R: How to test for trend of risk scores
0
0
Entering edit mode
6.6 years ago
m98 ▴ 420

I have some case/control data like so (many more rows)

ID    score     phenotype
1     0.6482772         0
2     0.9519315         1
3     2.7689036         0
4     1.9974466         1
5     1.6287841         1
6     1.9993825         0

I performed a logistic regression on pheno~score to determine if an increase in scores leads to increased odds ratio (a measure of disease risk)

I now want to do a trend test in R to test whether there is trend. This trend test would just give me one odds ratio and a p-value. Does anyone know which R package or function I could use? I've looked around and I'm struggling to find a simple package that can help me do this.

Thanks

R trend test risk scores • 2.4k views
ADD COMMENT
1
Entering edit mode

As phenotype is either 0 or 1 could you just do a fisher test as :

fisher.test(score,phenotype)

Could also be nice to plot the data as boxplots (x is the data.frame containing your data):

ggplot(x,aes(x=score,y=score))+geom_boxplot()
ADD REPLY

Login before adding your answer.

Traffic: 3022 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6