Sampling

Front 1

3 Methods of Survey Administration

Back 1

1. Interviewer - administered

2. Computer - administered

3. Self administered

Front 2

1. Interviewer - administered Survey

Back 2

The interviewer asks the Q

Captures the data on behalf of the respondent

Either in paper based / computer

Can be face 2 face or Voice 2 Voice (telephone)

Front 3

2. Computer administered Survey

Back 3

The computer can assist or direct the questions

Can be administered by interviewer(CATI) or by respondent (Online survey)
[Computer-assisted telephone interviewing]

Front 4

3. Self - administered Survey

Back 4

Respondent completes the survey on their own

Traditional paper based survey

Front 5

ADV of Questionnaires over

Structured interviews

Back 5

Cheaper to administer

Quicker to administer

Social desirability (Cautious p.232)

No Interviewer invariability

Convenience for respondents

Front 6

Dis-ADV of Questionnaires over

Structured Interviews

Back 6

Cannot prompt additional data

Lower response rate

Difficult asking certain kind of questions

Questionnaire can be read as a whole

Do not know who answers

Front 7

ADV of interviewer administered surveys

Back 7

FAQ R

Feedback

Adaptability

Quality

Rapport

Front 8

Dis Adv of interviewer administered surveys

Back 8

REISS

Requires training

Expensive
Interviewers are only human

Slower

Social desirability

Front 9

ADV of Computer Surveys

Back 9

USER

Use of pics (multimedia)

Speed

Error free interviews

Real time data capture

Front 10

Dis adv of computer surveys

Back 10

POD

Perceptions of security

Ownership or availability of computers

Front 11

ADV of self administered survey

Back 11

RRN

Reduced cost of interviewer time

Respondent control

No interviewer - evaluation apprehension

Front 12

Dis adv of self administered survey

Back 12

DR DIN

Data needs to be coded and transferred from paper to computer

Refusals, incomplete or innaccurate replies

Delays in using data

Increased cost of coding time

No opportunity to interact with respondent

Front 13

Sample

Back 13

The segment of the population that is selected for investigation.

A subset of the population.

The method of selection may be based on a probability or a non-probability approach

Front 14

Sampling frame

Back 14

The listing of all units in the population from which the sample will be selected

Front 15

Census

Back 15

Ask everyone

The enumeration of an entire population

This form of enumeration occurs once every ten years in the UK

Front 16

Positivists - needs for sampling

Back 16

Require ability to generalize from the sample to the population

Seeking reliability and validity

WISH to infer from the sample to the population

Front 17

Interpretivists - needs for sampling

Back 17

Does not wish to generalize from the sample to the population

Would seek validation of their findings in terms of trustworthiness and authenticity

WISH to derive insight from the sample alone

Front 18

3 types of generalisations
?? - doublecheck please

Back 18

1. Statistical

2. Analytical

3. Case to Case transfer

Front 19

Probability Sample

Back 19

A sample that has been selected using random selection so that each unit in the population has a know chance of being selected.

AIM - keep sampling error to a minimum

Front 20

Non-probability sample

Back 20

A sample that has not been selected using a random selection method. Essentially, this implies that some units in the population are more likely to be selected than others.

Front 21

Sampling error

Back 21

The difference between a sample and the population from which it is selected, even though a probability sample has been selected

Front 22

Non sampling error

Back 22

Differences between the population and the sample that arise either from deficiencies in the sampling approach, such as an inadequate sampling frame or non-response, or from such problems as poor question working, poor interviewing, or flawed processing of data

Front 23

Probabilistic Method

Back 23

Allows statistical inference to be carried out about the population

Needs time to set up and administer

Often costly

Requires the ability to set up a list of all members of the population

Front 24

Non probabilistic method

Back 24

Often users draw statistical inferences about the population

Usually is quicker to set up and administer

Often it is cheaper

Does not necessarily need a list of the population

Both can be representative of the population

Front 25

Probability Sample

Back 25

every element of the population has a known, nonzero probability of selection

The sampling frame is required

Statistical inferences can be made

Sampling error can be calculated

Front 26

Non probability sample

Back 26

the selection of specific elements from the population in a non-random manner

Front 27

4 types of Probability Sampling

Back 27

Simple random sample

Systematic sample

Stratified random sampling

Multi stage cluster sampling

Front 28

3 types of non probability sampling

Back 28

Convenience sampling

Snowball sampling

Quota sampling

Front 29

Simple Random

Back 29

Population is numbered, sample is selected by drawing numbers at random

Front 30

Adv of simple random sampling

Back 30

Relatively easy to administer

allows inference

Front 31

Dis adv of simple random sampling

Back 31

Requires defined sampling frame

assume there is no structure in population

no subgroups

Front 32

Systematic random sampling

Back 32

Population is listed, and elements are drawn using a predetermined interval

Front 33

ADV of Systematic random sampling

Back 33

Not necessary to number each member

BUT

Sampling frame must be randomly structured

Front 34

Stratified Sampling

Back 34

The population divided into mutually exclusive and exhaustive subsets (Strata) and random samples of elements is selected from each stratum

Front 35

Types of Stratified Sampling

Back 35

1. Proportional

2. Disproportional

Each strata is assumed to be homogeneous

Front 36

Types of non probability sampling

Back 36

1. Convenience sampling

2. Snowball sampling

3. Quota sampling