The demand for wine and substitute products: A survey of the - PowerPoint PPT Presentation

The demand for wine and substitute products: A survey of the literature A survey of the literature James Fogarty Economics Program Economics Program The University of Western Australia

Key findings Key findings � Demand for alcoholic beverages is price inelastic g p � Imported beverages are more elastic � Trend for more elastic demand since 1958 � Country effects are generally not statistically different � Stigler and Becker (1977 p 76) “tastes neither change � Stigler and Becker (1977, p. 76) tastes neither change capriciously nor differ importantly between people” � Wine in France is an exception � Framework of analysis matters � Consider just elasticity point estimate -- OLS � Consider the point estimate and the SE -- WLS

Data for the study Data for the study � 102 papers provided elasticity estimates � 102 papers provided elasticity estimates � From Stone (1945) to the present � English speaking country bias � English speaking country bias � Occasionally more than one country considered � In some cases more than one type of estimate Beer Beer Wine Wine Spirits Spirits 154 estimates 155 estimates 162 estimates

Standard data summary: wine Standard data summary: wine Wine Own-Price Elasticity Frequency Distribution Frequency F Mean: -.65 50 Median: -.55 No o. Observa St. dev.: .51 St d 51 40 Max: .82 30 Min: -3.00 ations Obs: 155 20 10 0 ositive -1.80 -1.60 -1.40 -1.20 -1.00 -.80 -.60 -.40 -.20 .00 wards onw po Elasticity Value

Summary country details for wine Summary country details for wine Country Country Est Est. Mean Mean S D S.D Country Country Est Est. Mean Mean S D S.D

Summary country details for wine Summary country details for wine Country Country Est. Est Mean Mean S D S.D Country Country Est Est. Mean Mean S D S.D Australia 18 -.66 .67

Summary country details for wine Summary country details for wine Country Country Est Est. Mean Mean S D S.D Country Country Est. Est Mean Mean S D S.D Australia 18 -.66 .67 Canada Canada 33 33 -.80 80 .39 39

Summary country details for wine Summary country details for wine Country Country Est Est. Mean Mean S D S.D Country Country Est Est. Mean Mean S D S.D Australia 18 -.66 .67 Canada Canada 33 33 -.80 80 .39 39 Cyprus 2 -.40 .23 Denmark 2 -.61 .45 Finland 9 -1.14 .63 France 3 -.07 .02 Germany 1 -.38 - Ireland 3 -1.33 .46 Italy Italy 1 1 -1.00 1 00 - Japan 2 -.10 .05

Summary country details for wine Summary country details for wine Country Country Est Est. Mean Mean S D S.D Country Country Est Est. Mean Mean S D S.D Australia 18 -.66 .67 N’lands 1 -.50 - Canada Canada 33 33 -.80 80 .39 39 N Z N. Z. 8 8 -.56 56 .28 28 Cyprus 2 -.40 .23 Norway 7 -.37 .43 Denmark 2 -.61 .45 Poland 1 .82 - Finland 9 -1.14 .63 Portugal 1 -.68 - France 3 -.07 .02 Spain 3 -.98 3 Germany 1 -.38 - Sweden 12 -.83 .41 Ireland 3 -1.33 .46 U.K. 39 -.72 .56 Italy Italy 1 1 -1.00 1 00 - U.S. U S 31 31 -.55 55 .45 45 Japan 2 -.10 .05

Meta analysis framework Meta-analysis framework � Meta-analysis question: � Meta analysis question: � Is the observed variation in elasticity estimates due to sampling error only? due to sampling error only? � Stepwise process of analysis � Step one: consider the fixed effects model St id th fi d ff t d l � Step two: consider the random effects model � If both the fixed and random effects models are rejected design a meta-regression

Meta-analysis approaches Meta analysis approaches � Fixed effects model � Fixed effects model � Find the weighted mean where the weights are the inverse of the estimate variance are the inverse of the estimate variance � Test statistic is based on the sum of the weighted mean square differences g q � High values lead to rejection of null that the reported elasticity estimates are from the p y same population

Meta analysis approach continued Meta-analysis approach continued � Random effects model � Random effects model � Proceed as for fixed effects but reduce the weight to very precise estimates weight to very precise estimates � Meta-regression approach � Observations can be grouped together Ob ti b d t th according to study characteristics � Grouping are likely to be based around Grouping are likely to be based around country, estimation method, time period, data frequency, etc. q y,

Compensated wine estimates Compensated wine estimates , ,

Compensated wine estimates Compensated wine estimates ⎛ ⎛ ⎞ ⎞ Est. 100 100 ⎜ ⎜ ⎟ ⎟ ⎝ ⎠ SE 75 , , 50 25 - -2 -1.5 -1 -0.5 0 0.5 1

Compensated wine estimates Compensated wine estimates ⎛ ⎛ ⎞ ⎞ Est. 100 100 ⎜ ⎜ ⎟ ⎟ ⎝ ⎠ SE Unweighted mean: -.62 75 75 , , 50 25 - -2 -1.5 -1 -0.5 0 0.5 1

Compensated wine estimates Compensated wine estimates ⎛ ⎛ ⎞ ⎞ Est. 100 100 ⎜ ⎜ ⎟ ⎟ ⎝ ⎠ SE Unweighted mean: -.62 Fixed effects mean: -.83 75 75 50 25 - -2 -1.5 -1 -0.5 0 0.5 1

Compensated wine estimates Compensated wine estimates ⎛ ⎛ ⎞ ⎞ Est. 100 100 ⎜ ⎜ ⎟ ⎟ ⎝ ⎠ SE Unweighted mean: -.62 Fixed effects mean: -.83 R Random effects mean: -.57 d ff t 57 75 75 50 25 - -2 -1.5 -1 -0.5 0 0.5 1

Summary testing results Summary testing results Model Model Held constant Held constant Result Result

Summary testing results Summary testing results Model Model Held constant Held constant Result Result Fixed Effects Beverage Always reject Beverage and country Beverage and country Always reject Always reject

Summary testing results Summary testing results Model Model Held constant Held constant Result Result Fixed Effects Beverage Always reject Beverage and country Beverage and country Always reject Always reject Random Effects Beverage Always reject B Beverage and country d t Al Always reject j t

Summary testing results Summary testing results Model Model Held constant Held constant Result Result Fixed Effects Beverage Always reject Beverage and country Beverage and country Always reject Always reject Random Effects Beverage Always reject B Beverage and country d t Al Always reject j t � So try meta-regression � WLS where weights are inverse variance

Interesting findings: Time Interesting findings: Time � The time trend variable � Enters as a quadratic, � 1958 is the point of most inelastic demand � The trend is gentle and between 1958 and 1994 the implied trend increase in elasticity is .13 � OLS � OLS – between 1958 and 1994 more inelastic between 1958 and 1994 more inelastic � A possible relationship with illicit substances � Marijuana Ecstasy Speed etc could be � Marijuana, Ecstasy, Speed, etc. could be substitutes � Speculative so other suggestions welcome

Interesting findings: Country effects Interesting findings: Country effects � Pair-wise testing – 66 comparisons per beverage Pair wise testing 66 comparisons per beverage Average Rejection Rates Beer Beer Wine Wine Spirits Spirits 12 percent 21 percent 12 percent � The main exceptions relate to wine: � Wine in France: 73 percent rejection rate (inelastic) � Wine in France: 73 percent rejection rate (inelastic) � Wine in UK: 45 percent rejection rate (elastic) � Wine Canada: 45 percent rejection rate (elastic) Wine Canada: 45 percent rejection rate (elastic) � Beer in NZ: 45 percent rejection rate (inelastic)

Final points of note Final points of note � Paper available with details and an appendix � Paper available with details and an appendix covering each paper � The approach could be a useful framework pp for some of the hedonic literature on expert opinion etc.