TECHNICAL REPORT 2001-2002 TEXAS CRIME POLL
The postal addresses were purchased from a commercial sampling company, Survey Sampling, Inc. (http://www.surveysampling.com/ssi_home.html). They provided a systematically selected sample of names and postal addresses selected from the most current white page telephone directories throughout the state (sorted by county, ZIP Code, area code and telephone exchange) The sample was distributed proportionately across all counties in Texas and was collected as follows:
Samples are first systematically stratified to each county in Texas. The sum of the total listed telephone households throughout the State was then calculated and divided by the desired sample size (3,044) to produce a sampling interval.
The counties were then listed in alphabetical order by county within the state of Texas. A random number between zero and one was generated and multiplied by the sampling interval to calculate a random starting point between one and the sampling interval. A cumulative count of elements was calculated. At the point at which the accumulation reaches the random starting point, a specific county was selected and the next sampling point was one interval away. Accumulation continued in this fashion until the entire sample was selected.
For example if the total number of telephone/mail records available were 1,000 and we required 100 numbers. Then sampling interval would be calculated by dividing 1,000 by 100. Therefore the sampling interval includes every tenth record. Then from a random start between 0 and 9 e.g. 4 every 10th number would be selected. 4th, 14th, 24th, etc.
Survey Instruments Mailed: 3,114
Bad addresses or late returns: 91
Survey Instruments Completed: 821
RESPONSE RATE: 821/(3,114 91) = 27.15%