Deck 1: Life in a Data-Laden Age: Finding and Managing Datasets

Question 1

A researcher assigns numbers to the categories of a variable in a dataset she is creating. These numbers are typically referred to as:

A) attributes
B) codes
C) cells
D) signifiers

Answer 1

B

Question 2

The most specific term to describe the process of taking a variable with five categories and using it to create a variable with three categories is called:

A) recoding
B) reclassification
C) collapsing
D) indexing

Answer 2

C

Question 3

John takes several variables and adds them together. He is engaging in the process called:

A) recoding
B) reclassification
C) collapsing
D) indexing

Answer 3

D

Question 4

Shahida's dataset has a respondent with a missing value on a particular variable. Based on what this respondent's values are on other variables, Shahida makes an educated guess as to what this missing value would likely be. Shahida is engaging in:

A) recoding
B) data mining
C) imputation
D) reclassification

Question 5

A set of questions in a survey that may be used in one year of a survey but not another year is called:

A) a dataset
B) a module
C) a corpus
D) a topic

Question 6

A survey that uses the same respondents over an extended period of time is called a

A) generalizable survey
B) cross-sectional survey
C) time-series analysis
D) longitudinal survey

Question 7

The General Social Survey would not be a good choice if you were interested in the opinions of:

A) children
B) prisoners
C) residents of mental institutions
D) all of the above

Question 8

The 2012 American National Election Studies did not use which of these modes of administration:

A) face-to-face
B) Internet
C) mail
D) all were used

Question 9

The World Values Survey has been collecting data since:

A) 1941
B) 1961
C) 1981
D) 2001

Question 10

The unit of analysis of the original World Values Survey is:

A) the individual
B) the family
C) the city
D) the country

Question 11

Which of the following is NOT a topic covered by the Pew Internet, Science, and Tech Project surveys used in the textbook?

A) scientific knowledge
B) health
C) dating
D) jobs

Question 12

A researcher wants to study how wealth is passed down from generation to generation. The best dataset to use for this is called:

A) The National Educational Longitudinal Survey
B) The National Longitudinal Study of Adolescent Health
C) The National Survey of Families and Households
D) The Panel Study of Income Dynamics

Question 13

A researcher wants to study friendship networks among teenagers. The best dataset to use for this is called:

A) The National Educational Longitudinal Survey
B) The National Longitudinal Study of Adolescent Health
C) The National Survey of Families and Households
D) The National High School Friendship Survey

Question 14

The most common measure of index reliability is called:

A) Amado's theta
B) Bertrand's sigma
C) Cronbach's alpha
D) Dorchester's beta

Question 15

A researcher assesses the reliability of his index, and finds that the Cronbach's alpha is 0.15. The researcher would want to:

A) proceed, as this alpha value is good
B) proceed with caution, as this alpha value is questionable
C) proceed only if he adds another variable to the index
D) stop and reassess, as the variables in his index do not go together well.

Question 16

A common criticism of the Body Mass Index measure is:

A) it works only for men
B) it doesn't take muscle into account
C) it doesn't apply to children
D) it applies only to the morbidly obese

Question 17

A researcher studies the presence of the word "change" in political speeches. She is engaging in:

A) survey research
B) indexing
C) content analysis
D) recoding

Question 18

A variable with categories that cannot be ranked is at the ______ level.

A) nominal
B) ordinal
C) lowest
D) ratio

Question 19

A variable that has a meaningful zero is at the ______ level.

A) nominal
B) ordinal
C) ratio
D) highest

Question 20

Because of its special characteristics, a dichotomy can be considered to be measured at which level?

A) nominal
B) ordinal
C) interval
D) ratio

Question 21

A statistical technique that allows us to make connections between samples and populations is called:

A) a generalizable technique
B) a sample technique
C) an inferential technique
D) an explanatory technique

Question 22

Here is a claim statement: education affects income. In this claim, education is the _________ variable and income is the _____________ variable.

A) independent, dependent
B) dependent, independent
C) nominal, ratio
D) affecting, effected

Question 23

Curington and her co-authors used data from an online dating website in order to study which social characteristic?

A) age
B) sexual orientation
C) race
D) gender identity

Question 24

Vasi and his co-authors studied the effects of which environmental film?

A) An Inconvenient Truth
B) Gasland
C) Silent Spring
D) WALL-E

Question 25

In Vasi's article on an environmental film, the occurrence of local protests was:

A) an independent variable in his study
B) a dependent variable in his study
C) both an independent variable and a dependent variable in his study
D) neither an independent variable nor a dependent variable in his study

Question 26

A researcher wants to collapse a five-category marital status variable into a two-category marital status variable. Explain two reasons why the researcher might want to do this.

Question 27

What is an index and why is it useful?

Question 28

Explain how you would combine these two variables into an additive index. End with a description of what the completed index would look like:
Variable 1: How happy are you? Codes: 0=Very happy, 1=Pretty happy, 2=Not at all happy
Variable 2: How satisfied are you with life? Codes: 0=Not at all satisfied, 1=Fairly satisfied, 2=Very satisfied

Question 29

Someone tells you the index you just built is unreliable. How would they likely be able to tell this, and what does this mean?

Question 30

What is the method of content analysis, and why is it more prevalent these days?

Question 31

You want to do a lot of statistical analyses about people's educations. You have two variables DEGREE (highest educational degree: high school diploma, associate's degree, bachelor's degree, masters degree) and EDUC (number of years of education). In relation to levels of measurement, explain which one you would choose and why.

Question 32

Temperature is considered to be an interval-level variable, which is between the ordinal level and the ratio level. Using temperature as an example, explain why interval is a higher level of measurement than ordinal, but a lower level of measurement than ratio.

Question 33

Explain why inferential statistics are so important to social scientists.

Question 34

Using the example of environmental attitudes, describe what descriptive, explanatory, and inferential statistics are.

Question 35

Rhetta (a black woman) conducts face-to-face surveys with fellow students from many races in order to assess their attitudes toward the Black Lives Matter movement. Explain why Rhetta may encounter social desirability bias, getting across that you know what this bias is.