Laserfiche WebLink
The National Citizen SurveyT"' <br />Table 83: Survey Response Rate <br />Total sample used <br />I=Complete Interviews <br />P=Partial Interviews <br />R=Refusal and break off <br />NC=Non Contact <br />O=Other <br />UH=Unknown household <br />UO=Unknown other <br />Response rate: (I+P)/(I+P) + (R+NC+0) + (UH+UO) <br />Overall <br />I 1,600 <br />463 <br />2 <br />0 <br />0 <br />0 <br />0 <br />1,115 <br />29% <br />Confidence Intervals <br />It is customary to describe the precision of estimates made from surveys by a "level of confidence" and <br />accompanying "confidence interval" (or margin of error). A traditional level of confidence, and the one used here, <br />is 95%. The 95% confidence interval can be any size and quantifies the sampling error or imprecision of the survey <br />results because some residents' opinions are relied on to estimate all residents' opinions.2 <br />The margin of error for the City of Ramsey survey is no greater than plus or minus five percentage points around <br />any given percent reported for all respondents (465 completed surveys). <br />For subgroups of responses, the margin of error increases because the number of respondents for the subgroup is <br />smaller. For subgroups of approximately 10o respondents, the margin of error is plus or minus io percentage <br />points. <br />Survey Processing (Data Entry) <br />Upon receipt, completed surveys were assigned a unique identification number. Additionally, each survey was <br />reviewed and "cleaned" as necessary. For example, a question may have asked a respondent to pick two items out <br />of a list of five, but the respondent checked three; in this case, NRC would use protocols to randomly choose two <br />of the three selected items for inclusion in the dataset. <br />All surveys then were entered twice into an electronic dataset; any discrepancies were resolved in comparison to <br />the original survey form. Range checks as well as other forms of quality control were also performed. <br />Survey Data Weighting <br />The demographic characteristics of the survey respondents were compared to those found in the 2010 Census and <br />American Community Survey estimates for adults in the City of Ramsey The primary objective of weighting <br />survey data is to make the survey respondents reflective of the larger population of the community. The <br />characteristics used for weighting were sex and age. No adjustments were made for design effects. The results of <br />the weighting scheme are presented in the following table. <br />2 A 95% confidence interval indicates that for every 100 random samples of this many residents, 95 of the confidence intervals created will <br />include the "true" population response. This theory is applied in practice to mean that the "true" perspective of the target population lies <br />within the confidence interval created for a single survey. For example, if 75% of residents rate a service as "excellent" or "good," then the <br />4% margin of error (for the 95% confidence interval) indicates that the range of likely responses for the entire community is between 71% <br />and 79%. This source of uncertainty is called sampling error. In addition to sampling error, other sources of error may affect any survey, <br />including the non -response of residents with opinions different from survey responders. Though standardized on The NCS, on other surveys, <br />differences in question wording, order, translation and data entry, as examples, can lead to somewhat varying results. <br />34 <br />