social science statistics 1

What are the 3 reasons the authors of your textbook give for using SPSS to learn statistics?

"pretty much every social scientist uses or has used it," "it is a nice way to get familiar with using computer programs to do statistics, and could be useful if you decide to really get into this stuff and learn to use other statistics programs," "it's available for both Windows and Mac"

Suppose that a household in a certain neighborhood makes more than all other neighbors, say $125,000 per year. Further suppose the range of income in this neighborhood is $50,000. How much does the household earning the least earn per year?

$75,000

Which of the following measures would be appropriate for the variable SEXEDUC, which contains the response categories "favor" and "oppose?"

...

Create a frequency distribution and an appropriate measure of central tendency for the variable "health." While 23.5% of respondents reported that they are in "excellent" health, _____[%] of respondents reported that they were in either "fair" or "poor" health.

27.2

Create a frequency distribution and an appropriate measure of central tendency for the variable "health." _____[%] of respondents to the 2016 GSS reported that they are in "good" health.

49.2

Create a frequency distribution and an appropriate measure of central tendency for the variable "tvhours." Using the mean and standard deviation, we can say that approximately two-thirds of the distribution watches between 0.20 hours and _____ hours per day of television.

5.76

Create a frequency distribution and an appropriate measure of central tendency for the variable "race." The largest group of respondents to the 2016 GSS by race was "White," who make up _____[%] of the sample.

73.7

Create a frequency distribution and an appropriate measure of central tendency for the variable "teensex." Exactly _____[%] of respondents to the 2016 GSS believe that sex before marriage, particularly for teens 14 to 16 years of age, is either "always wrong" or "almost always wrong."

77.5

Which of the following variables could be considered a continuous variable? gender number of siblings class rank age

age

Mode, median, and mean are measures of:

central tendency

A primary goal of social scientific research is to examine _____ that constitute our knowledge of the social world and then develop them into theories that help us make sense of the social world.

concepts

"A primary goal of scientific research is to examine the various _____ that constitute our knowledge of the social world and then develop them into _____ that help us explain, understand, and make sense of the social world." (p. 6)

concepts; theories

A ______ is a numeric display of the number of times (frequency) and the relative percentage of times each variable occurs in a given sample.

frequency distribution

The _____ is only appropriate for scale-level variables.

mean

The _____ is the middle-most case in a distribution. Statistics like "median household income" are resistant to outliers.

median

The measure that divides a distribution into two equal parts so that half of the cases are above and half are below it is referred to as the:

median

Which measure of central tendency is most appropriate to summarize the distribution of "health"?

median

Which measure of central tendency is most appropriate to summarize the distribution of "teensex"?

median

Which of the following is not a variable? hours spent on social media, age, race, middle class

middle class

In the GSS, the value labels NA ("no answer"), DK ("don't know"), and IAP ("inapplicable") are known as _____ data.

missing

The two main views (or tabs) in the SPSS Data Editor window are called _____ ___ ____ _____ ___.

data view and variable view

The SPSS Data Editor window contains two views. One is called ______ _____, and it contains "raw" data for analysis. The other view contains information about the data, and is called ______ ____.

data view; variable view

The _____ is the most commonly occurring value in a distribution. When working with a nominal-level variable, this is the only measure of central tendency that makes sense.

mode

The variable NEWSFROM asks GSS respondents about their main source of news information. Which of the three measures of central tendency is most appropriate for the variable NEWSFROM?

mode

Which measure of central tendency is most appropriate to summarize the distribution of race?

mode

Which of the following measures would be appropriate for the variable SEXEDUC, which contains the response categories "favor" and "oppose?"

mode

As a general rule, the smaller the sampling error, the _____ likely the data are representative of the population.

more

The Deprivation Theory of Religiosity states that people who have less (i.e. are deprived) relative to others in society would be expected to be _____ religious than those who are not socially deprived.

more

Are respondents to the 2016 GSS generally satisfied that the government is doing enough to halt the rising crime rate ("natcrime") and deal with drug addiction (natdrug)? Produce and analyze frequency distributions, appropriate measures of central tendency and dispersion for both variables in order to answer this question. (Hint: Consider the level of measurement of each variable before producing descriptive statistics.)

no, GSS respondents are generally not satisfied that the government is doing enough to halt the rising crime rate.

A researcher measures marital status by asking respondents whether they are currently married, widowed, divorced, separated, or never married. The level of measurement for this variable is.....

nominal

A variable that asks respondents' Religion (with possible categories such as Protestant, Catholic, Jewish, Muslim, Hindu, etc.) would be considered a _____-level variable.

nominal

Categorical variables can be unranked, as in the case with _____ variables, or they can be rank-ordered, as with _____ variables. _____-level variables contain rank-ordered categories that are equidistant, the distance between those categories is known to us.

nominal; ordinal; scale

"Given the sheer number of _____ commonly made by social scientists, researchers need a database to take into account all relevant data in their research."

observations

Likert-scale type questions, where respondents are given a range of categories such as "extremely satisfied," "somewhat satisfied," "neither satisfied nor unsatisfied," "somewhat unsatisfied," and "extremely satisfied" would be considered _____-level variables.

ordinal

_____ data analysis is when you collect and analyze your own data. When you re-analyze data that was collected by someone else, you are engaging in _____ data analysis.

primary; secondary

The _____ is the difference between the highest and lowest scores in a distribution.

range

When a meteorologist gives a weather forecast, they are reporting a predicted _____ within which the lowest and highest air temperatures ought to vary during a day.

range

A criminologist is interested in studying why people sometimes re-offend after being released from prison. She decides to test the following hypothesis— Increased rehabilitation efforts and programs will lead to a decreased rate of re-offending. What is the dependent variable in this scenario?

re-offending

Imagine that you work as an interviewer at a social science research organization, and you overhear one of your co-workers reading survey questions slightly differently than they are written. What measurement "problem" might arise from this inconsistency?

reading a survey question differently could generate inconsistent results since respondents were not all answering the exact same question. inconsistency is indicative of a "reliability" problem. (note that our results would also have "validity" issues, but these issues would stem fundamentally from the reliability problem previously mentioned.)

Sometimes we run into problems when trying to convert our concepts into variables. These Problems often stem from our concerns with creating measurements that are both _____ and _____.

reliable; valid

Each row (horizontal) in Data View represents a person or _____ to the survey (what is sometimes referred to as a case).

respondent

As a general rule, the less _________ ____there is in a sample, the more that sample is representative of the population from which the sample was drawn.

sampling error

If a survey asks for a respondent's age in years, the level of measurement for this variable would be ____.

scale

The mean is an appropriate measure for _____ variables.

scale

Which of the following is generally considered the "highest" or "most precise" level of measurement? nominal, ordinal, scale (interval-ratio)

scale (interval-ratio)

Why do we always read from the "Valid Percent" column rather than the "Percent" column?

the valid percent column excludes missing data, and we do not normally analyze missing data

"A primary goal of social scientific research is to examine the various concepts that constitute our knowledge of the social world and then develop them into _____ that help us to explain, understand, and make sense of the social world."

theories

What is wrong with the following categories for the variable Marital Status: Married Single Divorced Widowed Never Married Separated

they are not exclusive

The line of buttons running from left to right directly below the Menu Bar is called the _____.

toolbar

t or f: Inductive research begins with data, and concludes with theory construction, while deductive research begins with a theory, from which a hypothesis is derived and tested with data.

true

If a researcher wants to find information on the variables in a data file, which of the following Menu Bar commands should be used?

utilities > variables

Theories are to concepts as hypotheses are to _____.

variables

Suppose that a researcher is interested in studying people's religious habits. She reviews the research literature on religiosity and comes across the "Deprivation Theory of Church Involvement." Using what she learned from the theory, the researcher develops hypotheses, and then conducts statistical tests with GSS data to evaluate the relationship between income and church attendance. This type of research is an example of...

deductive research

The _____ variable is the variable you are trying to explain.

dependent

The _____ variable refers to the variable that the researcher is trying to explain or predict.

dependent

Hypotheses contain a(n) _____ variable (which is the variable that you are trying to explain) and a(n) _____ variable (which is the variable hypothesized to influence the other variable).

dependent; independent

_____ refer to different aspects of a concept. For example, the concept of religiosity might involve church attendance, prayer, belief in an afterlife, and so forth.

dimensions

Range, interquartile range, and standard deviation are measures of:

dispersion

The categories of each variable should meet what two requirements?

exhaustive and exclusive

Which of the following best describes sampling error?

the difference between the population we are interested in studying and the sample to which we have access.

Are the educational backgrounds of GSS respondents' parents similar? Produce and analyze frequency distributions, appropriate measures of central tendency and dispersion for "maeduc" and "paeduc" in order to generate your answer. (Hint: Consider the level of measurement of each variable before producing descriptive statistics.)

the educational backgrounds of GSS respondents' parents are similar, as evidenced by a comparison of their central tendencies. however, measures of dispersion show more variability among respondents' fathers compare to respondents' mothers.

Among other things, what can the standard deviation tell us about certain distributions?

the range of the (approximate) middle two-thirds of a distribution

Scale-level variables' dispersion can be appropriately measured using...

the range, the interquartile range, and the standard deviation

Create a frequency distribution and an appropriate measure of central tendency for the variable "teensex." Only _____[%] think it is "not wrong at all," whereas 12% think it is "sometimes wrong."

10.5

Create a frequency distribution and an appropriate measure of central tendency for the variable "educ." Using the mean and standard deviation, we can say that approximately two-thirds of the distribution lies between _____ years and 16.66 years of educ.

10.98

Create a frequency distribution and an appropriate measure of central tendency for the variable "educ." The average number of years of education of 2016 GSS respondents is _____.

13.82

Create a frequency distribution and an appropriate measure of central tendency for the variable "race." The second-largest group was "Black," with _____[%].

16.7

Most of the GSS data used in this class come from the responses of a representative sample of _____ adult Americans in 2016.

2,867

Create a frequency distribution and an appropriate measure of central tendency for the variable "tvhours." Respondents to the 2016 GSS report watching _____ hours of television per day on average.

2.98

When were the data discussed in Chapter 3 collected?

2016

What does GSS stand for?

General Social Survey

As a general rule, the _____ the sampling error, the less likely that the data are representative of the population.

larger

Identify the independent variable in the following hypothesis: Today, young Americans earn less on average than their parents' generation earned in the labor market.

generation (age)

The _____ variable is the variable hypothesized to lead to, or explain variation in another variable.

independent

If a researcher was interested in finding out which cases comprise the middle 50% of a distribution, and can be combined with the mean to find the range of the middle two-thirds (approximately) of a distribution.

interquartile range

Which of the following measures can tell us where the middle 50% of a distribution lies?

interquartile range

Suppose a person weighs themselves with the prior knowledge that they weigh about 150 pounds, and yet the scale reads 189 pounds. They step off the scale, and then back on. The scale again reads 189 pounds. What kind of measurement problem does this scale have?

it is not valid

Knowing a variable's level of measurement is important for ________ __ _______ ______ ____, since the type of information contained in a variable determines what can be said about the data.

selecting an appropriate statistical tool

Among many other uses, the _______ represents the average variability in a distribution, and can be combined with the mean to find the range of the middle two-thirds (approximately) of a distribution.

standard deviation

What 2 considerations should be kept in mind when constructing categories for a variable?

the categories should be exhaustive and (mutually) exclusive