Research Methodology

NSGA CONSUMER PURCHASE REPORT INTRODUCTION & METHODOLOGY

The survey procedure used for each report is similar. The basic consistency in methodology provides a sound basis for comparing overall purchase statistics. Future reports will continue to be based on similar consumer surveys so as to permit an analysis of trends.

Each report presents projections of consumer purchases from a survey of 80,000 households. Most fall/winter items are based on purchases during the calendar year. Most spring/summer products are based on purchases during the season.. Projections each year are based on the total number of households in the U.S.

The large panel was divided into four representative samples of 20,000 households each so that a maximum number of individual sporting goods products could be included in the survey. Replies were received from approximately 77% of the sample.

The Sport & Athletic Clothing category is taken from a separate study on sports participation done by the National Sporting Goods Association. The study is based on a survey of 10,000 households. Participants were asked to give their dollar expenditure for clothing purchases for each sport. These estimates reflect, for example, "clothing expenditures for golf," not purchases of "golf clothing."

In the questionnaire for Sport & Athletic Footwear, the person asked to respond was the one "most aware of shoe purchases by all household members." Prior to 1989, the person asked to respond was the one "most aware of sporting goods purchases by all household members." In certain shoe categories, this may have had an impact on the pairage reported.

Estimates of retail sales are shown for some products which were not included in the survey. These estimates are based on reliable published statistics where available. In other cases reliance was placed on knowledgeable industry sources.

In addition to the consumer survey, this report presents projections of Athletic Goods Team Sales prepared by the national Sporting Goods Association.

The data showing percent of units purchased in each type of outlet is based only on the most recent purchase. The percentages are indicative of the relative unit and dollar sales by outlet type, but they do not represent the actual percent of units and dollars sold by each type.

The consumer panel used in this study is maintained by National Family Opinion, Inc., operator of the largest consumer panel in the U.S. with almost 400,000 households. The panels are balanced to parallel the actual household distribution as reported by the U.S. Bureau of the Census, in five important characteristics: census region, income, household size, age of head, and population density. For example, 5.2% of the U.S. households live in New England, and 5.2% of the panel households live in New England.

DISTRIBUTION OF STATES BY REGION:

New England:

Connecticut
Rhode Island
Massachusetts
Maine
Vermont
New Hampshire

Mid-Atlantic:

New York
New Jersey
Pennsylvania

South Atlantic:

Delaware
District of Columbia
Florida
Georgia
Maryland
North Carolina
South Carolina
Virginia
West Virginia

East North Central:

Illinois
Indiana
Michigan
Ohio
Wisconsin

West North Central:

Iowa
Kansas
Minnesota
Missouri
Nebraska
North Dakota
South Dakota

East South Central:

Alabama
Kentucky
Mississippi
Tennessee

West South Central

Arkansas
Louisiana
Oklahoma
Texas

Mountain:

Arizona
Colorado
Idaho
Montana
Nevada
New Mexico
Utah
Wyoming

West:

California
Oregon
Washington

NSGA SPORTS PARTICIPATION METHODOLOGY

I. Introduction

Sports Participation is a research program designed to measure the number of individuals seven years of age or older who participated in each of a number of different sports within the previous year.

Sports Participation measure the annual number of participants in each sport, the frequency of participation (number of days of participation), total days of participation, and the average (mean) number of days of participation.

II. Methodology

--Sampling--

A mail panel resource of more than 300,000 pre-recruited households is used for each survey. The panel is balanced on a number of characteristics determined to be key indicators of general purchase behavior, including household size and composition, household income, age of household head, socio-economic status of the household, and region and market size.

During the first week of January each year, a self-administered questionnaire is mailed to 20,000 of these households. The sample is balanced to oversample lower "return rate" segments, thereby yielding a return sample which is correctly representative of the continental United States based upon these characteristics.

In order to keep the number of sports measured, two different surveys are conducted simultaneously, each one measuring approximately 30 sports.

--Questionnaire--

The questionnaire asked the male and female heads of household and up to two other household members who were at least seven years of age to indicate their age, the sports in which they participated, and the number of days of participation.

In order to reduce bias effect that is possible from the order in which the sports are listed, the list is given in alphabetic order to half of the households, and in reverse-alphabetic order to the remaining half of households.

Survey response rates average over 70% for each study.

--Returns--

The sample returns were projected using a two-step process. The first step ensured that the sample returns were correctly representative of the continental United States in terms of state of residence and market size. This was accomplished through the use of a 48-cell weighting matrix defined for both state and MSA market size.

The second step projected the weighted returns to be representative of participation in the entire continental United States. The projection matrix was defined for: household size; gender of household head for single member households; household head age for each household size break; household income for each household head age break; and region.

III. Statistical Notes

It is important to note that in basing estimates of a population on a sample drawn from that population, a degree of sample error is possible. While a number of biases can effect the extent of sampling error, it is to a great degree dependent on the size of the sample. The larger the sample, the more closely the estimate represents the total population.

Sampling error also affects samples of the same size. A sample drawn from a population will result in an estimate for a characteristic of population, the proportion of archers for example If another sample were drawn, it would be likely to include different members of the population. This would yield a slightly different estimate of the proportion of archers.

To allow judgments and decisions to be made with confidence when using samples, we can determine a confidence interval for the estimate.

A confidence interval is simply a range. A 95% confidence interval for the proportion of archers in the population is a range in which the estimates for the proportion of archers would fall 95% of the time, were the study to be done repeatedly. For example, suppose the proportion stating that they participated in archery was 2.1% (after weighting and projection). Thus, if we were to estimate the proportion of archers in the United States using 100 similar studies, 95 of those studies would yield an estimate within 95% confident interval of 2.0%-2.2% (+/-0.1%) from the stated proportion.

Confidence levels for measurements of the proportion of participants in each sport generally do not exceed +/- 1.0%.

DISTRIBUTION OF STATES BY REGION:

New England:

Connecticut
Rhode Island
Massachusetts
Maine
Vermont
New Hampshire

Mid-Atlantic:

New York
New Jersey
Pennsylvania

South Atlantic:

Delaware
District of Columbia
Florida
Georgia
Maryland
North Carolina
South Carolina
Virginia
West Virginia

East North Central:

Illinois
Indiana
Michigan
Ohio
Wisconsin

West North Central:

Iowa
Kansas
Minnesota
Missouri
Nebraska
North Dakota
South Dakota

East South Central:

Alabama
Kentucky
Mississippi
Tennessee

West South Central

Arkansas
Louisiana
Oklahoma
Texas

Mountain:

Arizona
Colorado
Idaho
Montana
Nevada
New Mexico
Utah
Wyoming

West:

California
Oregon
Washington

NSGA TEAM LICENSED AND SPORTS CLOTHING DIARY

The NSGA Team Licensed and Sports Clothing Diary is designed to provide the most up-to-date information on market size and consumer profiles for clothing purchased with logos and/or for use in an active sport.

I. Categories

Apparel categories included in the reports are:

• Fleecewear Tops (Male & Female. Sweatshirts)
• Fleecewear Bottoms (Male & Female. Sweat Pants, Sweat Shorts)
• Warm-Up Suits (Male & Female. Sweat Suit, Warm-Up/Jogging)
• Jackets (Male & Female. Ski Jacket; Golf Jacket/Windbreaker; Other Outerwear Jacket)
• Hats/Caps
• Knit Shirts (Male & Female. Golf/Rugby/Polo Shirt; Turtlenecks; Other Knit Tops)
• Tee Shirts (Male & Female. Tee Shirt-Not Underwear; Pocket Tee Shirt (Not Underwear); Tank Top; Crop Top; Sport/Casual Shirt; Shirt/Blouse)
• Shorts (Male & Female. Tennis Shorts, Running Shorts, Other Shorts)
• Athletic Socks
• Swimsuits (Male: Swimwear That Is A Brief, Boxer Or Bikini. Female: One or Two-Piece Swimwear)
• Leotards/Tights (Female Only. Leotards; Tights; Footless Sport Tights)
• Sports Bras
• Thermal Underwear (Male & Female. Tops, Bottoms, One-Piece)
  

II. Reports

A. Market Size

• This measures the market in terms of units purchased, retail dollar expenditures, and average price for each apparel category, showing:
• Total Apparel - All apparel purchased by/for consumers age 7 or older for each clothing category included in the report.
• Sports Apparel - Item was purchased for use in an active sport.
• Non-Sports Apparel - Item was not purchased for use in an active sport.
• Logo - Item is embroidered or screen printed.

Under items with logo, the following categories are included:

• Major Licenses - Major League Baseball (MLB), National Basketball Association (NBA), National Football League (NFL) and National Hockey League (NHL).
• Other Sports - Includes other pro sports, other sports activities and sports celebrities.
• Schools - Colleges/Universities/Other Schools.
• Non-Sport - Includes cartoon, animal, beverage, rock/other music, etc. In the tables, Cartoon, Celebrity is used only as examples of non-sport logos.

Tables are generated for selected demographics, including:

• Sex/Age
• Male Age
• Female Age
• Household Income
• Market Size/Census Region
• Channels of Distribution
• Price Point
• % Change vs. Year Ago

B. Specific Sport Use

Measures percent of clothing purchased for use in the following active sports:

• Aerobics/Dance
• Basketball
• Fishing/Hunting/Camping
• Golf
• Running/Jogging
• Skiing (Downhill)
• Swimming
• Tennis
• Walking For Exercise
• Other Exercise/Fitness
• Other Sports

NOTE: To qualify as purchased for specific sport use, the panelist must describe the item as having been purchased for sports use, and indicate the sport for which it was purchased. If clothing is purchased for both casual and sport use, or for use in multiple sports, the panelist may not identify an individual sport for which the clothing was bought.

III. Methodology

A. Diary

Using the American Shoppers Panel, a diary was mailed out to 16,000 households monthly. The diary asks for purchases made by all household members for selected food and household items, kitchen, bed and bath fabric items, toys/games/hobbies/crafts, clothing, sewing patterns and books.

B. Sample

The panel is recruited by mail and is demographically balanced on:

• Income
• Household Size
• Age of Household Head
• Census Region
• MSA Residence
• Family vs. non-Family

C. Projection

The returns are weighted to correctly represent the U.S. Census demographic configuration. After weighing, the data is then projected to approximate the total U.S. market.

A blank space in place of numbers represents insufficient sample size for that particular data item.

Northeast:

Connecticut
Rhode Island
Massachusetts
Maine
New York
New Jersey
Pennsylvania
Vermont
New Hampshire

North Central (Midwest):

Illinois
Indiana
Iowa
Kansas
Michigan
Minnesota
Missouri
Nebraska
North Dakota
Ohio
South Dakota
Wisconsin

South:

Alabama
Arkansas
Delaware
District of Columbia
Florida
Georgia
Kentucky
Louisiana
Maryland
Mississippi
North Carolina
Oklahoma
South Carolina
Tennessee
Texas
Virginia
West Virginia

West:

Arizona
California
Oregon
Colorado
Idaho
Montana
Nevada
New Mexico
Utah
Washington
Wyoming