Brainscape's Knowledge GenomeTM

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


See full index

Research Design > Non-Experimental Research w6/8 > Flashcards

Non-Experimental Research w6/8 Flashcards

1
Q

What are subject variables? What is the opposite of these?

A

Existing attributes of people in a study, e.g. Gender, age, personality. Manipulated variables contrast with subject variables.

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

What is the statistical technique correlation? In relation to correlation research?

A

It is used to determine the degree to which two variables are related. Not all correlational research report correlation in statistical tests - the test is not the identifier of the design.

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

What is a scatterplot? Why are they useful? Why is it a good idea to graph data before using a statistical test?

A

A graph to represent data from two variables - one plotted on x axis and one plotted on y axis. Each * = one ppt. Help to recognise patterns and relations. There may be a non-linear correlation that isn’t identified by the test.

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

What is regression?

A

A statistical process for predicting individual scores and estimating the accuracy of these predictions. Use predictor (x) to predict criterion variable (y).

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

What is a regression line?

A

A straight line on a scatterplot that best summarises a correlation.

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

What is a problem with correlations?

A

They don’t show causation - doesn’t tell you if one variable causes another. Also which variable is the cause and which is the effect? - could be other way round. There could be a 3rd unspecified variable.

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

What is inter-rater reliability?

A

Correlation between 2 researchers - extent to which they agree

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

What is test-retest reliability?

A

Correlation between test scores from different times - gives extent to which test produces same result on different occasions - is test reliable?

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

What is split-half reliability?

A

Correlation between test score on 1st half of test and 2nd half - assesses internal reliability (consistency) of test - extent to which all pats of test contribute equally to what’s being measured.

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

What is convergent validity?

A

Correlation between accepted measures - extent to which 2 accepted measures produce similar results - they should do.

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

What is discriminant validity?

A

Opposite of convergent - should be no correlation between 2 measures that should be unrelated.

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

What is concurrent validity?

A

Extent to which measure correlates with current behaviour

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

What is predictive validity?

A

Extent to which measure correlates with future behaviour

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Do Quasi-Experimental designs contain and IV and DV? What do these experiments want to do?

A

Yes.

Examine relations between more than 2 variables.

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

What is the IV for Quasi experiments? What’s it called?

A

A pre-existing variable - e.g. sex, age, temperament, that cannot be manipulated or randomly assigned. quasi-independent variable.

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

What is the difference between manipulated and subject variables?

A

Manipulated variables are assigned to ppts in a condition, subject variables are ones the ppt brings into the room.

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

4 processes required by randomised experiments that Quasi also require?

A
  1. Choose IVs and DVs wisely.
  2. Identify useful populations and settings to study.
  3. Ensure assumptions of statistical tests are met.
  4. Consider validity and generalisation.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What is the extra task that Quasi require?

A

Requires critical thinking about confounds and other problems that might result due to lack of random assignment.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Why is causality a problem for Quasi experiments?

A

Causal inferences are more limited in Quasi than experimental. Subject variable- groups may differ in several ways, IV can’t be said to cause DV. (whereas manip IV = DV in exp).

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

What type of variables do questionnaires & surveys measure?

A

They measure subject variables - existing characteristics of an individual, aka participant variables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What are surveys? What affect can they have?

A

Systematic data collection about a sample drawn from a specified larger population. They can shape policy and precede intervention studies.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What is a census?

A

Survey data obtained from every member of the population

23
Q

What is an opinion poll?

A

Data gathered to assess public opinion on an issue

24
Q

What are the advantages of surveys?

A

They are an excellent source of descriptive data. Representative surveys allow conclusions from samples to populations.

25
Q

What are the disadvantages of surveys?

A

They provide correlational data, which cannot be used to draw causal inferences.

26
Q

What are diagnostic tests?

A

They are used to identify the presence/absence of attributes to confirm/rule out a condition, disorder or disease

27
Q

What are screening tests?

A

Identify presence/absence of condition/disorder/disease, but given to larger groups of people - usually with no symptoms.

28
Q

What 2 characteristics should a good test/inventory have?

A
  1. Validity: test should measure what it is intending to measure.
  2. Reliability: test should be consistent in its evaluation of an individual.
29
Q

How are some questionnaires formatted to make responding quicker & easier?

A

Formatted as checklists or inventories.

30
Q

What is the purpose of questionnaires?

A

To assess attitudes, beliefs and behaviours - judgements about selves, another person or the environment. Can be used to identify new constructs and develop new theories - or test existing hypotheses.

31
Q

What is probability sampling?

A

Each member of the population has a definable probability of being selected for the sample.

32
Q

What is a representative sample?

A

Sample reflects attitudes of population as a whole.

33
Q

What is random sampling?

A

Random - every member of pop has equal chance of being selected.

34
Q

What is a biased sample?

A

Biased sample - might not reflect attributes of population.

35
Q

What is cluster sampling?

A

When subgroups are chosen based on a feature they have in common

36
Q

What is stratified sampling?

A

Stratified sampling ensures subgroups of the population are represented in the correct proportions for which they occur, in the final sample.

37
Q

What is convenience sampling?

A

Selecting participants on the basis of availability or cooperation

38
Q

What is quota sampling?

A

When subgroups of the population are chosen not randomly

39
Q

What is snowball sampling?

A

When participants are chosen based on referrals from previous participants - social media allows for this.

40
Q

What cognitive processes do surveys and questionnaires involve?

A

Complex ones - question has to be understood, then relevant info is retrieved, judgement is formed, and formatted to fit responses, answer is edited.

41
Q

Ads of open-ended questions?

A

Captures range of answers, can discover answers hadn’t envisaged. Used in exploratory phases of research.

42
Q

Disads of open-ended questions?

A

Require coding in order to be compared - which can be difficult. Issues with bias in interpretation and reliability.

43
Q

How to improve reliability of open-ended Qs?

A

Use content analysis, blind scoring and multiple scorers.

44
Q

Ads of closed-ended questions?

A

Scoring is easier and more objective as same range of responses from all ppts.

45
Q

Disads of closed-ended questions?

A

Constraint of possible answers. Could miss out on key info as potential answers need to be anticipated. Subject to bias

46
Q

Why is it good to have more answers in closed-ended questions?

A

Increase the range - easier to discriminate. But not too many as this leads to too much variability.

47
Q

What are likert scales? Good things about them?

A

Answers across a continuum - strongly agree (1) to strongly disagree (6). Less susceptible to bias, avoids social desirability bias.

48
Q

What are dichotomous answers?

A

Yes/no, True/false.

49
Q

What are nominal answers?

A

Monday, Tuesday, Wednesday

50
Q

What are ordinal answers?

A

Never, sometimes, often, always

51
Q

What are interval scales

A

1-6, same as likert

52
Q

What should be avoided when writing questions?

A

Avoid leading questions (which lead or bias the respondent). Avoid double-barrelled questions (2 questions in 1).

53
Q

What takes place after questionnaire is designed, and before main data collection?

A

Pilot studies - involving a small number of people similar to the target sample. Used to evaluate clarity of instructions, questions and to estimate timings.

54
Q

What is a useful method for evaluating and validating questionnaires and surveys?

A

Cognitive interviews - talk-aloud procedure followed by probe questions - what do people think he questions are asking?

Research Design (7 decks)

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