- Called of God or called of man?
- How would a Reformed theologian distinguish his or her view of atonement?
- Evidence that Peter alone was made a Bishop by Christ?
- How do you use the future of the verb devoir when using another verb aswell?
- clarify diffence between present, perfect, imperfect and pluperfect in French
- AR filter length
- (Faster) RCNN dataset physical markers
- how to create a DFT with scalloping/spectal leakage
- correctnes of multi prime RSA algorithm
- Can PRF F with generator P be secure?
- What to expect about the mobile phone usage during a flight to China and based on the CAAC regulations
- At what time of day does US visa expire?
- Travel Issues to Turkey
- Can a US green card holder transiting through China leave the airport? Recommendation for sight-seeing in Shanghai?
- Amtrak Seating NY to DC
- The soul as the form of the body – considering massive changes of the body
- Why can't uniformity of nature (in principle) be proven deductively?
- Need help to understand Kierkegaard's “An Ecstatic Discourse”
- Understanding Herr and its various meanings
- What is the english translation of ,,dagobertinisch"?

# Normalize Returns in PCA Hedging?

Lets say I want to form a portfolio of $N$ correlated instruments that minimizes the variance of my daily PnL, given by

$$

PnL = \sum_{i=1}^N h_i \Delta S_i

$$

where $h_i$ are the number of units of instrument $i$ and $\Delta S_i$ is the daily difference in price.

To minimize the variance, I find the covariance matrix of $\{\Delta S_i\}_i$ and perform PCA on this covariance matrix. I then take the eigenvector with smallest eigenvalue and use the entries as my hedging ratios.

My question is, if the daily difference in instruments are vastly different, say on average $\Delta S_1 = \$10$ while $\Delta S_2 = \$0.1$, does it make sense to normalize these before performing PCA?

I an inclined not to because they are in the same units, and I think it makes sense for instruments with a larger variance to contribute more; however, I have always thought I needed to normalize the data before performing PCA, so I am hesitant to do otherwise now.