I am doing correlation test on a factor and stock price(both are numerical values). I calculate the correlation from the following two ways:
- Pearson correlation between factor value and stock price
- Pearson correlation between factor value and first order difference of stock price(i.e., price[i+1] - price[i])
It turns out correlations in two cases vary a lot. Any explanation on the difference between the two approaches? I used to suppose they are very close.