Raffaele Miniaci and Sergio Pastorello, "Mean-Variance Econometric Analysis of Household Portfolios", Journal of Applied Econometrics, Vol. 25, No. 3, 2010, pp. 481-504. All program and data files are ASCII files in DOS format. They are zipped in the file mp-files.zip. Unix/Linux users should use "unzip -a". The data used in this paper are from the Survey of Consumer Finances 2004. The raw data can be downloaded in Stata format from the Federal Reserve Board website: http://www.federalreserve.gov/PUBS/oss/oss2/2004/scf2004data.html#STATADAT Raw data were aggregated and transformed as described in the paper using the Stata do-files contained in StataCode.zip: JAE_start.do collapse_JAE.do labelfin_JAE.do cleandata_JAE.do labeldata_JAE.do portfin_JAE.do The main do-file is JAE_start.do, which sets up and runs the remaining 5 files. These commands generate an ASCII file containing the data actually used in the paper. This clean data file is also enclosed as mp-data.txt, which contains 4214 observations following a line with variable names. The file mp-data.txt contains the following variables: Variable Definition d Portfolio regime: 1 = No bonds, no equities 2 = Bonds, no equities 3 = No bonds, equities 4 = Bonds, equities a1 Share of wealth invested in bonds a2 Share of wealth invested in equities const Constant age Age (years)/100 age2 age^2 dumncomp Dummy for the household composition: 0 = number of components <= 3 1 = number of components > 3 dummarried Dummy for the household head marital status: 0 = not living in couple 1 = living in couple dumgrad Dummy for the household head education: 0 = at most high school 1 = university degree dumself Dummy for the household head job status: 0 = not self-employed 1 = self-employed dumret Dummy for the household head retirement status: 0 = not retired 1 = retired dumwhite Dummy for the household head ethnic group: 0 = not white 1 = white dumsex Dummy for the household head gender: 0 = male 1 = female dumadv Dummy for the financial advisor: 0 = no financial advisor 1 = financial advisor w Wealth (in 1,000 US$) w2 w^2 y Income (in 1,000 US$) y2 y^2 weight Sampling weight