o Tabulate responses for important demographic characteristics and Field Work Error Review Data Collection Worker Characteristics Success Depends On Work Orientation o Extended Self Aptitude Discipline Third Ear Command Ability to Woo Ethical Supervision Requirements Sampling Control Control of Cheating Quality of Control and Editing Central Office Control key questions Editing Responses 1 Field Editing Performed by the interviewer Done as soon after the interview as possible Able to remember details Able to follow up if necessary Look for blanks inconsistencies 2 Office or Final Edit Again look for blanks and inconsistences Get hold of the interviewer while they are still in town Data Cleaning Identify Blunders Missing Data Leave Blank 5 s and 6 s in a 0 1 variable Mean substitution neutral value Most Often selected Delete case or just those with missing pairs DK NA Compare missing against other known answers Summary Identification Field Backup Data Sets Cleaning time is well spent Luck Coding covered in the Questionnaire Design section Total Error Random Sampling Error Non Sampling Error Response Error Non Response Error Researcher Error Interviewer Error Respondent Error Non Coverage Surrogate Information Error Respondent Selection Inability Error non response Measurement Error Questioning Error Unwillingness Error refusal Population Definition Error Recording Error really respondent not at home Sampling Frame Error Cheating Error Data Analysis Error Difference between the statistic and sampling distribution Is increasing the sample size the answer Error Components Sampling Error Non Sampling Error Non observational o Non coverage o Non response Refusal Sampling frame researcher interviewer judgment Quality of introduction incentives available scary informed consent sponsor anonymity confidentiality o Not at Home Busier Segments of the population Schedule of Call backs Observational o Data Collection errors Interviewer Bias based on background psychological and behavioral factors errors in asking probing recording and falsification Office processing errors o Editing Coding Tabulation Analysis o Is a poorly written survey a data collection or office problem Basic Analysis Goodness of Fit Compare actual with expected o Use chi square Works even with nominal data o Make use of known values for the population must have values from the population o Ho there are not significant differences between the observed and expected distributions List of stores purchased for a mail questionnaire o Stores were classified by sales revenue by the list owner Number of mutually exclusive categories k o Received 200 responses to the survey o Use Kolmogorov Smirnov Test Vodka Requires data that is at least ordinal o Again use need known values o Ho There are not significant differences between the observed and expected distributions Calculations