Week 7 and 8 Flashcards

1
Q

What is rigour?

A

Strictness in how a study is conducted.

Supports quality, believability, and trustworthiness of study findings.

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

What is reliability?

A

Refers to the extent to which the instruments yield the same results on repeated measures.
Concerned with CONSISTENCY, ACCURACY, PRECISION, STABILITY, EQUIVALENCE, HOMOGENEITY.

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

What is validity?

A

Describes whether the measuring tool actually measures the correct phenomenon.

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

What is the correlation coefficient?

A

Expresses the strength and direction of a relationship.

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

What does it mean to have stable reliability?

A

The instrument is considered stable when it can produce the same results over and over again.

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

Describe homogenous reliability.

A

All items in a tool measure the same concept or characteristic.

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

What is test-retest reliability?

A

stability of scores of an instrument when administered more than once to the same participants under similar conditions.

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

What is parallel form reliability?

A

like test-retest in that the same people are tested more than once with a specific interval, but in the assessment of parallel-form, a different form is given on the second testing.

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

What can homogeneity be assessed by?

A

item-to-total correlation, split-half reliability, Kuder-Richardson coefficient, Cronbach’s alpha.

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

What is item to item correlation?

A

a measure of the relationship between each scale item and the total scale. When calculated, a correlation for each item on the scale is generated.

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

What is split-half reliability?

A

involves dividing a scale into halves and making a comparison. Provides a measure of consistency in terms of sampling content.

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

What is Kuder- Richardson Coefficient?

A

estimate of homogeneity used for instruments that have a dichotomous response format. Involves yes/no true/false questions.

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

What is Cronbach’s alpha?

A

test of internal consistency in which each item in the scale is simultaneously compared with the others and a total score is then used to analyze the data.

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

What is equivalence?

A

either the consistency or agreement among observers who use the same measurement tool or the agreement between alternative forms of a test yield a high correlation.

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

What is interrater reliability?

A

the consistency of observations between two or more observers with the same tool. Either two ore more individuals should make an observation or one observer should observe the same behaviour on several occasions

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

What is content validity?

A

degree to which the measure represents the universe of content, the domain of the construct.

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

What is face validity?

A

rudimentary type of validity in which the instrument intuitively gives the appearance of measuring the concept.

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

What is criterion-related validity?

A

degree of relationship between the participants performance on the measurement tool and the participants actual behaviour.

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

What is predictive validity?

A

degree of correlation between the measure of the concept and a future measure of the same concept

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

What is construct validity?

A

degree of correlation between the measure of the concept and a future measure of the same concept

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

What is the hypothesis testing approach?

A

the investigator uses the theory or concept of underlying the measurement instrument to validate the instrument.

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

What is convergent validity?

A

exists when two or more tools that are intended to measure the same construct are administered to participants and found to be positively correlated.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What is divergent validity?

A

if a test is too similar to another test

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

What is the multitrait-multimethod approach?

A

involves examining the relationship between instruments that are intended to measure the same construct and between those that are intended to measure different constructs.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

What is the constructed groups approach?

A

to the development of construct validity, the researcher identifies two groups of individuals expected to score high or low in characteristic being measured by instrument

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

What is the factor analysis approach?

A

researcher assesses the degree to which the individual items on a scale truly cluster around one or more dimensions.

27
Q

What is the observed test score?

A

derived from a set of items consists of the true score plus error.

28
Q

What is systematic error?

A

Measurement error that is attributable to relatively stable characteristics of study population that may. bias their behaviour, cause incorrect instrument calibration, or both.

29
Q

What is a population?

A

An entire aggregation of cases in which the researcher is interested.

30
Q

What is a sample?

A

A subset of a population

31
Q

What is sampling?

A

Process of selecting units to represent a population

32
Q

What is the accessible population?

A

The members of a population that researchers select a sample from.

33
Q

What is a sampling bias?

A

Systematic over-or under-representation of a population segment on a characteristic relevant to the research question.

34
Q

What are the advantages and disadvantages of probability sampling?

A
- Each population element has a random
chance of being sampled.
• Greater confidence that the sample is
representative, so it’s more generalizable.
• Often more challenging and time
consuming.
35
Q

what are the advantages and disadvantages of non-probabilty sampling?

A

• Each population element has a nonrandom and unknown chance of being
sampled.
• Much less confidence that the sample is
representative, so less generalizable.
• Usually much more feasible.

36
Q

What is probability sampling?

A

• A strategy for selecting and recruiting
study participants.
• Happens before enrollment.
• Aim: To ensure a representative sample.

37
Q

What is randomization?

A
• A random process for assigning
participants to study groups.
• Happens after enrollment with people who
have already agreed to join the study.
• Aim: To ensure equal distribution of
variables between study groups.
38
Q

What is non-probability quota?

A

The researcher identifies groups (strata) of the
population of interest, and samples deliberately
to represent each strata.
• Can be done when the researcher knows the
population profile…
• OR when the researcher deliberately samples an
underrepresented group.
• Unknown source of bias, like all non-probability
samples.

39
Q

What is non-probability matching?

A

Targeted sampling to create groups that are
comparable on pre-identified variables.
• The more variables matched, the more rigorous
it becomes.
• The more variables matched, the harder it is to
get a sufficient sample size.

40
Q

What are the stages of probability simple random sampling?

A
  1. Define the population of interest (a set).
  2. List all accessible members of that population (a sampling frame).
  3. Generate a random list of numbers.
  4. Start at a random point on the random list of numbers, and select potential
    participants from your sampling frame as “their number” comes up.
41
Q

What are the advantages of probability simple random sampling?

A

• ADV: No bias from the researcher, no systematic bias (except in the selection of the
accessible population).
• ADV: Most likely to be representative, given a large enough sample size.

42
Q

What are the disadvantages of probability simple random sampling?

A
  • DISADV: Time-consuming and inefficient, not very feasible.

* DISADV: Maybe impossible if the researchers can’t build a sampling frame.

43
Q

What is stratified random sampling?

A

• Members of the population are grouped into homogenous subsets by relevant variables,
then researchers sample randomly within those subsets to match population distribution
of variables.
• Like quota sampling, but the selection within strata is random.
• Sampling can be proportionate or disproportionate (e.g. if the distribution in the
accessible sample does not reflect the population of interest).

44
Q

What are the advantages of stratified random sampling?

A

• ADV: Increased representativeness, low risk of bias.

45
Q

What are the disadvantages of stratified random sampling?

A

Variable info may not be available, time-consuming, challenging, and expensive.

46
Q

What is multi-stage sampling?

A

• Random sampling in stages, BIG à medium à small
• Can use simple or stratified random sampling at each stage.
• Usually done to manage a large accessible population (e.g. census data, public health
nurses in Canada, etc.)

47
Q

What are the advantages of multi-stage sampling?

A

• ADV: More economical and efficient, sometimes can be used when a sampling frame isn’t
directly available.

48
Q

What are the disadvantages of multi-stage sampling?

A

Higher risk of sampling errors, data requires more complex statistical management.

49
Q

What is systematic sampling?

A

• Selection of every kth case drawn from a population list (e.g. every 3rd person presenting
to an ER, every 12th enrollee at a physiotherapy clinic).
• Population must be very narrowly defined, and the accessible population must be closely
aligned with the population of interest for this to be considered a probability sample.
• The sampling frame also needs to be random in relation to the variable of interest, and
the first person must be selected randomly.

50
Q

What are the advantages of systematic sampling?

A

Efficient and convenient.

51
Q

what are the disadvantages of systematic sampling?

A

It’s easy to introduce bias.

52
Q

What is measurement?

A

The assigning of numbers to objects or events according to predetermined rules

53
Q

What must data collection be?

A

Objective – Not influenced by the person who collects the data.
• Systematic – Collected the same way by each person or instrument, every time.
• Data collection plans must control for both researcher and systematic bias.
• Data collection plans and training of data collectors should be detailed in the protocol.

54
Q

What is operationalization?

A

Translating the concept of interest into something observable and
measurable.

55
Q

What is the conceptual definition?

A

How the concept of interest is defined for this study.

56
Q

What is the operational definition?

A

How the conceptual definition is defined for the purposes of measurement.

57
Q

What is consistency?

A

Methods used to collect data from each participant in the study is the same or close to the same as possible.

58
Q

What is physiological measurement?

A
• Physical, chemical, microbiological, or
anatomical.
• Requires specialized equipment.
• E.g. Weight, temperature, x-ray, blood
levels
59
Q

What is observational measurement?

A

• Systematic planned recording of events.
• Consistent with the study’s objectives
and related to concepts and theories.
• Can be structured or unstructured.
• E.g. Observing nurses for signs of caring
during rounds in LTC.

60
Q

What is concealment?

A

Whether participants
know they are being observed.
• Intervention: The observer provokes
action.

61
Q

What is an interview?

A

Verbal data collection. Can be structured, semi-structured, or unstructured.

62
Q

What is a questionnaire?

A

An instrument designed to elicit data about knowledge, attitudes, beliefs, and feelings.

63
Q

What is the criteria for instrument development?

A
  1. Define construct
  2. Formulate items (questions)
  3. Assess items for content validity.
  4. Develop instructions.
  5. Pre-test, pilot test.
  6. Estimate reliability and validity.