Methodology

The Physical Activity and Transit (PAT) survey was conducted in 2010 and 2011 by the New York City Department of Health and Mental Hygiene. Data were collected to measure the level and context of physical activity in New York City and to improve understanding of what motivates individuals to be physical active including opportunities for activity, perceptions of safety and security, and other neighborhood factors. For more information on the PAT, please visit:

TARGET POPULATION
The target population of the PAT was adults aged 18 and older who were able to walk more than 10 feet and who lived in one of the five boroughs of New York City. Of the 3908 adults who completed the initial telephone screener, 3811 were mobile and completed the full survey.

HEALTH TOPICS
The PAT asked approximately 125 questions, covering the following: a modified version the Global Health and Physical Activity Questionnaire (GPAQ) designed by the World Health Organization on physical activity in the work, recreation and transportation domains. Also included were questions on chronic disease, diet, alcohol and tobacco, neighborhood conditions, and mental health. The survey also asked a multiple demographic variables to facilitate weighting and comparisons among different groups of New Yorkers.

SAMPLING
The PAT was conducted using a fully overlapping dual frame design, using randomly generated landline and cellular telephone samples. (Roughly 25% were completed on a cell phone.) To provide equal statistical power for borough-level comparisons, a similar number of participants were interviewed in each borough of New York (Bronx, Brooklyn, Manhattan, Queens and Staten Island). All data were then weighted to adjust for the probability of selection and differential nonresponse and sum to Census estimates of the number of people living in each borough.

Interviewing was done by Abt-SRBI, a survey research company based in New York City. Interviews were conducted in English, Spanish, Russian and Chinese (Cantonese and Mandarin). Data collection for wave 1 occurred in September - November of 2010; wave 2 was conducted in March - November of 2011. The average length of the survey was 35 minutes.

LIMITATIONS
The sampling methodology did not capture adults who could not be reached by either landline or cellular telephone. The PAT also excluded adults living in institutional group housing, such as incarcerated persons or those living in college dormitories.

SAMPLE SIZE, RESPONSE AND COOPERATION RATES
The sample size (completed interviews), the response rate and the cooperation rate are provided in the table below.

Response and cooperation rates are measurements of overall survey participation among those sampled. More specifically, the Cooperation Rate is defined as the number of those who participated in the survey, divided by the number of individuals in the sample who were contacted and identified as eligible. The Response Rate is a more conservative measure and is defined as the number of individuals who participated in the survey, divided by the number of individuals in the sample who were contacted and identified as eligible, as well as those never contacted and those with unknown eligibility.

While there are multiple ways to calculate both these rates, the Health Department uses AAPOR's third definition (1) for the PAT, as detailed below for 2010–2011:

  • Full Sample: 3,908
  • Response Rate (AAPOR#3): 38%
  • Cooperation Rate (AAPOR#3): 92%

*RR and CR rates for 2010–2011 are combined landline and cell rates and include screening interviews with non-mobile New Yorkers. Complete telephone disposition reports are available for both the landline and cell-phone samples.

DATA ANALYSIS
In order to appropriately analyze PAT data, a weight is applied to each record. The weight consists of an adjustment for the probability of selection (number of adults in each household / number of residential telephone lines), sampling design (including disproportionate sampling by borough), as well as a post-stratification weight. Post-stratification weights were created by weighting each record up to the borough-level population, while taking into account the respondent's age, gender and race. Responses were also weighted to account for the distribution of the adult population comprising three telephone usage categories (landline only, landline and cell, cell only) using data from the 2008 New York City Housing and Vacancy Survey.

If you need assistance with the data, wish to suggest additional variables to be added, or have additional questions about the survey's methodology, please send an email to survey@health.nyc.gov .

(1) The American Association for Public Opinion Research. 2009. Standard definitions: Final Dispositions of Case Codes and Outcome Rates for Surveys. (PDF) 6th edition. Lenexa, Kansas: AAPOR.

Additional Resources