Those conducting a survey must first determine the sample from which they want to obtain data. Random selection is the most popular manner of selecting a representative sample. Surveys can usually be conducted in one of three ways: (1) mailing a questionnaire, (2) questioning by telephone, and (3) personal interviews. Designing the questions requires precision in wording, clarity of thought, and care not to take too much time. Simple data analysis can determine the central tendency, the range of answers, and how representative the sample was. Opinion surveys may themselves help deter crime and reduce fear of crime, while environmental surveys help police quantify the physical characteristics of neighborhoods and link them with specific neighborhood problems. These surveys help identify problems, determine what changes will help solve them, and measure the effectiveness of the efforts. Checklists, sample questions, tables, list of further readings, appended sample survey instruments, and 38 references