How do films & TV shows influence our level of tolerance and respect towards cultural diversity and ethnicity? Analyze at least 5 TV shows and films
Sampling for Quantities & Qualitative Research
Abeer AlNajjar
1
Population
Target group (universe in texts)
Census (to study every member of a population)
because measuring every member of a population usually is not feasible most researchers employ a Sample
Sample ( a subgroup of the population)
2
Communication researchers are interested in a population (also called a universe when applied to texts) of communicators, all the people who posses a particular characteristic, or, in the case of those who study texts, all the messages that share a characteristic of interest.
The population of interest to researchers (often called the target group) might be members of a business, communication majors at a university, all students at a university, all people living in a city, all eligible voters in a country.
Texts ( editorials published in a specific newspaper for a week, or a large universe such as every editorial published In every newspaper in the UAE, or even larger such as all persuasive messages).
The best way to generalize to a population is to study every member of a population (Census)
If every member is studied, we know, by definition, the population’s response at the point in time the study was done
Sample
The results from the sample are then generalized back to (used to represent) the population
Representative sample ( population validity)
Its similarity to its parent population
3
The results from the sample are then generalized back to (used to represent) the population). For such generalization to be valid (demonstrate population validity), the sample must be representative of its population. That is, it must accurately approximate the population.
Types of sampling
Random sampling (probability sampling)
Involves selecting a sample in such a way that each person in the population of interest has an equal chance of being included
Nonrandom sampling (nonprobability sampling)
Is what ever researchers do instead of using procedures that ensure that each member of a population has an equal chance of being selected
Sampling error
Is a number that express how much the characteristic of a sample probably differ from the characteristics of a population
5
There are 2 different types of sampling procedures, and differ in terms of how confident we are about the ability of the selected sample to represent the population from which it is drawn
Random sampling (probability sampling)
Involves selecting a sample in such a way that each person in the population of interest has an equal chance of being included
By giving everyone an equal chance , random sampling eliminates the danger of researchers biasing the selection process because of their own opinions or desires. By eliminating bias, random sampling provides the best assurance that the same characteristics of the population exist in the sample, and, therefore, that the sample represents the population.
Nonrandom sampling: it sometimes is not possible to sample randomly from a population because neither a complete population list nor a list of clusters is possible
Is what ever researchers do instead of using procedures that ensure that each member of a population has an equal chance of being selected
Random error can be calculated for random samples, but not for nonrandom sample
Random sampling methods-Quantitative Research
1)simple random sample
2) systematic sample
3) stratified sample
4) cluster sample
6
There are four types of random samples
simple random sample: we assign each person a successive number and then select from these numbers in such a way that each number has an equal chance of being chosen. Numbers are chosen until the desired sample size is obtained.
You should first have a full list of the population . If this is not possible some other methods of random sampling should be used
2) systematic sample (ordinal sample): chooses every nth person from a complete list of a population after starting at a random point
Systematic sample usually used in very large populations, perhaps because they are easier to employ than a random sample
3) stratified sample: categorizes population with respect to a characteristic a researcher considers to be important, called a stratification variable, and then samples randomly from each category. One popular way of stratifying a population is with regard to demographic variables.
Each one of the proceeding types of random sampling necessitate obtaining a complete list of the population of interest and then randomly selecting members from it.
Burt obtaining a complete list is not always possible.
4) cluster sample
Randomly selecting units, or clusters (in this case, branch offices) of the employee population.
Non-random sampling methods-Qualitative Research
convenience
volunteer
purposive
Seek individuals who meet criteria
quota
Network
Seek individuals who fit profile
Snowball sampling
Ask participants for referrals
7. Maximum variation sampling
Seek participants until data are redundant
7
This applies when we are studying people with characteristics for which no lists exist.
Researchers must be very careful in generalizing the results they get from nonrandom sample to a population, and must always disclose when they are doing so
Convenience: (accidental) respondents are selected non-randomly on the basis of availability. Market researchers for example often go to shopping malls and interview any available people who shop there
The most popular type of convenience sample for researchers who teach at universities is one composed of students.
The problem with convenience sample, as with all nonrandom samples, is that there is no guarantee that the respondents chosen are similar to the general population they are suppose to represent
The results from convenience samples, therefore cannot be applied with much confidence to a larger population.
Volunteer sample: respondents choose to participate in a study. (depression and verbal aggressiveness in different marital couple types
To recruit volunteers researchers often offer some reward to those people who sign up for studies, especially to university students
Purposive: (deliberate)
Quota: a nonrandom sample in which respondents are selected nonrandom on the basis of their know proportion in a population
9
Sampling Qualitative Data-Observation & Interviews
Impossible to observe every interaction of all interactants
Identify settings, persons, activities, events, and time periods
Distinguish between routine, special, and untoward events
Randomly selecting days and times increases the representativeness of your observations
10
Gaining Access
If you take on a covert role, your acceptance by others depends on your ability to play the part
Consider a gatekeeper or sponsor
Will your observations provide the data you need?
Is the setting suitable?
Can you observe what you want to observe?
Will your observations be feasible?
Can you observe in such a way that you are not suspect to others?
11
Becoming Familiar with People and Places
Draw a map of the interaction setting
Ask for a tour
Ask for relevant background
12
Developing Trust
Trust must be addressed due to researcher’s intimate role with participants
Must be addressed in first contact
Trust is person-specific
Trust is established over time
Trust can be destroyed with one event
Trust between researchers and participants is paramount
13
Developing Rapport
Ask simple questions
Maintain positive conversation posture
Learn names and titles
Perform commitment acts
Locate key informants
14
What Constitutes Data in Qualitative Research?
The concept of data is broadly cast
ranges from public to private
More continuous than discrete
Field notes
Recordings
Written or digital documents
Photographs or maps
Artifacts
15
Your Impact as a Researcher
Your sex, age, and ethnicity affect what you observe and how you observe it
Report similarities and differences that you believe affected data collection or interpretation
Research teams should be diverse
Males and females
Age
Ethnic, racial, or cultural groups
Reliability vs. Validity
reliability = consistency & stability
validity = accuracy
16
Sampling for Content Analysis
18
Selecting What to Code
Are the messages available or must they be created?
Narrow the data set for the elements of interest
May still need to sample elements
Messages may have structural characteristics that need to be considering in sampling
19
Interpreting Coding Results
Analysis must be relevant to hypothesis or research question
Frequencies
Differences
Trends
Patterns
Standards