If you want to compare just two treatments, then you can use a t-test, which obviously would have equal sample sizes. But if you want to compare 'counterparts', you should make one data table and use a GLM/ANOVA and post-hoc tests, which take into account all possible interactions. Differences in sample sizes won't be an issue in the GLM unless the differences are very big, in which case the variables (treatments) themselves can become correlated and variance homogeneity may be affected. You can also use non-parametric tests or PERMANOVA, which don't require such strict assumptions. But I don't have an R script though :)

You need special techniques for count data. See the links below:

https://www.google.com/search?q=regression+on+counts&ie=utf-8&oe=utf-8&client=firefox-b-1

https://www.google.com/search?client=firefox-b-1&ei=QbZVW9bCHpjCjgT31baQDQ&q=regression+on+counts+R&oq=regression+on+counts+R&gs_l=psy-ab.12..33i22i29i30k1l4.157574.159121.0.162235.2.2.0.0.0.0.123.215.1j1.2.0....0...1c.1.64.psy-ab..0.1.123....0.bGIsuHavNUI

For sure there are methods in R to handle this as the second link shows.

Best wishes, David Booth

Hello

Please refer to,

Michael J. Crawley(2008). Statistics: An Introduction using R. Wiley.

Regards,

Zuhair

I agree with Andrew Paul McKenzie Pegman.

Thanks to him for his valuable answer with elaborate description.

The link for resource given by David Eugene Booth will be helpful Thanks to him.

The reference given by Z. A. Al-Hemyari will benefit Kaan Özgenc .

Thanks to Z. A. Al-Hemyari

and best wishes to Kaan Özgenc.

Thanks to Balima Larba Hubert fir his informative answer. Best wishes to Kaan Özgenc.

Generalized Linear Model (GLM) in R with Example - Guru99

https://www.guru99.com/r-generalized-linear-model.html