Hi Everyone,
I am working with data of SNPs, I want to do logistic regression analysis.
In multinomial logistic regression, is it compulsory to choose most common genotype as reference? or I can choose any genotype as reference?
In my one SNP (Genotypes: II, ID, DD), when I choose most common II genotype as reference than Odds ratio come out like 0.57, but on choosing ID genotype Odds ratio change to 1.67 with p
The "category" you choose as reference will determine the manner in which you infer your results. Therefore, it is case dependent. In my area of research, severe injuries are often selected as the "base case". These are also the least occurring, in terms of injury severity. As long as you are calculating your "base case" constant and coefficients correctly, you are just fine.
Hi Misbah,
I think statistically, yes you can pick any category as your reference so long as you interpret your results accordingly. Genetically, I'm not sure it can be interpreted. Usually either homozygous group is used, or by alleles carried (eg. all carriers of "I" or "D").
By using heterozygotes as your reference, are you saying that the odds are higher in both homozygous genotype groups compared to the het group? Biologically, this is not possible.
I would first check how many individuals are in your homozygous rare group (DD). If the number is very low you might want to club all rare allele carriers together (ID and DD), for power or because your effect might be dominant.
Hope this helps.
According to my experience,statistically it doesn't matter which genotype you choose as a reference But yes biologically . You should be clear that substitution which is affecting the protein functional or structure. also,you should consider the frequency of individuals falling under each genotypic category as it also determines which allele is the minor one in the population. You should both the factors and infer the results according to your reference that will dictate the type of effect your variation has on the population.
I hope this will guide you
Regards
Charu
Thank you so much everyone for your valuable answers. They helped me alot.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Regression