1 survey research. 2 topics appropriate for survey research used for exploratory, descriptive &...
TRANSCRIPT
22
Topics appropriate for survey Topics appropriate for survey researchresearch
Used for exploratory, descriptive & Used for exploratory, descriptive & explanatory purposesexplanatory purposes
Probably best method to collect original Probably best method to collect original data for describing a population too large data for describing a population too large to observe directlyto observe directly
33
Guidelines for Asking Guidelines for Asking QuestionsQuestions
Choose appropriate question form: two optionsChoose appropriate question form: two options
– Open-endedOpen-ended--Respondent is asked to provide own --Respondent is asked to provide own answer to question answer to question
– Closed-endedClosed-ended--Respondent is asked to select an --Respondent is asked to select an answer from among a list provided by researcheranswer from among a list provided by researcher
Closed-ended questions require the categories of Closed-ended questions require the categories of answers to be exhaustive and mutually exclusiveanswers to be exhaustive and mutually exclusive
44
Guidelines for Asking Guidelines for Asking QuestionsQuestions
Make items clearMake items clear
– Babbie uses examples of "proposed peace Babbie uses examples of "proposed peace plan"...Which peace plan? plan"...Which peace plan?
– And, employment "last week"...Monday And, employment "last week"...Monday through Friday or Sunday through Saturday through Friday or Sunday through Saturday as the Census Bureau defines week? as the Census Bureau defines week?
55
Guidelines for Asking QuestionsGuidelines for Asking Questions
Avoid double-barreled questionsAvoid double-barreled questions
– Example:Example: "Did you walk to work or carry your "Did you walk to work or carry your lunch?" …..Yes or Nolunch?" …..Yes or No
– Regardless of the answer you get from the Regardless of the answer you get from the respondent, you don’t know what information respondent, you don’t know what information you have.you have.
66
Guidelines for Asking Guidelines for Asking QuestionsQuestions
Respondents must be Respondents must be competentcompetent to answer to answer
– Babbie uses example of asking students to indicate the percentage of fees to Babbie uses example of asking students to indicate the percentage of fees to be used for a long list of activities, about which the respondents have little be used for a long list of activities, about which the respondents have little knowledgeknowledge
Respondents must be Respondents must be willingwilling to answer to answer
– There may be a risk to the respondent in answering the questionThere may be a risk to the respondent in answering the question
– Reluctance may be due to nature of the information sought.Reluctance may be due to nature of the information sought.
– ExampleExample:: asking a staff member of a non-profit agency her/his opinion about asking a staff member of a non-profit agency her/his opinion about the leadership qualities of the administratorthe leadership qualities of the administrator
– Using a technique that guarantees anonymity or confidentiality greatly Using a technique that guarantees anonymity or confidentiality greatly increases R’s willingness to answer questionsincreases R’s willingness to answer questions
77
Guidelines for Asking Guidelines for Asking QuestionsQuestions
Questions should be relevant to the RespondentQuestions should be relevant to the Respondent
– Babbie uses example of Babbie uses example of fictitiousfictitious person, Tom Sakumoto person, Tom Sakumoto
9% of R's said they were familiar with him. 9% of R's said they were familiar with him. Shows R’s tendency to be helpful to researcherShows R’s tendency to be helpful to researcher
Short items are bestShort items are best
Avoid negative itemsAvoid negative items
– Possibility of misinterpretation is great Possibility of misinterpretation is great
– Babbie uses example of asking R to say if they agree/disagree with Babbie uses example of asking R to say if they agree/disagree with statement that "The U.S. should statement that "The U.S. should notnot recognize Cuba". recognize Cuba".
Often, R’s will “read over” the word Often, R’s will “read over” the word “NOT”“NOT”
88
Questionnaire ConstructionQuestionnaire Construction
General questionnaire format should be General questionnaire format should be uncluttereduncluttered
– Squeezed-together questionnaires are Squeezed-together questionnaires are disastrousdisastrous
Formats for respondents should be clean Formats for respondents should be clean and clearand clear
99
Questionnaire Construction, Questionnaire Construction, p.2p.2
Contingency questionContingency question
– A question that only applies to the R’s who A question that only applies to the R’s who answered a previous question in a particular answered a previous question in a particular “qualifying” manner“qualifying” manner
– Make sure that the directions for answering Make sure that the directions for answering the subsequent questions are clear for the the subsequent questions are clear for the respondentrespondent
1010
Contingency question, Contingency question, exampleexample
Have you ever been abducted by aliens?Have you ever been abducted by aliens?
– [ ] Yes[ ] Yes– [ ] No [ ] No (go to ques. # 4)(go to ques. # 4)
If yesIf yes: Did they let you steer the ship?
[ ] Yes
[ ] No
If yesIf yes: How fast did you go?
[ ] Warp speed
[ ] Weenie speed
1111
Questionnaire Construction, Questionnaire Construction, p.3p.3
Matrix questionsMatrix questions
– AdvantagesAdvantagesUses space efficiently, R's will probably complete it fasterUses space efficiently, R's will probably complete it faster
Format may increase comparability of responses to different Format may increase comparability of responses to different questions questions
– DisadvantagesDisadvantagesMay encourage researcher to use matrix format when another form May encourage researcher to use matrix format when another form would be betterwould be better
Can foster a response-set among R's in which they may develop a Can foster a response-set among R's in which they may develop a patternpattern
1212
Matrix question, Matrix question, exampleexample
Contact with criminal justice systemContact with criminal justice system
Have you ever…Have you ever…
YesYes NoNo Ref/DKRef/DK
Been a defendant in a criminal caseBeen a defendant in a criminal case 11 22 77
Been a witness in a criminal caseBeen a witness in a criminal case 11 22 77
Reported a crime to the policeReported a crime to the police 11 22 77
Been the victim of a crimeBeen the victim of a crime 11 22 77
1313
Questionnaire ConstructionQuestionnaire Construction
Ordering questions in a questionnaireOrdering questions in a questionnaire
– The appearance of one question can affect The appearance of one question can affect answers given to later ones answers given to later ones
– As remedy, do not make the questions As remedy, do not make the questions random, that will look chaotic to the R and random, that will look chaotic to the R and confuse the issue confuse the issue
– Safest solution is sensitivity to the problemSafest solution is sensitivity to the problem
1414
Questionnaire Construction, Questionnaire Construction, p.5p.5
Questionnaire InstructionsQuestionnaire Instructions
– Must be clear, concise and Must be clear, concise and COMPLETECOMPLETE
Pre-testing the questionnairePre-testing the questionnaire
– ALWAYS PRE-TEST!!!!ALWAYS PRE-TEST!!!!
1515
Comparing different survey methodsComparing different survey methodsChoosing among mail questionnaire, personal interview and Choosing among mail questionnaire, personal interview and
telephone surveytelephone survey
Factors influencing coverage and information Factors influencing coverage and information gatheredgathered
Mailed Mailed questionnairquestionnair
ee
Personal Personal interviewinterview
Telephone Telephone surveysurvey
Lowest relative costLowest relative cost 11 33 22
Highest % returnHighest % return 33 11 22
Highest accuracy of informationHighest accuracy of information 22 11 33
Largest sample coverageLargest sample coverage 33 11 33
Completeness, including sensitive materialCompleteness, including sensitive material 33 11 22
Overall reliability & validityOverall reliability & validity 22 11 33
Time required to gather informationTime required to gather information 33 22 11
Ease of gathering informationEase of gathering information 11 33 22
Total number of rankings—1,2,3Total number of rankings—1,2,3 2,2,42,2,4 5,1,25,1,2 1,5,11,5,1
Note: 1=most favorable ranking, 2=intermediate ranking, 3=least favorable rankingNote: 1=most favorable ranking, 2=intermediate ranking, 3=least favorable ranking
Source: Delbert Miller. Source: Delbert Miller. Handbook of Social Research Design and MeasurementHandbook of Social Research Design and Measurement, 5, 5thth Edition,1991, p. 168 Edition,1991, p. 168
1616
Strengths of survey researchStrengths of survey research
Useful in describing large populationsUseful in describing large populations
Are flexible in that you can ask many questions Are flexible in that you can ask many questions regarding your topicregarding your topic
Standardized questionnaires have strength Standardized questionnaires have strength regarding measurement generallyregarding measurement generally
– Survey researcher must ask the same question of all Survey researcher must ask the same question of all subjects subjects and…and…
– Impute the same intent to all respondents giving a Impute the same intent to all respondents giving a particular responseparticular response
1717
Weaknesses of survey Weaknesses of survey researchresearch
Standardized questionnaire items often Standardized questionnaire items often represent the least common denominator in represent the least common denominator in assessing people’s attitudes, etc.assessing people’s attitudes, etc.
Does not deal well with the context of social Does not deal well with the context of social lifelife
Can be inflexible…cannot change the survey Can be inflexible…cannot change the survey instrument if field conditions changeinstrument if field conditions change
1818
Weaknesses of survey Weaknesses of survey researchresearch
Subject to artificialitySubject to artificiality
– A person giving a conservative answer to a questionnaire does not A person giving a conservative answer to a questionnaire does not necessarily mean the person is conservativenecessarily mean the person is conservative
– Artificiality has two aspectsArtificiality has two aspects
Topic of study may not be amenable to measurement through a Topic of study may not be amenable to measurement through a questionnairequestionnaire
Studying the topic may affect it…Studying the topic may affect it…
– Asking someone whether they think the governor should be impeached Asking someone whether they think the governor should be impeached when R may have given no thought to it until asked for the opinionwhen R may have given no thought to it until asked for the opinion
1919
Quantifying data , CodingQuantifying data , Coding
System to translate the responses to questions to System to translate the responses to questions to numeric expressions that the computer can numeric expressions that the computer can processprocess
Two basic approaches to coding processTwo basic approaches to coding process
– Begin with developed coding schemeBegin with developed coding schemeBabbie uses occupation as example...but must use scheme that is Babbie uses occupation as example...but must use scheme that is appropriate for research questionappropriate for research question. .
– Generate codes from data that you collectedGenerate codes from data that you collected. .
2020
Using a developed coding Using a developed coding scheme, scheme, exampleexample
OccupationOccupation
– The question to the R would be: What is The question to the R would be: What is your occupation?your occupation?
– The R’s response is then placed in one of The R’s response is then placed in one of several categories that you have already several categories that you have already identifiedidentified
2121
Using a developed coding Using a developed coding schemescheme
What is your occupation?What is your occupation?
– Let’s say that the answer was Let’s say that the answer was “nurse”“nurse”
– Scheme 1: by typeScheme 1: by typeProfessional, managerial, clerical, semi-skilled, etc.Professional, managerial, clerical, semi-skilled, etc.
In this scheme, the R’s occupation would be placed in the In this scheme, the R’s occupation would be placed in the “professional”“professional” category category
– Scheme 2: by sector of the economyScheme 2: by sector of the economyManufacturing, health, education, commerce, etc.Manufacturing, health, education, commerce, etc.
In this scheme, the R’s occupation would be placed in the In this scheme, the R’s occupation would be placed in the “health”“health” categorycategory
2222
Using a developed coding schemeUsing a developed coding scheme
Note:Note: record the response of the R record the response of the R verbatimverbatim
Place the response into one of your pre-determined Place the response into one of your pre-determined categories during the data manipulation phasecategories during the data manipulation phase
– Use “recode” facility in SPSS Use “recode” facility in SPSS
Remember, you can always Remember, you can always “aggregate”“aggregate” data data
– Cannot Cannot “disaggregate”“disaggregate” data data
2323
Using a developed coding Using a developed coding schemescheme, , example, p.4example, p.4
What is your occupation?What is your occupation?
– Verbatim responsesVerbatim responses
R1:R1: “nurse” “nurse”
R2:R2: “sell shoes” “sell shoes”
R3:R3: “build cars” “build cars”
R4:R4: “manager at Wendy’s” “manager at Wendy’s”
R5:R5: “physician” “physician”
R6:R6: “computer programmer” “computer programmer”
R7:R7: “retired” “retired”
R8:R8: “soldier” “soldier”
TypeType SectorSector
professionalprofessional healthhealth
salessales commercialcommercial
semi-skilled semi-skilled laborlabor
commercialcommercial
managerialmanagerial commercialcommercial
professionalprofessional healthhealth
professionalprofessional information information techtech
retiredretired retiredretired
militarymilitary militarymilitary
2424
Generating codes from data Generating codes from data
collected,collected, exampleexample
Student responses to “biggest problem facing college today”Student responses to “biggest problem facing college today”
Responses can be coded as “academic” or “non-academic”Responses can be coded as “academic” or “non-academic”
AcademicAcademic Non-academicNon-academic
Tuition is too highTuition is too high xx
Not enough parking spacesNot enough parking spaces xx
Faculty don’t know what they’re Faculty don’t know what they’re doingdoing
xx
Advisors are never availableAdvisors are never available xx
Not enough classes offeredNot enough classes offered xx
Cockroaches in the dormsCockroaches in the dorms xx
Too many requirementsToo many requirements xx
Cafeteria food is infectedCafeteria food is infected xx
Books cost too muchBooks cost too much xx
Not enough financial aidNot enough financial aid xx
2525
Codebook constructionCodebook construction
End product of the coding process is the conversion of data End product of the coding process is the conversion of data items into numerical codesitems into numerical codes
These codes represent attributes composing variables which.... These codes represent attributes composing variables which....
Are assigned locations within a data fileAre assigned locations within a data file
– Location means the Location means the specific columnspecific column of the data file where, for of the data file where, for example, the responses for “gender” would occurexample, the responses for “gender” would occur
A A codebookcodebook is a document that describes the locations and is a document that describes the locations and lists the assignment of codes to the attributes composing lists the assignment of codes to the attributes composing those variablesthose variables
– It is the It is the fundamentalfundamental document of the research process document of the research process
2626
Codebook serves two Codebook serves two functionsfunctions
Primary guide for the coding processPrimary guide for the coding process
Guide to locating variables in the data Guide to locating variables in the data file during analysisfile during analysis
2727
Example of Coding InstructionsExample of Coding InstructionsPublic Attitudes: Crime, Drugs & Public ServicesPublic Attitudes: Crime, Drugs & Public Services
Enterprise Community/Wilmington/Statewide SurveyEnterprise Community/Wilmington/Statewide Survey
Variable Name (column location)Variable Name (column location) Value labelValue label
1. ID# (1-3)1. ID# (1-3) Continuous (001 through n)Continuous (001 through n)
2. Area (4)2. Area (4)
1= Westside, 2= West Center, 3= Delaware 1= Westside, 2= West Center, 3= Delaware AvenueAvenue
4= Southwest, 5= Eastside, 6= Northeast4= Southwest, 5= Eastside, 6= Northeast
7= Northwest, 8= New Castle, 9= Kent, 10= 7= Northwest, 8= New Castle, 9= Kent, 10= Sussex Sussex
3. Defendant in criminal case (5)3. Defendant in criminal case (5) 1=Yes, 2=No, 8=NA1=Yes, 2=No, 8=NA
4. Witness in a criminal case (6)4. Witness in a criminal case (6) 1=Yes, 2=No, 8=NA1=Yes, 2=No, 8=NA
5. Report crime to police (7)5. Report crime to police (7) 1=Yes, 2=No, 8=NA1=Yes, 2=No, 8=NA
6. Victim of crime (8)6. Victim of crime (8) 1=Yes, 2=No, 8=NA1=Yes, 2=No, 8=NA
2828
Data Cleaning...a fundamental Data Cleaning...a fundamental activityactivity
The process of detecting and correcting coding errorsThe process of detecting and correcting coding errors
Two typesTwo types
– Possible-code cleaningPossible-code cleaning--for any given variable there are only a --for any given variable there are only a specified set of codes possiblespecified set of codes possible
ExampleExample, gender--computer program would "beep" when an erroneous , gender--computer program would "beep" when an erroneous code is entered and refuse the codecode is entered and refuse the code
Family Court experience with gender codes Family Court experience with gender codes
– Contingency CleaningContingency Cleaning--process of checking only those cases that --process of checking only those cases that should have data on a particular variable should have data on a particular variable dodo in fact have such datain fact have such data