ch 4 Flashcards
two types of statistics
descriptive
inferetial
three types of non-probability sampling
convenience sampling
snowball sampling
quota sampling
multi-stage cluster sampling involves _______stages
two or more
- selecting clusters (groups of elements)
- selecting subunits within cluster
- randomly sampling within the clusters
what are multi-stage cluster sampling used for
large populations (no adequate sampling frame, elements are geographically dispersed)
how to select a stratified random sample
stratify the population (divide into subgroups)
select a simple random sample or a systematic sample from each stratum
in stratified random sampling ensure that _____ in the population of ______ represented in the sample
subgroups
proportionally
explain systematic sample
selected from sampling framing (no random. numbers)
- choose a number at random from 1 to i (size of sampling interval)
- this number is known as a random start
about what percent of all sample means lie within 1.96 standard errors off the mean
95%
what is a sampling frame
a list of elements in the population
how many people you ask to get a good estimate depends on
the level of variability
when there is low variability you do not have to ask as many people to get an ______ response
accurate
four types of probability samples
simple random sample
systematic sample
stratified random sampling
multi-stage cluster sampling
what does standard error of the mean measure
probability samples with sufficient sample sizes that have minimal sampling error
probability samples with sufficient sample sizes minimize the amount of
sampling error (but it is still bound to occur)
is it virtually impossible to eliminate sampling error, why?
yes, using random samples and making the samples as large as possible helps to minimize sampling error
when do errors of estimation occur
when there is a discrepancy between the sample and the total population
Sampling
the selection of a subset of a population
for observation
what are the two main sampling types
- Probability: Uses random selection methods, associated
with quantitative methods. - Non-probability: Does not use random selection methods,
associated with qualitative research.
systematic
A probability sampling method in which units are selected from a sampling frame at fixed intervals (for example, every fifth un
cluster sample
A procedure in which the researcher first samples sets of cases (“clusters”) and then samples units within them, usually using a probability sampling method.
non-probability sampling
A sample selected using a non-random sampling method. Essentially, this means that some units in the population are more likely than others to be selected.
quota sampling
A type of non-probability sample that matches the proportions of people in different categories in the population
sampling error
Differences between the characteristics of a random sample and the population from which it is selected.
Element or unit:
A single case in the population. In the social sciences that element or unit is usually a person, but many other things can be sampled as well: nations, cities, regions, schools, firms, and so on. Finch and Hayes (1994), for example, based part of their research on a random sample of wills of deceased people
population
All the cases about which you are seeking knowledge, or all the cases to which your conclusions are meant to apply
sampling frame
The list of elements from which the sample will be selected
probability sample
A sample selected using a random process such that each unit in the population has a known chance of being selected. The aim of probability sampling is to keep sampling error (see below) to a minimum
Non-response
A situation that occurs whenever some unit selected for the sample refuses to participate in the study, cannot be contacted, or for some other reason does not supply the required data.
Census:
Data collected from all elements in the population rather than from a sample. The phrase “the census” typically refers to the enumeration of all (or nearly all) members of the population of a nation-state—that is, a national census
Sampling error
An error of estimation that occurs if there is a difference between the characteristics of a sample and those of the population from which it was selected. Sampling error can occur even when a random method is used
what is the sampling ratio
n/N
systematic sample is directly from the
sampling frame without using random numbers
In systematic sampling, it is important to ensure that there is no
pattern or ordering, a feature called periodicity.
in systematic sampling is there equal chance of being picked
not every possible combination of cases has an equal chance of being selected
stratified random sampling
A sample in which units are randomly sampled from a population that has been previously divided into sub-groups (strata)
Without a sampling frame, it’s impossible to
select a simple random or systematic sample.
Many researchers prefer probability samples because
they allow one to make inferences from the sample to the population from which it was selected (can be generalized).
Which of the following statistics estimates the amount by which a sample mean is likely to differ from the population mean?
Standard error of the mean
most important of sample
absolute size not the proportion of the population that it makes up
increasing the size of a sample increases
the precision of the estimates derived from it
as sample size increases sampling errors tend to
decrease
heterogeneity of the population means you will need a
larger sample
contingency table×
A table made up of rows and columns that shows the relationship between two variables. Usually, at least one of the variables is a nominal variable or ordinal variable. Each cell in the table shows the number or (more often) the percentage of cases for that specific combination of the two variables
What strategy allows social researchers to achieve statistically meaningful results when a subgroup of interest comprises a very small proportion of the population?
Random over-sampling
quota sampling critques
- not representative
- It is not appropriate to calculate a standard error term (such as the standard error of the mean) from a quota sample, so it is not possible to estimate the amount by which a sample characteristic is likely to differ from the population.
onsiderations relating to probability sampling derive largely from concerns about
external validity
How do social researchers test the limits of generalizability issuing from changes over time?
Replication
correct
Even when a sample is selected using probability sampling, findings can only be generalized to the population from which the sample was taken.
true
Studies of mass media tend to focus on issues of
representation
The time span analysed in content analysis often depends on
the research question
What effect has the growing use of cellphones had on telephone surveys?
Decreased response rates
Which type of survey is the least accessible to all sample members?
Sampling errors in research occur because
occur because there is a discrepancy between the sample group and the total population.
What is the advantage of multi-stage cluster sampling
It allows interviews to be more geographically concentrated
difficulty with multi-stage cluster sampling
It may be difficult because different clusters may have different numbers of elements in them.
The most efficient use of convenience sample is to
test the reliability of measures to be used in a larger studyproportional sampling.
Quota sampling interferes with
interferes with representativeness of the sample.
Follow-up contact with non-responsive participants are used for
telephone interviews.
three search principles
respect
concern
justice
The first priority of a social researcher should be to ensure
that people being studied do not get hurt
In Canada, most research must comply with the
TCPS2 (CIHR, NSERC, & SSHRC,
who reviews research project that involves humans before it begins
a research ethic board
the principle of respect for persons
The utilitarian defines the rightness of actions, and the
goodness of ends, in terms of the pleasure, happiness, or satisfaction, to which they give rise
The principle of respect for persons
maintains that humans should not be treated as mere “objects” or as a means to an end.
infomation sheet or letter of information
given to people weighing the pros and cons of ressearch - this outlines what it is
informed consent
the principle that prospective participants in social research should be given as much information as they need to make a sound decision about whether to participate in a study; a key principle in social research ethics.
two difficulties of informed consent
- It’s extremely difficult to give prospective participants absolutely all the information required to make an informed decision about their involvement
- In ethnographic research, the researcher is likely to come into contact with a wide spectrum of people, and ensuring that absolutely everyone has the opportunity to give informed consent is not practicable.
informed consent can impact
reactive effects
_______ is the starting point of respect for persons in social research.
free, informed consent
What does the practice of debriefing involve in social research?
Giving participants previously withheld information about the study correct
randomized response technique was originally designed for
interview situations for controversial/illegal activities
pseudonyms are used to protect_____ ______. what is the issue with qualitative research
peoples identities. qualitative describes the social setting in depth which can give clues to people
covert research. what defence is used
investigation in which the people being observed are not informed that they are part of a study. defence: research benefits outweigh any harm that may come to the people being studied. however it is usually avoided as much as possible
In the context of social research, justice entails
the burdens and benefits of research should be spread evenly across society
Which of the following motivated the development of the randomized response technique?
To protect participants in the event police examine research data and bring researchers into court as witnesses correct
Cues picked up by participants that lead them to act in certain ways to avoid ruining the study or to otherwise please the researcher are called
demand characteristics
Which of the following is a rule of thumb concerning the use and size of payments for participation in social research
Payment should not exceed the sorts of benefits to which the participants are accustomed
what were the issues with the tuskegee study
deception
no informed consent
nothing was learned
what was learned from the shock experiment
50% obeyed commands
people listen and trust the authority
what research ethics were violated in the shock experiment
deception
informed consent
violation of participant welfare
harm
involuntary participation
Which of the following is a method used to maintain anonymity of participants
Ethnographic work correct
The first priority of social researchers should be
the welfare of research subjects
In participant observation projects where participants are aware of the researcher and the project, consent
may be obtained verbally
Payment for participation in a study is
unacceptable if the participants are paid for risks they would not otherwise take.
