POLS 2900 2nd midterm

midterm

A nominal variable can have only three categories

False

To determine whether a variable has criterion-related validity, figure out whether it accurately predicts a set of interrelated variables.

false

If not entirely sure how you’re going to use collected data, it is best to operationalize your variables as ratio, as opposed to ordinal, measures

false

The key difference between an index and a scale is that index items are weighted, whereas scale items are not

false

A set of questionnaire items that formed a Guttman scale on one data set will always form a Guttman scale on another data set.

False

You should always include at least one item in an index on which all respondents give the same answer.

False

In research, the statistic is more accurate than the parameter

false

A confidence interval at the 68% confidence level will be larger than one constructed at the 95% confidence level

false

findings based on a sample can be taken as representing only the aggregation of elements from which the sample was drawn, not the entire population

true

open-ended questions are comparable to essay questions on an exam, while closed-ended questions are comparable to multiple choice question so on an exam

true

When conducting a face-to-face survey, it is essential that interviewers use probes to elicit more information in response to closed-ended questions.

false

The viewpoint of the researcher should always be made clear when writing survey questions.

false

What is a nominal variable

Categories exhaustive and mutually exclusive.

Political scientists would not accept the operationalization of political ideology as eye color because such measurement lacks

validity

Imagine you collect data on how voters feel about gun control when you are actually interested in how much they know about what federal gun control measures are currently in place. You have an operationalization problem concerning

the specific dimension of the variable to be studied.

What should social scientists take into account when considering use of a composite measure

Item has face validity, sufficient variance, unidimensional

Why do social scientists use composite measures

unable to measure a complex concept with a single item, single item can’t provide sufficient variation, composite measures efficiently achieve data reduction.

Coefficient of reproducibility is only appropriate when using

Guttman scale

Coefficient of reproducibility must stay below

.5

You want to examine the relationship between sex and partisanship. You use as your sample all the students in your research methods class. What kind of sampling design are you using?

reliance of available subjects

I would like to survey 50 people on their attitudes regarding Bowling Green's "Not In My Town" campaign. I choose to stand on the corner of Main St. and Wooster, and give my short survey to the first 50 people who pass by the corner, I have engaged in ____________.

reliance on available subjects or convenience sampling

You are doing research on hospital personnel - orderlies, technicians, nurses, and doctors. You want to be sure you draw a sample that has cases in each of the personnel categories. You want to use probability sampling. An appropriate strategy would be

stratified sampling.

You want to examine the relationship between party identification and religion. You use as your sample all of the members of 3 churches located near campus. What kind of sampling design are you using?

reliance on available subjects

A researcher discovered that 40% of the households in City X are Republican households and that 60% are Democratic households. The researcher sends interviewers into the field and tells them to conduct 80 interviews and that 40% of their interviews should be with Republican households, and 60% should be with Democratic households. Since this is all the researcher tells the interviewers, this research uses

quota sampling.

What is the **chief** problem with the following survey question, asked of a random sample of US adults?

 

**Do you think the presidential campaigns should be publicly funded and limited to a 6-week period?**

It is double-barreled.

sampling interval calculation- standard distance between elements selected from a population.

 K= study population size/ sample size

Sampling ration- proportion of elements in a population selected for inclusion in sample.

sample size/ study population size

How do you do systematic sampling?

Assign a single number to every member of the study population, choose a random start, include every Kth element in the sample.

How do you random sample

Assign a single number to every member of the study population, use a random number generator to select sample members.

How do you do stratified sampling?

stratify list, draw a systematic sample. Organize list based on every element

Coefficient of reproducibility

1- number of errors/ number of guesses

\
number of guesses = number of survey questions \* respondents

How to calculate response rate

\# completed surveys/ # surveys attempted

\
50%- adequate

60%- good

70% or higher- very good