Stats Test 3- Part 1- d.n.

Sampling part 1

100

What is Sampling and Why is sampling helpful?

Sampling allows us to study a workable number of cases from the large group to derive findings that are relevant to all members of the group.

• We can get better information from carefully drawn samples than we can from an entire group. This is especially true when the group under study is extremely large. For example, the United States takes a census; The reason is that, with only a few thousand people to contact, the task is more manageable, involving better-trained interviewers, greater control over the interviewers, and fewer hard-to-find respondents.

200

This type of sample should have all the same characteristics as the actual population. For example, it is one that accurately reflects the distribution of relevant variables in the target population. e.g. a researcher wants to study the success of unmarried teenage mothers in raising their children, with the goal of improving the provision of services to these adolescents. The research sample should reflect the relevant characteristics of unmarried teenage mothers in the community. 

Representative Sample

The representative character of samples allows the conclusions that are based on them to be legitimately generalized to the populations from which they are drawn.

•A representative sample is proportionally equivalent to the (larger) population it was drawn from

•Representative sampling better enables you to generalize your findings (derived from the sample) to the (larger) population that it was drawn from – this is known as external validity

Representative sampling facilitates external validity

300

• This all the possible cases of the issue we are interested in studying.
• E.g. the people or group that have the thing in common that we are studying, e.g. all school-age children, all voters, all CSULA students, etc.
• It  does not necessarily mean “people”; it could be a groups or program

Population

-the target population is all possible cases of our unit of analysis.

The definition of a population should specify four things: 

(1) content  (e.g. content of the population refers to the particular characteristic that the members of the population have in common. e.g. members of their population was that they were health or social service agencies.)

(2) units (e.g. unit indicates the unit of analysis, which in one example is organizations rather than individuals or groups. (Although Greenley and Schoenherr collected data from practitioners and clients in the organizations, their focus was on comparing the performance of agencies.)

(3) extent (e.g. of the population refers to its spatial or geographic coverage. e.g.  limited the extent of their population to health and social agencies serving one county in Wisconsin.)

(4) time (the temporal period during which a unit must possess the appropriate characteristic to qualify for the sample. e.g. Greenley and Schoenherr conducted a cross-sectional study, and only agencies that were in operation at the time those authors collected their data qualified. A longitudinal study might include agencies that came into existence during the course of the study.)

400

This consists of one or more elements selected from a population. The manner in which we select elements for the ____ has enormous implications for the scientific utility of the research based on that ____.

Sample

To select a good sample, we need to clearly define the population from which to draw the sample.

500

The listing of all the elements in a population.

 In many studies, we draw the actual sample from this listing. The adequacy of the ______ is crucial in determining the quality of the sample, and the degree to which the sampling frame includes all members of the population is of major importance.

Sampling Frame

The population consists of the sampling frame, and we can make legitimate generalizations only about the sampling frame.

Many social workers, for example, do not belong to the NASW. Thus, a sample taken from the NASW membership roster represents only NASW members and not all social workers. When using organizational lists as sampling frames, then, it is important to assess carefully who the list includes and who the list excludes.

• The sample frame is the part of the population that you could access
• The phone numbers of those who are listed
• Individuals who attend a group meeting
• Students who opt to be on a mailing list
• Example:  The sample frame consists of the 21,000 (70% of 30,000) students who have their email ID set to public

Sampling Part 2

100

• non-probability sample- but this does not invalidate the applicability of the data- you just can’t generalize the data to the whole population
• e.g. age 18-65, female, Latina, cancer, willing to take placebo or drugs
• Participants must meet multiple criteria:
• -age is 18 – 65
• and female
• and Latina or African American
• and diagnosis of cancer
•  and scheduled for 3 – 5 radiation treatments
• and willing to take experimental drug or placebo
• and not using any non-prescribed drugs or supplements

Purposive / Judgmental Sampling

200

Type of sample that in non-probability, and there is a set quota for total n per strata to gather, and stop gathering data (on that strata) when the quota is met

•Quota:  70 right handed people & 30 left handed people

•Quota:  50 bachelor’s students & 50 master’s students & 10 doctoral students

•Quota:  20 Smokers & 20 Nonsmokers

Quota Sampling

300

When would you use non-probability sampling?

1. to see if there is a link between the IV and DV, but you ate not concerned with external validity, e.g. in in experimental research, where future research in other settings will establish generalizability

2. When goal is to understand the social process and meaning structure of a particular setting or group, e.g. the research goal often is only to develop an understanding of one particular setting or group of people

3. When it is  impossible to develop a sampling frame of a population, e.g. for people who do illegal or stigmatized behavior, such as drug use or criminal activity. Rather than giving up on the study of such populations, however, researchers use non-probability samples.

Limitations:

First, without the use of probability in the selection of elements for the sample, we can make no real claim of representatives. There is simply no way of knowing precisely what population, if any, a non probability sample represents. This question of representativeness greatly limits the ability to generalize findings beyond the level of the sample cases.

A second limitation is that the degree of sampling error remains unknown—and unknowable. With no clear population represented by the sample, we have nothing with which to compare it.

400

• non probability sample that can’t represent and generalize results to large population
• no sample frame -->We start with a few cases of the type we want to study, and we let them lead us to more cases, which in turn leads us to still more cases, and so on. 
• the sample builds up as we continue to add cases. Because this type of sampling depends on the sampled cases being knowledgeable of other relevant cases, the technique is especially useful for sampling subcultures where the members routinely interact with one another.
• This type of sampling also is useful in the investigation of sensitive topics, such as child abuse or drug use, where the perpetrators or the victims might hesitate to identify themselves if approached by a stranger, such as a researcher, but might be open to an approach by someone who they know shares their experience or deviant status

Snowball Sampling

500

______can occur when participants with certain characteristics are (unintentionally) selected / not selected

•______ can compromise external validity

•Where, how, and when subjects are recruited may ____the sample:

•Sports bar

•Women’s locker room

•Lobby of a high-tech company using an anonymous touch-screen survey

•Liquor store in an impoverished neighborhood between 1:00 AM – 3:00 AM

•People waiting in line at an ATM

Sampling bias

Wild Card

100

The extent to which the sample findings reasonably represent the (larger) population(s) is called...

External validity

200

With this type of sampling, all items in the sample frame do not have an equal chance of being selected, or the sample frame does not exist

•DOES NOT have the potential for external validity

Nonprobability Sampling

Since the sample does not consist of a proportional reflection of the population, findings cannot be generalized to the larger population that the sample was drawn from; compromises external validity*

•Availability / Convenience Sampling

•Purposive / Judgmental Sampling

•Quota Sampling

•Dimensional Sampling

•Snowball Sampling

*External validity is the extent to which the findings from a sample can be generalized to the population.

300

Probability Type of sampling which involves taking every nth element listed in a sampling frame. This sampling method uses the table of random numbers to determine a random starting point in the sampling frame. From that random start, we select every nth element into the sample. The value of n is called the sampling interval, and it is determined by dividing the population size by the desired sample size. For example, if we wanted a sample of 100 from a population of 1,000, then the sampling interval would be 10.

•Has the potential for external validity

Systematic sampling!

Uses periodic selection process to derive sample

1. Identify sample frame (60)

2. Decide on the size of the sample (15)

3. k = skip = (sample frame) ¸ (sample)

4. k = 60 ¸ 15 

5. k = 4

6. Select a random start point between 1 and k (4) = 3

7. From start point (3), select each kth (4th) item:  3, 7, 11, 15, 19, 23, 27, 31, 35, 39, 43, 47, 51, 55, 59

400

Type of sampling that is "Equal-opportunity sampling – each potential element (person / data record) in the sample frame has the same chance of being selected:

•Simple Random Sampling

•Stratified Sampling

•Systemic Sampling

•Multi-Stage Cluster / Area Sampling

Probability Sampling

500

1. Type of sampling where from a sample frame of 40, create two strata:  30 females and 10 males. --> Randomly sample 10% from each strata:  3 females and 1 males.

2. Type of sampling where from a sample frame of 40, create two strata:  30 females and 10 males.

--> Randomly sample 3 from each strata:  10% females, 30% males.

***This technique is useful when the n (number of elements) in a strata is low.

1. Stratified Proportionate Sampling (probability sample, has EXTERNAL VALIDITY)

2. Stratified Disproportionate Sampling

(probability sample, has EXTERNAL VALIDITY)

Wild Card

100

• How does nonprobability sampling apply to populations?

*External validity is the extent to which the findings from a sample can be generalized to the population. Non- probability sampling does not have the potential for external validity.

200

Type of sampling where it is a probability sample and has external validity and..

You Gather the largest sample frame possible (from one domain), Determine the desired sample size, Make random selections until the sample size is fulfilled 

Simple random sampling = “SRS”

• E.g. randomly select 10 people out of 60

E.g: 1.  Sample frame = 60

2.  Desired sample size = 10

3.  Randomly select any 10

300

Type of sampling where all items in the sample frame do not have an equal chance of being selected, or the sample frame does not exist

Since the sample does not consist of a proportional reflection of the population, findings cannot be generalized to the larger population that the sample was drawn from; compromises external validity*

Examples include:

•Availability / Convenience Sampling

•Purposive / Judgmental Sampling

•Quota Sampling

•Dimensional Sampling

•Snowball Sampling

*External validity is the extent to which the findings from a sample can be generalized to the population.

Non-Probability Sampling 

400

Type of sampling where you set the number or ____for total "n" per strata to gather, and stop gathering when ___(set number) is met

• This is a type of NON- probability sampling which does not have external validity
• e.g. Set number for total n per strata to gather, and stop gathering data (on that strata) when the ____(number) is met

Quota Sampling

e.g. 

• Quota:  70 right handed people & 30 left handed people
• Quota:  50 bachelor’s students & 50 master’s students & 10 doctoral students
• Quota:  20 Smokers & 20 Nonsmokers

500

Type of sampling that is non-probability and does not have external validity and Researcher recruits whoever is readily accessible

e.g. •People walking by, •Students in a classroom, •People waiting in a line at an ATM

Availability / Convenience Sampling

Sampling Part 3

100

This is a sample where each element in the population has some chance of inclusion in the sample, and the investigator can determine the chances of each element's inclusion.

Each elements probability of inclusion in a probability sample is nonzero and known.

Probability sample

200

• sampling where each element in the population has an equal probability of inclusion in the sample.
• The simplest technique for drawing probability samples
• We treat the target population as a unitary whole when sampling from it

Simple Random Sampling (SRS)

• SRS is limited to fairly small-scale projects that deal with populations of modest size for which we can obtain adequate sampling frames. The importance of SRS lies not in its wide application. Rather, SRS is the basic sampling procedure on which statistical theory is based; and it is the standard against which other sampling procedures are measured.

300

A method of sampling which involves taking every "k"th element listed in a sampling frame. This type of sampling uses the table of random numbers to determine a random starting point in the sampling frame. From that random start, we select every "k"th element into the sample. The value of k is called the sampling interval, and it is determined by dividing the population size by the desired sample size. For example, if we wanted a sample of 100 from a population of 1,000, then the sampling interval would be 10. From the random starting point, we would select every 10th element from the sampling frame for the sample.

• We treat the target population as a unitary whole when sampling from it

- systematic sampling can produce biased samples, although this is rare. The difficulty occurs when the sampling frame consists of a population list that has a cyclical or recurring pattern, called periodicity.

Systematic Sampling

400

Sampling method that can reduce sampling errors. 

• With SRS and systematic sampling methods, we treat the target population as a unitary whole when sampling from it.
• This type of sampling changes this by dividing the population into smaller subgroups, called ___, before drawing the sample and then drawing separate random samples from each of the __.
• ADVANTAGE=> Reduction in Sampling Error b/c it reduces sampling error for a given sample size to a level lower than that of an SRS of the same size. This is so because of a very simple principle: The more homogeneous a population on the variables under study, the smaller the sample size needed to represent it accurately.

Stratified Sampling

This type of sampling changes this by dividing the population into smaller subgroups, called Strata.

Example: commercial-size cans of nuts, one labeled "peanuts" and the other "mixed nuts." Because the can of peanuts is highly  homogeneous, only a small handful from it gives a fairly accurate indication of the remainder of its contents. The can of mixed nuts, however, is quite heterogeneous, containing several kinds of nuts in different proportions. A small handful of nuts from the top of the can cannot be relied on to represent the contents of the entire can. If the mixed nuts were stratified by type into homogeneous piles, however, then a few nuts from each pile could constitute a representative sample of the entire can.

500

This is a procedure in which we obtain the final units to include in the sample by first sampling among larger units, called clusters, that contain the smaller sampling units. A series of sampling stages are involved, working down in scale from larger clusters to smaller ones. 

Area sampling/ cluster sampling