&q=how+to+use+ggplot2+package&oq=How+to+use+ggplot2&gs_l=psy-ab.1.6.0l4j0i22i30l6.561039.584109..610713...0.2..0.157.3352.35j4......0....1..gws-wiz.......0i71j0i13j33i160j33i299j33i10j0i67j0i131.HjzK2KKfk5w
If you demand a stat test for linear trend you can find some here:
https://www.google.com/search?q=tests+for+linear+trends&rlz=1C1CHBF_enUS874US874&oq=tests+for+linear+trends&aqs=chrome..69i57.13499j0j4&sourceid=chrome&ie=UTF-8
I DO NOT recommend these for your purpose
D. Booth, PhD, PSTAT
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Graphs