Deck 19: Editing and Coding: Transforming Raw Data Into Information

Question 1

Coding requires transferring the meaning of written responses to numbers.

Answer 1

True

Question 2

Missing value is the technical term for items left blank.

Answer 2

False
The term is item nonresponse.

Question 3

A field supervisor checks for technical omissions such as blank pages on an interviewer form.

Answer 3

True

Question 4

Technology has reduced errors by checking for inconsistencies automatically.

Question 5

With respect to deletions for missing data,list-wise deletion means the data that the respondent did provide can still be used in statistical analyses.

Question 6

Dummy coding can be used for dichotomous responses like "yes "or "no."

Question 7

The process of data analysis begins before the data have been collected.

Question 8

Coding is the process of assigning a numerical score or other character symbol to previously edited data.

Question 9

The purpose of editing is to ensure that the data are complete,consistent,and readable.

Question 10

A record is a collection of related fields in a data file.

Question 11

The idea that the coding categories used should allow for all possible responses to the question is another way of saying that the data should be mutually exclusive.

Question 12

Editing is the same thing as coding.

Question 13

In-house editing rigorously investigates the results of data collection.

Question 14

A questionnaire with 5% or more of the responses is suspect and should be deleted from further analyses.

Question 15

Raw data are the facts that are in a form suitable for a decision.

Question 16

Mistakes that are made by the respondent in a phone survey are called nonrespondent errors.

Question 17

A string file is a collection of characters that represent a single type of data.

Question 18

One way to deal with missing values is to randomly select an answer.

Question 19

An important part of the editing,coding,and filing stages of data analysis is checking for errors.

Question 20

A data editor may have to reconstruct data.

Question 21

____ is the technical term for items left blank.

A)Imputation
B)Item plug
C)Item nonresponse
D)Item inconsistency

Question 22

Assigning a "1" or "0" code where each number represents an alternate response such as "yes" or "no," is an example of:

A)editing
B)dummy coding
C)reverse coding
D)plugging

Question 23

When a field interviewer records an impossible answer (e.g.birthdate: 1861),this means that the data need to be:

A)edited
B)transformed using a plug value
C)coded
D)deleted

Question 24

All of the following are choices available when dealing with missing data EXCEPT:

A)leave the response blank
B)randomly select an answer
C)insert the mean value of a variable for the missing response
D)tabulate the data

Question 25

Kelsea is an interviewer and incorrectly entered respondents' choices on ten surveys.This type of error is called:

A)nonrespondent error
B)respondent error
C)random error
D)editing error

Question 26

A data sheet documents the location of each variable in a data matrix.

Question 27

Many researchers use a statistical process to provide an educated guess for missing responses in data based on the respondent's choices to other questions.Which method of dealing with missing data does this represent?

A)impute a missing value
B)plug in a neutral response
C)plug in alternative choices for missing data
D)randomly select an answer

Question 28

The purpose of coding open-ended questions is to reduce the large number of individual responses to a few general categories of answers that can be assigned numerical codes.

Question 29

Assigning males the value of zero and females the value of one in a database to record the gender of the respondents is an example of:

A)coding
B)test tabulation
C)editing
D)verification

Question 30

Which of the following need to be corrected as part of the editing process?

A)omissions
B)legibility
C)consistency
D)all of the above

Question 31

The assignment of numbers to edited data is known as:

A)editing
B)adjusting with a plug value
C)coding
D)all of the above

Question 32

When Arbitron has its own staff verify the accuracy of radio-station call letters (e.g.KMOX)to ensure that they are possible radio call letters in the geographical area of the respondent,this is an example of:

A)external editing
B)in-house editing
C)in-house coding
D)external coding

Question 33

The unedited responses from a respondent exactly as indicated by that respondent are referred to as:

A)codes
B)files
C)raw data
D)strings

Question 34

When a coding method produces more categories than are deemed important during a later stage of the research,the categories can be reduced to a smaller number of categories by combining categories.

Question 35

Precoding is the tallying of a small sample of the total number of replies to a particular question,

Question 36

A method of handling missing data in which only the actual variables for a respondent that do not contain information are eliminated from use in statistical analyses is called:

A)list-wise deletion
B)pair-wise deletion
C)selective deletion
D)partial deletion

Question 37

Which of the following refers to the notion that the data file actually contains the information that the researcher is trying to obtain to adequately address research questions?

A)data reliability
B)data verification
C)data completeness
D)data integrity

Question 38

When a survey is highly unstructured,it is possible to precode the response categories before the data are collected.

Question 39

Codes are rules for ____ data.

A)interpreting
B)classifying
C)recording
D)all of the above

Question 40

A researcher has decided to insert a response for items not answered by respondents.This answer the editor inserts is referred to as a(n):

A)proxy value
B)simulated value
C)imputation
D)plug value

Question 41

A collection of characters that represents a single type of data,usually a variable,is called a:

A)field
B)data file
C)value label
D)string file

Question 42

A collection of related records is known as a:

A)data file
B)code
C)record
D)field

Question 43

Valarie's job at a research firm is to transfer data from survey questionnaires to a computer file.Her job is:

A)data entry
B)data coding
C)data editing
D)data scanning

Question 44

In creating coding categories for open-ended questions,the tallying of the replies to a small number of completed questionnaires for a question in order to create coding categories for that question is known as:

A)recoding the data
B)test tabulation
C)data entry
D)creating a plug value

Question 45

When a phone survey tries to obtain the opinions of registered voters (who need to be age 18+),and the field editor finds an interview in which the respondent was only 17 years old,the field editor should ____________________ this survey.

Question 46

A data processing input device that reads material directly from mark-sensed questionnaires is called a(n):

A)direct-entry mode
B)verified entry system
C)tabulation scanning system
D)optical scanning system

Question 47

Which term represents a computer terminology for a series of alphabetic characters (non-numeric characters)that may form a word and is used to represent text variables?

A)value label
B)string character
C)data matrix
D)word matrix

Question 48

A collection of related fields that represents the responses from one sampling unit is known as a:

A)file
B)record
C)code
D)label

Question 49

A survey question asked respondent how much of the Super Bowl they watched by asking them to check one of the four following choices: "all of it," "most of it," "some of it," or "none of it." How many dummy variables would a researcher need to dummy code this question?

A)one
B)two
C)three
D)four

Question 50

Which of the rules for coding has been violated by the following responses to a question about annual salary?

A)Coding categories should be exhaustive.
B)Coding categories should be mutually exclusive.
C)Coding categories should be test tabulated.
D)Coding categories should be alphabetic only.

Question 51

When a field supervisor checks data at the end of each day that it is collected to catch technical omissions (e.g.missing responses to questions),this is an example of ____________________.

Question 52

The process of checking and adjusting data for omissions,legibility,and consistency is known as ____________________.

Question 53

Which of the following can be used if the researcher knows what answer categories exist before data collection occurs?

A)test tabulation
B)sheet coding
C)precoding
D)field editing

Question 54

Which of the following is an alternative to dummy coding using the values of -1 and +1 to represent two categories of responses?

A)reverse coding
B)inverse coding
C)effects coding
D)verified coding

Question 55

In test tabulation,what is the typical percentage of responses from completed questionnaires that a researcher will use to create coding categories?

A)10 percent
B)20 percent
C)30 percent
D)50 percent

Question 56

A researcher has assigned "1" to represent freshman,"2" for sophomore,"3" for junior,"4" for senior,and "5" for graduate student.These labels (i.e. ,freshman,sophomore,etc. )assigned to the numeric code are called:

A)value labels
B)coding labels
C)cues
D)strings

Question 57

When a research organization does the editing of its data using its own staff,this is known as ____________________ editing.

Question 58

A question on a survey that has not been answered by the respondent is called a(n)____________________.

Question 59

The idea that the coding categories applied to a given question should allow all possible answers to the question to receive a code is another way of saying that the coding categories should be:

A)mutually exclusive
B)precoded
C)exhaustive
D)all of the above

Question 60

Which of the following means that coding categories have no overlap so that a subject or response can be placed in only one category?

A)exhaustive
B)mutually exclusive
C)unique
D)precoded

Question 61

When a word or a short phrase can be associated with a numeric code,this code is called a(n)____________________.

Question 62

Explain how researchers handle missing data.

Question 63

The activity of transferring data from a research project to computers is called ____________________.

Question 64

Compare and contrast list-wise deletion and pair-wise deletion methods for handling missing data and discuss which one is used most today.

Question 65

Discuss the two basic rules for code construction.

Question 66

A(n)____________________ documents the location of each variable in a data matrix.

Question 67

Define field editing and list the three things a field supervisor is looking for when conducting field editing.

Question 68

Assigning numbers to edited data is known as ____________________.

Question 69

A collection of related records that make up a data set is called a(n)____________________.

Question 70

A coding scheme that has a code for all possible responses is said to be ____________________.

Question 71

Constructing coding categories by tallying a small number of responses to a particular question is known as ____________________.

Question 72

Discuss the elements of data files,such as field,string characters,record,data file,and value label.

Question 73

A method of handling missing data in which only the actual variables for a respondent that do not contain information are eliminated from use in statistical analyses is called ____________________.

Question 74

A data processing device that reads data from mark-sensed surveys into the computer is called a(n)____________________ system.

Question 75

When an editor replaces a missing answer to a question with a random response from among the fixed-alternative responses for that question or inserts a neutral response,the number inserted is called a(n)____________________.