Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

RSS Ordinary - module 1 > Study design and survey design > Flashcards

Study design and survey design Flashcards

1
Q

What is response rate?

A

This is how many people respond to the survey. When carrying out a survey you need to account for people not responding by having plans for follow up or substitution. Reduced response rates will affect the accuracy of your findings as you sample will not be representative of the population.

To calculate, divide the number of selected units that have responded by the number of original,y selected units and x by 100 for the % response rate.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is the survey population?

A

The units in the sample from whom data is collected.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is the target population?

A

This is the group of population units from whom we would like to collect data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is blind experimentation?

A

This is a way of controlling for confounding effects from the subjects or the researchers in an experiment.

Single blind - the subjects do not know which group they are assigned to, such as one group taking a medication and the other a placebo.

Double-blind - both the subject and the researcher does not know which subjects are assigned to which group.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is a census survey?

A

This involves the collection of data from all units in the population of interest.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is a cohort study?

A

This is a longitudinal survey that selects a sample of individuals and follows them over a period of time. Like ‘Child of Our Time’.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is the name of a group in a study that does not receive experimental treatment?

A

Control group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is the experimental group?

A

The group of subjects that receive experimental treatment such as a new medicine being taken by that group. A comparison is made between this group and the control group.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is an experimental study?

A

This involves deliberately applying a treatment to one group of experimental units and comparing that group to a group that does not receive the treatment. These are known as the control units.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is the term for a survey that collects data from the same sample of respondents at regular intervals of time?

A

A longitudinal sample survey

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is the term for researchers watching the natural characteristics of a group of units in their normal environment?

A

An observational study

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is a one off sample survey?

A

A sample survey that provides a snapshot of a proportion of the population at one point in time. This is also known as a cross-sectional survey.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is a panel survey?

A
  • a type of longitudinal survey
  • recruits a single representative sample
  • collects data from these same respondents
  • taken at regular intervals
  • sometimes add the children of panel members
  • removing people from the sample when they die
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

‘Surveys conducted at regular intervals where a new sample is taken each time the survey is run.’ What is this?

A

This is a repeated cross-sectional sample survey.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is a survey study?

A

The aim is to collect data from a sub-set of the population that describes the target population. The hope is that the characteristics the survey is designed to describe are present to the same degree, and are distributed in the same way, in the responding sample compared to the target population as a whole.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is block randomisation?

A

A method of accounting for confounding factors by grouping like units together and then randomly allocating the units within each group to either the experimental or control group.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is a confounding factor?

A

A factor that may influence the results of experimental research.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What are the main stages of a study?

A
  • Decide objective and variables to be collected
  • Decide on population of interest
  • Define sampling frame
  • Check sampling frame
  • Randomly select a sample
  • Collect the data in appropriate manner
  • Data capture and processing
  • Analyse the results
  • Produce outputs
  • Reflect on approach taken
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is research?

A

A systematic investigation and study to establish the facts and conclusions? We can seek to answer a question using experimental or observational study.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What is hypothesis testing?

A

This is a theory statement such as ‘taking vitamin C on a daily basis reduces the chance of getting a cold’. You then set about researching to establish if this is true or not.

21
Q

What is the null hypothesis?

A

This is the commonly accepted assumption. This is then challenged by the researcher having an alternative hypothesis.

22
Q

What is an alternative hypothesis?

A

This is a hypothesis that the researcher comes up with that contradicts the null hypothesis.

23
Q

What is a type 1 error in hypothesis testing?

A

This is when you accept the alternative hypothesis when you should have accepted the null hypothesis.

24
Q

What is a type 2 error in hypothesis testing?

A

This is when you accept the null hypothesis but you should have accepted the alternative hypothesis.

25
Q

What is a ‘critical value’ in hypothesis testing?

A

It is line you draw before you collect and analyse the data to decide at what point you would accept or reject the hypothesis.

26
Q

Why might someone repeat their study on another sample?

A

To see if they find the same results. This does not control for confounding factors but it can check to see if the same findings are applicable.

27
Q

What are the advantages of an experimental study?

A
  • You can investigate the impact of an intervention
  • There are steps you can take to control for confounding factors
  • You can use block randomisation to monitor impact on different groups.
28
Q

What are the disadvantages of an experimental study?

A
  • You cannot impost something that would be unethical
  • You cannot completely eliminate confounding factors.
  • People may behave differently knowing that they are in an experiment.
29
Q

What are the advantages of an observational study?

A
  • Observe things as they occur naturally.
  • No burden on participants
  • You don’t have to convince people to take part of you are accessing records
  • No worry that people are acting differently
30
Q

What are the disadvantages of observational studies?

A
  • You are unable to control for confounding factors.
  • It could be difficult to record everything you are interested in.
  • Need expensive trained observers.
  • May need to be combined with interview/ questionnaire.
31
Q

What are the advantages of a census?

A
  • Whole population coverage - should be representative.
  • Good data quality - data can be used as a benchmark.
  • Allows multivariate analysis
  • Can be supplemented by admin and survey data.
32
Q

What are the disadvantages of a census?

A
  • Expensive
  • Respondent burden and non-response
  • Slow to process and publish data
  • Hard-to count will need follow up visits
33
Q

What is a cohort study?

A

When a group of units are selected that share a common characteristic or experience within a defined time period such as people the same age. Example is the Child of Our Time’ research study.

34
Q

What is a drawback of serial sample surveys/ repeated cross sectional surveys?

A

As a new sample is taken each time it does’t tell us how individuals are affected. Relationships between variables may not be seen as accurate as different people.

35
Q

What is a problem with longitudinal surveys?

A

High respondent burden, people may moved or drop-out.
Expensive.
‘Conditioning’ of answers as questions are known in advance.

36
Q

Why are longitudinal studies helpful?

A

Track the relationship between variables over time. Only one sample needed.

37
Q

Why do researchers carry out sample surveys rather than census surveys?

A

This is because it is very expensive to collect data from all units in the population. The hope is that an appropriately chosen sample will have similar characteristics, distributed in a similar way so we can create inferential statistics from the data about the whole population.

38
Q

How are data collected for the School Census?

A

It is a statutory requirement for LA maintained schools to submit the data, under Education Act 1996. Different modules are collected in each termly census. The school’s management information system (MIS) software will extract the relevant data items for each census. It is called COLLECT.

Validation checks are carried out automatically. If there is a problem with the data there is time for corrections to be made and they are flagged as an error. A summary report is produced for the head to check before submitting.

Academies submit straight to DfE and others straight to LAs.

39
Q

How has the School Census been used for statistical purposes, other than those for which it was originally designed?

A

Work on data matching to try and create outputs on ethnic group.

40
Q

What sort of data are collected for the School Census?

A

The School Census is information collected by DfE on schools in the country and their pupils. For each LA maintained school and some non-maintained such as academies, information on school type, attendance, attainment, childcare arrangements and FSM are used to inform funding, RAISEonline and performance tables are also used by researchers. Pupil records include things like name, age, sex, address, ethnic group, SEN status, language, service child, care status, attendance, attainment, any reasons for exclusions.

41
Q

Why might a researcher decide to spend their money on a small amount of face-to-face interviews rather than a larger mail survey?

A
  • If non-response is lower for the interviews, you could still collect data from a representative sample.
  • Better quality information may be collected as the interviewer can explain questions in more detail.
  • Aids like show cards could be used help understanding on increase confidentiality.
42
Q

Why might a mail survey be a preferred data collection instrument?

A
  • Can reach more people - geographic spread
  • Could be hard-to-reach groups
  • May not want to send interviewers to certain areas
  • Do not have trained interviewers available
  • Possibly more appropriate for private information
  • If the respondent has to check different documents this gives the more time to do so.
43
Q

What could you do if you suspect that respondents are not reporting income data accurately?

A

Attempt to access and use admin data such as HMRC, PAYE data.

44
Q

What should an interviewer be provided with?

A

Scripted questions to ensure consistency
Instructions including on routing
Some method of recording answers
Security device - phone and press button

45
Q

What is a repeated cross-sectional survey?

A

Surveys conducted at regular intervals where a new sample is taken each time the survey is run.

46
Q

What is a one off cross sectional survey?

A

Takes a snapshot of the population of interest at one point in time.

47
Q

What is the difference between repeated cross-sectional surveys and longitudinal surveys?

A

They are both repeated over time but in cross-sectional a new sample is drawn and in longitudinal the same sample is used, although some elements might be replaced.

48
Q

What should happen in the development of survey questions?

A
  • Clear definition of what data needs to be collected.
  • Focus groups
  • Research into best question design
  • Expert groups
  • Cognitive interviews
  • Pretesting/ piloting
  • Improvements
49
Q

What is cognitive testing?

A

Evaluation of a respondent’s understanding by asking them questions about the data collection questions such as…

  • How would you re-word the question?
  • Were you able to answer the question accurately?
  • Were there any difficulties answering?

You could also look at time spent on the different questions to think about lowering respondent burden.

RSS Ordinary - module 1 (7 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions