In additior. te sampling errors, mail-questionnaire data contain 
response bias errors which result in an inflated estimate of kill. Ex- 
perience has shown that these response errors are not consistent in size 
from one area to another nor from one year to the next in the same area. 
Also, they are large as compared to sampling error and their presence 
seriously limits the usefulness of survey data unless they are removed .2/ 
Methods for removing response bias errors have been developed2/ 
and the kill data presented in this report have been adjusted in accord- 
ance therewith. 
1] E. Le Atwood, Validity of Mail Survey Data on Bagged Waterfowl, 
Journal of Wildlife Management, Vol. 20, No. 1, pp. 1-16. 
2/ Ee Le Atwood, A Procedure for Removing the Effect of Response Bias 
Errors from Waterfowl Questionnaire Responses, Biometrics, Vol. 14, 
No. 1, March 1958. ¥ | 
6 
