Marco Costanigro, Ron C. Mittelhammer, and Jill J. McCluskey, "Estimating Class-specific Parametric Models under Class Uncertainty: Local Polynomial Regression Clustering in an Hedonic Analysis of Wine Markets", Journal of Applied Econometrics, Vol. 24, No. 7, 2009, pp. 1117-1135. There are two data files. These are both ASCII files in DOS format. They are zipped in the file cmm-data.zip. Unix/Linux users should use "unzip -a". The file "data.txt" is composed of 9,600 observations derived from ten vintage years (1991-2000) of tasting ratings reported in the Wine Spectator Magazine (online version) for California and Washington red wines. This file was used to obtain the main estimation results presented in the paper. It contains 9,601 rows and 30 columns. A full description of the variables follows. Variable Description units Price wine price (CPI adj.) $ Cases cases produced # Score WSM tasting score # Age years of aging Years Napa valley region of production =1 if produced in named region bay area / central region of production =1 if produced in named region sonoma region of production =1 if produced in named region south coast region of production =1 if produced in named region carneros region of production =1 if produced in named region sierra foothills region of production =1 if produced in named region mendocino / lake region of production =1 if produced in named region washington region of production =1 if produced in named region Nonvarietal grape variety used =1 if multiple varieties used Pinot noir grape variety used =1 if named variety used Cabernet grape variety used =1 if named variety used Merlot grape variety used =1 if named variety used Shyrah grape variety used =1 if named variety used Reserve additional label information =1 if reserve wine Vineyard additional label information =1 if vineyard information is provided Estate additional label information =1 if estate produced 91 vintage =1 if produced in named vintage 92 vintage =1 if produced in named vintage 93 vintage =1 if produced in named vintage 94 vintage =1 if produced in named vintage 95 vintage =1 if produced in named vintage 96 vintage =1 if produced in named vintage 97 vintage =1 if produced in named vintage 98 vintage =1 if produced in named vintage 99 vintage =1 if produced in named vintage Wine Class cluster #, per LPRC #=1,2,3,4 The file "testing.txt" is an additional sample of 3,233 observations from WSM and was used for the forecasting exercise. It has 3,234 rows and 29 columns. A full description of the variables follows. Variable Description units Price wine price (CPI adj.) $ Cases cases produced # Score WSM tasting score # Age years of aging Years Napa valley region of production =1 if produced in named region bay area / central region of production =1 if produced in named region sonoma region of production =1 if produced in named region south coast region of production =1 if produced in named region carneros region of production =1 if produced in named region sierra foothills region of production =1 if produced in named region mendocino / lake region of production =1 if produced in named region washington region of production =1 if produced in named region Nonvarietal grape variety used =1 if multiple varieties used Pinot noir grape variety used =1 if named variety used Cabernet grape variety used =1 if named variety used Merlot grape variety used =1 if named variety used Shyrah grape variety used =1 if named variety used Reserve additional label information =1 if reserve wine Vineyard additional label information =1 if vineyard information is provided Estate additional label information =1 if estate produced 91 vintage =1 if produced in named vintage 92 vintage =1 if produced in named vintage 93 vintage =1 if produced in named vintage 94 vintage =1 if produced in named vintage 95 vintage =1 if produced in named vintage 96 vintage =1 if produced in named vintage 97 vintage =1 if produced in named vintage 98 vintage =1 if produced in named vintage 99 vintage =1 if produced in named vintage