I would appreciate hearing your views on whether solving the problem below is possible in STATA.
I am looking to find a portfolio of uncorrelated instruments. The portfolio should be as large as possible, from a population of 250 instruments available. Here "uncorrelated" refers to any correlation between -0.03 and 0.03.
The difficulty is that for each uncorrelated pair, I need to identify a third element which has low corr with either element in the pair, then add fourth, then fifth, etc. until I can no longer find any instruments to add. Doing this manually can take hours to process all the possible combinations, so I am hoping there is a STATA code that can achieve the result.
I attach a sample .csv file of 250 instruments with daily returns over last year.
Related Posts with Portfolio of uncorrelated instruments
How to do calcuations between different datatypes (double, long, float)?Hello. I try to create some new ID-variables. Actually my datatype for pid/hid is "long". With MWE i…
Merging two variables from different questionnairesDear all I am using the panel dataset of South African National Income Dynamics Survey (NIDS) - wav…
Panel Data Analysis (Run desired regression)Dear Specialist First Thanks for your reading. I have a Panel Data set. I treated Region as id var…
Unicode analyze error - too big fileHi Guys! I am new in Stata and I have a problem with analyzing and translating dta file encodings by…
Summary statistics tableHi, I want to summarize age, education, family_size and voters (average and standard deviation) by c…
Subscribe to:
Post Comments (Atom)
0 Response to Portfolio of uncorrelated instruments
Post a Comment