International Health Policy Program -Thailand Panatapon Chongprasertying,Kannapon Phakdeesettakun Center for Alcohol Studies, International Health Policy.

Slides:



Advertisements
Similar presentations
Lesson 10: Linear Regression and Correlation
Advertisements

Conclusion to Bivariate Linear Regression Economics 224 – Notes for November 19, 2008.
1 SSS II Lecture 1: Correlation and Regression Graduate School 2008/2009 Social Science Statistics II Gwilym Pryce
ICES 3° International Conference on Educational Sciences 2014
Liqueur sales in Finnish fruit wine estates – the beginning of the end? Thomas Karlsson & Esa Österberg Nordic alcohol and drug researchers’ assembly Reykjavík,
CHAPTER 23: Two Categorical Variables The Chi-Square Test ESSENTIAL STATISTICS Second Edition David S. Moore, William I. Notz, and Michael A. Fligner Lecture.
Seasonality in Calorie Consumption: Evidence from Mozambique. Channing Arndt, Mikkel Barslund, Jose Sulemane Support from the African Economic Research.
National Drug Research Institute Preventing Harmful Drug Use in Australia Violence in the night-time economy: availability and amenity.
International Health Policy Program -Thailand 1 Literature of density of alcohol outlets effects on alcohol consumption and alcohol-related problems Weranuch.
Journal Club Alcohol, Other Drugs, and Health: Current Evidence July–August 2008.
Copyright © 2014, 2013, 2010 and 2007 Pearson Education, Inc. Chapter Hypothesis Tests Regarding a Parameter 10.
Analysis of the rationale for, and consequences of, nonprofit and for-profit ownership conversions by Tami Mark Health Services Research, April 1999 Presentation.
Full time and part time employment Coventry population in employment by gender Source: Annual Population Survey, Office for National Statistics
Contributed by National Academy of Statistical Administration, India.
1 CHAPTER M4 Cost Behavior © 2007 Pearson Custom Publishing.
The Effects of De-listing Publicly Funded Health Care Services Mark Stabile Department of Economics and Center for Economics and Public Affairs University.
FOOD DESERTS Lori Kowaleski-Jones Department of Family and Consumer Studies University of Utah.
Diane Stockton Trend analysis. Introduction Why do we want to look at trends over time? –To see how things have changed What is the information used for?
Copyright © 2011 Pearson Education, Inc. Multiple Regression Chapter 23.
Linear Regression and Correlation
Following lives from birth and through the adult years Examining the truth behind the myth of the 'the Monstrous Army on the March' Dylan.
International Health Policy Program -Thailand Present by : Wittaya Wisutruangdaj Sopit Nasueb Alcohol control policies and alcohol consumption by youth:
Tim Stockwell Director, Centre for Addictions Research of BC ( ) Professor, Department of Psychology University of Victoria, BC,
Alcohol Availability & Alcohol Consumption: New Evidence from Sunday Sales Restrictions Kitt Carpenter (UC Irvine) & Daniel Eisenberg (University of Michigan)
Jaw Pain: Characteristics and Prevalence in Fibromyalgia and other Rheumatic Disorders Robert S. Katz 1, Frederick Wolfe 2. 1 Rush University Med Center,
1 Distance and Information Asymmetries in Lending Decisions by Sumit Agarwal and Robert Hauswald (& sons) Discussant Hans Degryse CentER – Tilburg University,
Improvement of Employment Chances of the Unemployed and the Visual and Audible Disabled by using Virtual Learning Applications The Netherlands, some basic.
1st Pan American Conference on Alcohol Policies Alcohol, Gender and Culture in Peru: Preliminary epidemiological estimates Marina Piazza, MPH, ScD; Inés.
CHAPTER 14 MULTIPLE REGRESSION
International Health Policy Program -Thailand 1 Present by Orratai Waleewong International Health Policy Program (IHPP) Ministry of Public Health, Thailand.
Centre for Market and Public Organisation Using difference-in-difference methods to evaluate the effect of policy reform on fertility: The Working Families.
Determinants of Credit Default Swap Spread: Evidence from the Japanese Credit Derivative Market.
The Examination of Residuals. Examination of Residuals The fitting of models to data is done using an iterative approach. The first step is to fit a simple.
McGraw-Hill/Irwin Copyright © 2010 by The McGraw-Hill Companies, Inc. All rights reserved. Chapter 13 Linear Regression and Correlation.
Correlation Analysis. A measure of association between two or more numerical variables. For examples height & weight relationship price and demand relationship.
International Health Policy Program -Thailand Wittaya Wisutruangdaj Vanichar Fakkhum Presentation to APR academic meeting IHPP meeting room 20 February.
Psych 230 Psychological Measurement and Statistics Pedro Wolf September 23, 2009.
Managerial Economics Demand Estimation & Forecasting.
Canadian Public Health Association 2008 Annual Conference Halifax, Nova Scotia, May 31 – June 4, 2008 Does Province of Residence Matter to the Health and.
Initiative 1100: Summary & Impact 1 Rick Garza Deputy Administrative Director.
Acute effects of alcohol on neural correlates of episodic memory encoding Hedvig Söderlund, Cheryl L. Grady, Craig Easdon and Endel Tulving Sundeep Bhullar.
The Fiscal Impacts of Expanded Spirits Retailing in New Hampshire Summary Findings Brian Gottlob PolEcon Research February.
CORRELATION: Correlation analysis Correlation analysis is used to measure the strength of association (linear relationship) between two quantitative variables.
CHAPTER 23: Two Categorical Variables The Chi-Square Test ESSENTIAL STATISTICS Second Edition David S. Moore, William I. Notz, and Michael A. Fligner Lecture.
Employment, unemployment and economic activity Coventry working age population by ethnicity Source: Annual Population Survey, Office for National Statistics.
Chapter Seventeen. Figure 17.1 Relationship of Hypothesis Testing Related to Differences to the Previous Chapter and the Marketing Research Process Focus.
Business Statistics for Managerial Decision Farideh Dehkordi-Vakil.
N318b Winter 2002 Nursing Statistics Specific statistical tests Chi-square (  2 ) Lecture 7.
Remittances and competitiveness: Evidence for Latin America Migration and Development Thematic Group Seminar Humberto Lopez November 26, 2006 Presentation.
Correlation & Regression Analysis
Business Statistics for Managerial Decision Making
Lecture PowerPoint Slides Basic Practice of Statistics 7 th Edition.
Linear Regression and Correlation Chapter GOALS 1. Understand and interpret the terms dependent and independent variable. 2. Calculate and interpret.
Copyright © 2014, 2011 Pearson Education, Inc. 1 Chapter 24 Building Regression Models.
Chi-Square Analysis Test of Homogeneity. Sometimes we compare samples of different populations for certain characteristics. When we do so we are performing.
Statistics for Business and Economics Module 2: Regression and time series analysis Spring 2010 Lecture 7: Time Series Analysis and Forecasting 1 Priyantha.
Chi Square Procedures Chapter 14. Chi-Square Goodness-of-Fit Tests Section 14.1.
AP Stats Check In Where we’ve been… Chapter 7…Chapter 8… Where we are going… Significance Tests!! –Ch 9 Tests about a population proportion –Ch 9Tests.
Chapter 10: The t Test For Two Independent Samples.
©The McGraw-Hill Companies, Inc. 2008McGraw-Hill/Irwin Two-sample Tests of Hypothesis Chapter 11.
Chapter 13 Linear Regression and Correlation. Our Objectives  Draw a scatter diagram.  Understand and interpret the terms dependent and independent.
Wine Consumption Across Generations – A Life Cycle Approach Work in Progress Geir W. Gustavsen 1 and Kyrre Rickertsen 1,2 1 Norwegian Institute of Bioeconomy.
Human Population Pyramids
Regression Analysis.
Minimum alcohol price policies The Canadian Experience
American Public Health Association Meeting November 6, 2007
Is the freedom from Cognitive Impairment really at hand?
Regression Analysis.
AP Stats Check In Where we’ve been… Chapter 7…Chapter 8…
Linear Regression and Correlation
Presentation transcript:

International Health Policy Program -Thailand Panatapon Chongprasertying,Kannapon Phakdeesettakun Center for Alcohol Studies, International Health Policy Program, Ministry of Public Health Thailand The density of liquor outlets: Case Study of The British Columbia, Canada.

International Health Policy Program -Thailand Aim : To investigate the independent effects on liquor sales of an increase in (a) the density of liquor outlets and (b) the proportion of liquor stores in private rather than government ownership in British Columbia between 2003/ /8. Design : The British Columbia Liquor Distribution Branch provided data on litres of ethanol sold through different types of outlets in 89 local health areas of the province by beverage type. 2

International Health Policy Program -Thailand Statistical analyses : Multi-level regression models were used to examine the relationship between per capita alcohol sales and outlet densities for different types of liquor outlet after adjusting for potential confounding social,economic and demographic factors as well as spatial and temporal autocorrelation. Setting: Liquor outlets in 89 local health areas of British Columbia,Canada. -Interior - Northern - Vancouver Coastal - Vancouver Island - Fraser 3

International Health Policy Program -Thailand 4 Variable name Dependent : Monthly per capita litres of absolute alcohol from…… - Beers - Coolers - Spirits - Wines - beer, cooler, spirit and wine otherwise known as ‘alcopops’—mixed alcohol and soft drinks with the strength of between 5% and 10% alcohol by volume

International Health Policy Program -Thailand Independent : 1.Monthly number of..…per population aged restaurants - government stores - bars - private stores Fixed effect 2.Season : - January–March - April–June - July–September - October–December 5

International Health Policy Program -Thailand 3. Calendar year as continuous variable : 2003–2008 Ex : -2003/4 mean:1 April 2003 to 31 March /8 mean:1 April 2007 to 31 March local health areas:89local health - Interior - Northern - Vancouver Coastal - Vancouver Island - Fraser 5. % of population aged 20–29 to population aged <14 % % - >18 % 6

International Health Policy Program -Thailand 7 6.Sex ratio : % of male versus female aged low income : % of low income versus all families 8. Population density (residents/km 2 ) – – < ≥ 37.00

International Health Policy Program -Thailand Per capita alcohol sales increased from 8.04 litres in 2003/04 to 8.63 litres in 2007/08 The number of outlets of all kinds per 10,000 population increased from in 2003/04 to in 2007/08 Per Capita Alcohol Sales and Density of Liquor Outlets by Region and Time. 8

International Health Policy Program -Thailand Per Capita Alcohol Sales and Density of Liquor Outlets by Region and Time Restaurants and private stores increase Government liquor stores decreased Bars remained unchanged 9

International Health Policy Program -Thailand Multi-level regression analysis Relationships between alcohol sales and outlet density 10 Per capita sales of alcohol were associated significantly and positively with changes in monthly number of each kind of liquor outlet per 10,000 residents. The direction of the relationship for government liquor stores was negative when adjustments were made for other independent variables. All types of density measures were associated significantly with changes in per capita alcohol sales : - Restaurants, bars and private stores were associated significantly and positively. - Government stores was associated significantly and negatively. The density of private stores was associated positively and significantly with per capita sales of beer, coolers, spirits and wine, while the density of government stores were related significantly negatively to per capita sales of beer, coolers or spirits, but not wine. The density of restaurants per head of population was associated most strongly positively with all varieties of alcoholic beverage sales.

International Health Policy Program -Thailand A 10% increase in the density of restaurants results in a 2.33% increase in per capita alcohol sales. A similar increase in the density of private stores results in only a 0.28% increase in alcohol sales. The estimated effect sizes are converted to an estimate of percentage change in per capita alcohol sales for all premises for a 10% increase in the population density of each type of outlet, for example: Multi-level regression analysis Relationships between alcohol sales and outlet density 11

International Health Policy Program -Thailand Multi-level regression analysis Proportion of private versus government stores and alcohol sales 12

International Health Policy Program -Thailand The proportion of stores in private hands was associated significantly with total alcohol sales (P < 0.01) Other independent variables which were related positively and significantly to per capita alcohol sales in this model were: - Financial year, the percentage of population aged 20–29 years in the local population aged 15 years and older (P = 0.05) and all annual quarters other than January to March (P < in each case). - The proportion of low-income families in a local area was associated negatively with per capita alcohol sales (P < 0.001). The multi-level regression analysis shown in Table 6 controlling or socio-economic and demographic variables found: 13 Multi-level regression analysis Proportion of private versus government stores and alcohol sales

International Health Policy Program -Thailand Between the financial years 2003/04 and 2007/08 the number of private liquor stores rose by 33.4%, while the number of government liquor stores fell by 9.9%. Overall, conclude that there is strong evidence for a connection between the number of liquor outlets overall per population and per capita alcohol sales: - hypothesis 1 was supported for most varieties of liquor outlet and beverage types. - hypothesis 2 was supported that private liquor outlets are somehow intrinsically more risky than government liquor stores, both for total alcohol sales and for sales of beer, wine and spirits, although not coolers. This suggests some support for the observation that private stores enable some differentiation of the alcohol market, putting further upward pressure on alcohol sales. Discussion 14

International Health Policy Program -Thailand The fully adjusted multi-level regression models found significant and positive associations for the number of restaurants, bars and private stores with total per capita sales of alcohol and also separately for sales of most beverages. By contrast, the population density of government stores was associated significantly and negatively with total alcohol sales, as well as sales of beer, coolers and spirits, but not wine and the numbers of restaurants per residents aged 15 and over was associated the most closely with changes in per capita sales of alcohol. A 10% increase in numbers of different liquor outlets per adult residents was associated with: - A 2.33% increase in per capita sales of alcohol for restaurants. - A 0.50% increase for bars. - A 0.28% increase for private stores. - A 0.22% decrease for government stores. These changes appear modest, it is important to bear in mind that they are changes in total per capita alcohol sales, not simply changes in sales for that particular type of liquor outlet. Discussion 15

International Health Policy Program -Thailand Conclude that there was a stimulating effect on alcohol sales introduced by increasing proportions of private stores over and above the increase in total number of liquor outlets that occurred during the study period. It is important to note that population density of liquor stores was less associated with total alcohol sales than was population density of on premise outlets (bars and restaurants). This is a counter- intuitive finding, as liquor stores contribute a substantially larger proportion of all alcohol sales than to bars and restaurants. This is also consistent with the finding that densities of private alcohol stores are associated significantly positively with changes in per capita alcohol sales, while densities of government alcohol stores are associated significantly and negatively with per capita alcohol sales. Private outlets, both on- and off-premise, have typically more freedom of economic response than government monopolies. Discussion 16

International Health Policy Program -Thailand Overall, findings support strongly a relationship between population density of liquor outlets and alcohol consumption. One impact of the policy that has led to gradually increasing partial privatization of liquor stores has been an increase in the overall number of outlets in many areas. This, in itself, has been associated clearly with increased per capita alcohol sales The analyses presented here show that there was substantial variation across different regions of British Columbia, both in density of liquor outlets and the population rate of alcohol sales. Further, these analyses indicate that local variation in population density of liquor outlets is associated strongly with changes in per capita alcohol sales—and that increasing privatization of liquor stores has further stimulated alcohol sales and consumption. Discussion 17

International Health Policy Program -Thailand As would be expected from international research, any increase in population density of outlets will put upward pressure on per capita alcohol consumption which will, in turn, usually increase a wide range of serious alcohol-related harms. Main finding is that when controlling for liquor outlet density plus spatial, temporal, economic and demographic characteristics across 89 local health areas, increasing privatization of liquor stores in British Columbia in recent years has been associated significantly with increasing alcohol sales per head of population with probable adverse effects on public health. Thus, a fully privatized system might be expected to increase total alcohol consumption still further, along with adverse alcohol-related consequences. Discussion 18

International Health Policy Program -Thailand Reference Tim Stockwell and other. “Changes in per capita alcohol sales during the partial privatization of British Columbia’s retail alcohol monopoly 2003–2008: a multi-level local area analysis”. Addiction, 104, 1827–

International Health Policy Program -Thailand 20