Midterm Flashcards
(237 cards)
1
Q
What was the original definition of Heath according to WHO? Pros and cons?
A
Health is a state of complete physical, mental, and social well-being and not merely the absence of disease or infirmity
Pros: beyond physical sense and incorporates mental and social domains
Cons: difficulty defining wellbeing and to maintain complete
2
Q
What was the Frankish et al. definition of health?
A
The capacity of people to adapt to, respond to, or control life’s challenges and changes
3
Q
Define holistic
A
Incorporating the concept of holiday or the idea that the whole is more than merely the sum of its parts, in theory or practice: holistic psychology
Whole is more than a sum of parts
4
Q
What is the updated WHO definition of health?
A
The extent to which an individual or group is able to realize aspirations and satisfy the needs, and to change or cope with the environment.
Health is a resource for everyday life, not the objective of living; it is a positive concept emphasizing social and personal resources, as well as physical capacities
5
Q
Define research and health research
A
Research: systematic process of enquiry that aims to generate new scientific knowledge
Health research: any research relevant to health
6
Q
What are the steps to scientific method?
A
- Ask a question
- State a hypothesis
- Conduct an experiment
- Analyze the results
- Make a conclusion
7
Q
What are the two subcategories of empirical research?
A
Observation: no control over exposure or treatment
Experimental: leader of the experiment has control over the experimental group
8
Q
Define basic and applied research
A
Basic: considered to involve the search for knowledge without a defined goal of utility or specific purpose
Applied: problem oriented and is directed towards a defined and purposeful end
9
Q
What are CIHR’s four pillars of health?
A
- Biomedical (mechanisms of disease)
- Clinical research (on, for patients; diagnosis and intervention)
- Health services and policy research (quality, cost, delivery)
- Social, cultural, environmental, and population health research
10
Q
What are youngs four categories about the purpose of health?
A
- To describe
- comparisons between people or groups
- illustrate differences in health - To explain
- cohort study often used
- following groups over time and monitoring health risks and outcomes - To predict and 4. To control
- develop and evaluate strategies to mitigate health problems
- need collaboration between policy makers and researchers
11
Q
Name some major research milestones in Canada.
A
1921: production of insulin
1930: creation of pablum
- feeding babies better
1945: polio vaccine
1951: first external pacemaker
1951: blasting away cancer cells
1960’s: addition of vitamin d to milk
2000: CIHR founded
2005: learning about autism
12
Q
What is a research paradigm?
A
Ones beliefs about what constitutes knowledge and how it is generalized
A paradigm is a belief system that guides the way we do things or more formally establishes a set of practices
13
Q
What are the three types of research paradigm?
A
Epistemology: nature and definition of truth
Ontology: nature of reality
Methodology: how you go about collecting data
14
Q
What are the three types of epistemology?
A
Positivism
Interpretivism
Critical realism
15
Q
What is positivism?
A
Valid knowledge and truth is generated through scientific process
Based on observation/measurement and generalization
Things you can actually measure
16
Q
What was positivism criticized for?
A
Focusing too much in characteristics of individuals
17
Q
What is interpretivism?
A
Seeks to generate a subjective understanding of social phenomena
Understanding what the world looks like through the eyes of those studied
18
Q
What is critical realism?
A
True knowledge and truth is often generated by theorizing rather then measuring or observing
Reality exists independently of individuals perceptions
19
Q
What are the two types of ontology?
A
Objectivism
Constructivism
20
Q
What is objectivism?
A
Study phenomena that exists as external objects
Beyond influence of researcher
Ex. Height or weight
21
Q
What is constructivism?
A
Study socially constructed objects
Beliefs, ideologies, behaviours and human actions
22
Q
What are the two types of methodology?
A
Quantitative
Qualitative
23
Q
Describe quantitative methology
A
Relies on numeric data and statistical analysis
Often collected via large scale social and epidemiological surveys with fixed response ranges
24
Q
Describe qualitative methodology
A
Mostly use open ended research questions concerned with meaning
One to one interviews, focus groups, oral history, or analysis of written or visual material
Researcher is in close contact with people, place, and events that become the research field
25
What are the two phases of theorizing?
Deduction
| Induction
26
Define deduction
Testing of pre-existing hypothesis
| Collect data to test a hypothesis
27
Define induction
Generalizing new theories
| Findings from a study may be used to generate a new question or hypothesis
28
What is the qualitative/quantitative divide?
Tendency to view them as mutually exclusive
| Mixed method design could blend the advantages of both traditions
29
What is the role of the researcher in the research process?
Study specific: research question, study design, ethics, data collection and analysis, secure and manage data, prepare study findings, develop a new research question
Administrative: establish a budget, records, timeline, supervisor
30
What are the 12 steps to research?
1. Identify the research or topic idea
2. Literature search
3. Define the problem
4. Developing a good research question
5. Generate hypothesis
6. Choosing the right study design
7. Defining the variable
8. Identify the study population
9. Conduct study
10. Data anaylsis
11. Getting the word out
12. Amend research question
31
Describe the process of identifying a research topic or area
```
Personal interest or questions
Professional experience
Which topics have grants
Literature
Professional meeting
Discussion
```
32
Describe the literature search
Identify studies relevant to your research study
Choose more recent papers
Try review papers
33
What are serials, periodicals, journals and grey literature?
Serials: publication on a continuing basis
Periodicals: published periodically
Journals: scholarly focus, peer reviewed
Grey literature: thesis material, non standard literature material
34
How do you define the problem?
Narrow down a topic area
Prepare a problem statement - a concisely written phrase
Avoid being vague
35
Describe a good research question
Focuses on only 2 or 3 variables
Is designed with respect to current knowledge
Can be investigated with available time/resources/ethical constraints
Can use comparative terms
Must use clear concepts
Include cause and effect relationship
Does not leave room for ambiguity
36
What are the different types of research questions?
Factual: simply looking for a causal relationship and describe them
Comparative: two alternatives to a situation and apply them in actual practice
Predictive: how things might be in the future
Problem solving: propose solution
Paradoxical: explore an apparently contradictory situation to make a suggestion for resolving the contradiction
37
What does FINER stand for?
```
Feasible
Interesting
Novel: in relation to previous findings, new setting, new population
Ethical
Relèvent
```
38
How do you generate a hypothesis?
Express a relationship between two variables
Testable statement between the relationship
Has an independent and dependent variable
39
Define null and alternate hypothesis?
Bill hypothesis: no significant effect between the independent and the dependent variables
Alternative: significant effect between the dependent and the independent variable
40
What are the main types of study design?
Experimental
Exploratory
Descriptive
41
What are naturalistic observations?
Watch subjects in their environment
| Do not manipulate environment
42
What is the Hawthorne effect?
People are in a study and know they are being watched so they change their behaviour
43
What are Cade studies?
Descriptive
| Detailed picture of one or a few subjects
44
What is the correlation method?
Correlation expressed a relationship between two variables
| Does not show correlation
45
What's is the correlation coefficient?
A number that measures the strength of a relationship
46
What are the different types of variables?
Confounding: causes a change in B that is not A
Continuous: age
Categorical: male or female
Binary: outcome or not
Ordinal: used to rank a sample of individuals with respect to some characteristic
Dummy; created by recording categorical variables that have more then two categories into a series of binary variables
47
Define identifying a study population
Who or what
Inclusion/exclusion criteria
Sample size calculation
48
What is the Nuremberg code?
1947
Scientific to medical experiments
Emerged from nazi war crime trials
49
What was the declaration of Helsinki?
A series of guidelines adopted in the 18th world medical assembly
Concern for the interests of the subject must always prevail over the interest of science and society
50
What is the Belmont report?
Created in wake of tiskigee outcry
Respect for persons - informed consent
Beneficience - assessment of risks and benefits
Justice - fair selection of participants
51
What are the three principles of the tri-council policy statement?
1. Respect for persons
2. Concern for welfare
3. Justice
52
Describe principle 1
Respecting autonomy: involved as participants, free and informed consent, accountability and transparency
Protecting those with developing or diminishing autonomy
Confidentially and privacy
Fair recruitment
Follow up and communication of risks
Collaborative research
53
What should informed Vincent include?
```
About
Funding
Description of participation
Alternative ways to do the study
Risks
Benefits
Withdrawal
```
54
Describe principle 2.
All impacts on physical mental and spiritual health as well as physical, economical, and social circumstances
55
Describe principle 3
Obligation to treat fairly and equitably
Equal access to benefits/equal share of burden
Avoid under or overprotection
Sample selection
Fair distribution of risks
Fair distrabution of benefits
56
What is the research ethics board?
Can help strengthen research
| Protects participants and researchers
57
When are research boards needed?
All research involving human participants whether funded or not
Must be obtained before research begins
Also required for research involving human biological material
58
What are some examples of special populations?
Children: free informed consent of competent adolescent or parent
Elderly: decision making capacity is severely compromised, must give advanced authorization or consent from another individual
Aboriginal: requirement of community engagement
59
What projects don't require ethics reviews?
No humans
Public data
No interactions
No identification of individuals during dissemination
60
What are the different types of data sources?
Surveillence systems
Population based sources
Institution based sources
61
What are the different types of population based sources?
Censuses
Registeries
Vital registration systems
Household surveys
62
What are the different types of institution based sources?
Resource records
Service records
Individual records
63
Describe serveillence systems
Can provided detailed data on a single condition or from selected sites
Not always representative of population
May collect little information relèvent to equity stratifiers
64
What are the different types of serveillance systems?
Outbreak disease serveillance
Sentinel surveillance
Risk factor surveillance
Demographic surveillance
65
Describe outbreak disease surveillance
Aims to track cases of epidemic prone diseases as well as their risk factors
Often relies on frequent reporting by health facilities
66
Describe sentinel surveillance
Uses a sample of clinics for intensified monitoring
| Used by disease programs such as HIV and malaria
67
Describe risk factor surveillance
Describes data collection and analysis in noncommunicable disease monitoring
Often focuses on data obtained through surveys
68
Describe demographic surveillance
Found in many low to middle income places
Sites have a longitudinal birth and death registration system for a local population to collect information about the cause of death and other health related data
69
What is a census?
May be a good source of info about equity stratifiers but usually contains only limited info on health
70
How is census geography divided?
Provinces and territories
Census divisions
Census subdivisions: municipalities
Dissemination areas: 400-700 people
71
What are some special geographical units in Canada?
Census metropolitan areas: a grouping of census subdivisions compromising of a large urban area and surrounding urban fringes
Census agglomération areas: smaller version of CMA
Census tracts: CMA's and CAs with pop >50000 are subdivided into 2500 to 8000
Localities: historical names location or place
72
Describe a vital registration system
National birth and death registries
Best and most reliable source for fertility, mortality, life expectancy, and cause of death statistics
Often be linked to information on sex, geographical region, occupation, education
73
What did James farr do?
Developed an early disease classification system
Founder of demography
Collected and analyzed bills of mortality
Collected and analyzed Britains mortality statistics
Developed basic practices used today on vital statistics and disease classification
74
Describe the ICD-10 system
21 major chapters based mainly on organ systems
Each divided in paragraphs and subsections
Ex C34.4 lung cancer, lower lone
Uses alphanumeric code that indicates the location of the concept within a disease hierarchy
75
Define immediate, underlying, and antécédent cause
Immediate: condition leading directly to death
Underlying: disease or injury that initiates the train of events leading directly to death
Antecedent: intervening cause of death between the intermediate and underlying cause of death
76
Describe household surveys
Most common and overall most reliable data source
Representative for a specific population
Rich data on a specific health topic as well as living standards and other complimentary variables
Allows for measurement of time trends
Conducted in multiple countries
77
Describe surveys
Can be targeted at specific conditions or more general
78
What is the CCHS objectives?
Provide timely, consistent, cross sectional estimates of health determinants, health status, and health system utilization across Canada
79
Describe institution based data sources
Data are readily and quickly available
Can be used at lower administrative levels
May be fragmented or poor quality and cannot be linked to other sources
80
What are some methodological issues of the disease registry?
Classification rules: What to do when the rules change
Need for standard diagnostic criteria
Validity of diagnosis
Completeness of capture
Representativeness of registered subjects
Methods of capturing information required on each subject
81
Describe active versus passive reporting for subject identification in registeries
Passive: subjects identified using existing records with no active reporting by MD, patient, etc
Active: MD required to report anyone with diagnosis
Other: volunteers, members of patient support groups
82
What are some uses of registry data?
Descriptive epidemiology of disease
Generate etiological hypothesis
Prognosis
Source of subjects for studies of etiology and prognosis
83
Define study designs
Determined by how one chooses or samples and measures the exposure and disease or outcome states
84
Define incidence rates
Number of new cases of disease in defined population at risk per into time
85
Define prevalence proportion
Number of existing cases in a defined population at risk during one point in time or a period of time
86
What is the optimal study design?
Driven by study question
Available population
Resources
Current state of research
87
Define epidemiology
How often health related issues take place in different groups of people, why patterns of health or disease exist between populations with an aim to control health problems
88
What are the different types of observational studies?
```
Descriptive
Ecological
Cross-sectional
Case-control
Cohort
```
89
What are the two types of intervention?
Randomized control trial
| Experiment
90
What are the two types of quantitative research methods?
Observational
| Interventional
91
What is a cohort?
A group of people with something in common, usually an exposure or involvement in a define population group
92
What is a cohort study?
An analytical study which is undertaken to obtain additional evidence to refute or support existence of association between suspected cause and disease
93
What are some features of cohort studies?
Cohorts are identified prior to appearance of disease under investigation
Study groups are observed over a period of time to determine the frequency of disease among them
Proceeds from cause to effect
94
What occurs at the end of the followup period in cohort studies?
```
Calculate measure of frequency:
Cumulative incidence (incidence proportion, attack rate, doesn't account for people moving)
Incidence density (takes into account person time in followup)
```
95
When should you use a cohort study?
There is good evidence of an association between exposure and disease from other studies
Exposure is rare
Attrition of study population (loss of study population) can be minimized
Sufficient funds are available
96
What is the frame work or a cohort study?
Exposed or unexposed go to diseased or non-diseased
97
What must be considered in the selection of a cohort?
Must be free from disease under study
Both groups should be equally susceptible to disease under study
Must be comparable in respect of all variable which influence the occurence of disease
Diagnostic and eligibility criteria of the disease must be defined before hand
98
What are the three types of cohort study?
Prospective study
Retrospective study
Ambidirectional study
99
Describe a prospective cohort study?
Start with a reference population some of whom have certain characteristics or attributes relevant to the study with others who do not have those characteristics
Both groups should be free from te condition under consideration at the onset
100
What are some possible problems of the prospective cohort study?
```
Long
Expensive
May lose track of subject
If really rare not enough people develop it
Exposure can change over time
```
101
What is a retrospective cohort study?
```
One in which the outcomes have all occurred before the start of the investigation
Info is less complete and less accurate
Not useful for emerging new exposures
Less costly
Shorter
```
102
What is an ambi-directional cohort study?
Elements of prospective and retrospective cohort are combined
Cohort is identified from past records and assesses of date for the outcome
Same cohort is the followup prospectively into the future for the further assessment of outcome
More complete and accurate info
Useful in new emerging exposures
More expensive and longer
103
What are prognostic cohort studies?
Used to identify factor that might influence the prognosis after a diagnosis or treatment
104
What are some features of a prognostic cohort study?
Cohort consists of cases diagnosed at a fixed time or cases treated at a fixed time by a medical or surgical treatment, rehabilitation procedure, psychological adjustment
105
What are the steps to a cohort study?
```
Selection of study population
Obtaining data on exposure
Selection of comparison group
Follow up
Analysis
```
106
Describe the selection of study subjects?
The usual procedure is to locate or identify the cohort, which may be a total population in an area of sample thereof. Cohort can be community, exposure, birth, occupational, marriage, diagnosed or treatment
107
What is an open or dynamic cohort?
A population in which the person time experience can accrue from a changing roster of individuals
108
What is a fixed cohort?
Exposure groups in a cohort study are defined at the start of followup with no movement of individuals between the exposure groups during the followup
109
What are some ways that we can obtain information on exposure?
Cohort members: interviews, questionnaires
Review or records
Medical examination/special tests
Environmental survey
110
What is an internal comparison group?
Single cohort enters the study and its members on the basis of information obtained, can be classified into several comparison according to degree of exposure
111
What is an external comparison group?
When information on degree of exposure is not available
| Comparison with general population can also be used as comparison group
112
Describe the followup of the cohort study?
My be years or even decades
| Method should be determined depending on the outcome of the study to obtain data for assessing outcome
113
What occurs during analysis of a cohort study?
Data analyzed in terms of indicidence rate of outcome among exposed and non exposed
Estimation of risk
114
When is cumulative incidence used in a cohort study?
Acute diseases with short induction periods and a short time of followup
115
When is incidence density used in a cohort study?
Chronic diseases with short induction periods and a short time of followup
116
What is relative risk and how is it calculated?
Estimates the magnitude of an association between exposure and disease
Indicates the likelihood of developing the disease in exposed group relative to non exposed
RR= incidence in exposed/incidence in non-exposed
117
What are ecological studies?
Unit of analysis is the group not the individual
| Correlations are obtained between exposure rates and disease rates among different groups or population
118
What are the two types of ecological studies?
Ecological comparison study: examines exposure rates among different groups over the same time period
Ecological trend study: examines changes in exposure and changes in disease within the same community, country, or other aggregate unit
119
Define ecological fallacy
Observations made at the group level may not represent the exposure-disease relationship at the individual level
120
What are the advantages and disadvantages of ecological studies?
Advantages: quick, simple, inexpensive, good approach for generating hypothesis when a disease is of unknown origin
Disadvantages: ecological fallacy, imprecise measurement of exposure and disease
121
Define a case control study
Observational study of groups having a specific health event compared to a group without the health event
122
What is the traditional design for a case control study?
Controls samples from the population still at risk at the end of the study period
Disease odd ratio = exposure odds ratio
123
What are the advantages to case control studies?
Better suited to study of rare disease than cohort
Relatively quick
Preferred when exposure data are difficult or expensive to obtain
Can evaluate more than one hypothesis
Little is known about disease
Studies in dynamic population
124
What are the disadvantages of case control studies?
Insufficient for rare exposures
Reliance on retrospective data
Sometimes difficult to infer temporal relationship between exposure and disease
More susceptible to participation bias
Challenges in identifying suitable control series
125
What is the difference in sampling between case control and cohort?
Cohort: sampling is by exposure
| Case control: sampling is by outcome
126
What is preferred between incident and prevalence cases in the case control approach?
Incident cases are preferred
127
What are some sources of identifying cases in case control studies?
```
Death certificates
Registeries
Hospital/clinic lists
Pathology records
Advertising
```
128
What are some sources of controls in case control studies?
```
Hôpital controls
Friend controls
Friend/family controls
Neighbourhood controls
Dead controls
```
129
What design considerations are there regarding case control studies?
Associating being estimated: type of event/exposure
Incidence rate of event
Prevalence of exposure
Essential risk factors that may be associated with exposure
Ability to measure accurately these variables
130
Define matching
The process of making study groups comparable to factors that are risk factors for the outcome and are associated with exposure
131
Define individual matching
Caliper (interval) for continuous covariances or exact matching for categorical variables
P
132
Define frequency matching
Distrabution between groups ~ equal
133
What is the equation for relative risk in a cohort study?
RR= (a/a+b)/(c/c+d)
134
What is the equation for OR?
OR= (axd)/(bxc)
135
What are some biases in case control studies?
Selection bias: non response, detection bias
| Observation bias: recall bias - cases are more likely to remember exposure than controls
136
What are mathematical parameters used for in health research?
Used to relate the number of health outcomes or cases of a disease (numerator) to the size of the source population (denominator) in which they occurred
137
What do rates and proportions tell us?
Rates tell us how fast the disease is occurring in a population
Proportions tell us what fraction of the population is affected
138
Describe ratios
Obtained by dividing one quantity by another
| May be related or completely independent
139
Describe proportions
A ratio when the numerator is included in the denominator
| Often expressed as a percent
140
Describe incidence
Related to the development of new cases of disease
Calculated for a given amount of time
Incidence = (#new cases)/(#at risk)
141
Describe rate
Measures how quickly something of interest happens
| (#new cases)/(#total time among disease free subjects) x 1000
142
Define period prevelence
Number of people with a health condition anytime during a follow up period
PP = (C + I)/N
143
What might a high or low prevelence reflect?
High: high risk, prolonged survival without cure
Low: low risk, rapid fatal progression, rapid cure
144
Define risk
Proabability that an individual with certain characteristics will develop or die from a disease or even more generally, will experience a health status change over a specified follow up interval
Assumes that a person does not have disease at the beginning
Does not die from other causes
0 to 1
145
What is cumulative incidence?
```
Probability of developing outcome in a defined period time
Ranges from 0 to 1
Unitless
CI = (#new cases)/(#disease free people)
Assumes fixed close cohort
```
146
What are some problems with cumulative incidence?
Attrition is a reality
Formula does not reflect continually changing population size for dynamic cohorts
Does not allow people to be followed for different periods
147
Describe incidence density
Rate of developing disease
ID = (new cases)/(person time at risk)
Not as easy to use for individual risk prediction
Accounts for losses, competing risks, changes in exposure over time, differential follow up time
148
What two conditions must a categorical variable satisfy?
Categories are mutually exclusive
| Categories must be collectively exhaustive
149
What are the four scales of measurement?
Nominal: categories without order
Ordinal: categories with order
Interval: distance is meaningful between categories
Ratio: scale of categories have absolute zero
150
How are the scales of measurement differentiated?
1. Rules for assigning numbers to values of the variable
2. Mathematical properties of the scales
3. Types of stats used with them
151
Define classical test theory
The score that is obtained (Xo) on a scale consists of two parts, the true score (Xt) plus some error (E)
Error is unrelated to true score
Expected value of the error for each item is zero, errors with cancel each other out
152
What is reliability?
Consistency in measurement
153
What are some sources of unreliability?
Meaning of questions is unclear or produces random answers
Raters not adaquately trained on method o making rating
Instructions may be unclear or inconsistent
Outsides event may have an effect
154
Define equivalency, stability, internal, inter-rater, and intra-rater reliability
Equivalency: related to the cooccurrence of two items
Stability: related to time consistency
Internal: related to the instruments
Inter-rater: related to the examiners criterion
Intra-rater: related to the examiners criterion
155
Describe equivalency reliability
The extent to which two items measure identical concepts at an identical level of difficulty
Determine by relating two sets of test scores to one another to highlight the degree of relationship or association
156
Describe stability reliability
Test by computing correlation of two or more forms, taken under same circumstances
Appropriate only if the phenomenon that the test measures is known to be stable over the interval between the assessments
157
Describe internal consistency
The extent to which tests or procedures added the same characteristic, skill, or quality
Mesure of precision between the measuring instruments used in a study
Helps interpret data and predict the value of scores and the limits of the relationship among variables
158
Describe inter-related reliability
Dependent upon the ability of two or more individuals to be consistant
Uses training, education and monitoring skills
159
Describe intra-rater reliability
Type of reliability assessment in which the same assessment is completed by the same rater on two or more occasions
160
Define reliability
Ratio of true variance to observe variance
161
Define reliability coefficient
A numerical index which assumes a value between 0 and 1
162
What are some methods of estimating reliability?
Test-retest (coefficient of stability)
Parallel forms: repeated measures with equivalent forms of a test (coefficient of equivalence)
Internal consistency: repeated measures using items on a single test
Inter-rater
163
Describe test-retest reliability
Situation: same people taking two administrations of the same test
Procedure: correlates scores on the two tests which yields the coefficient of stability
Meaning: the extent to which scores on a test can be generalized over different occasions (temporal stability)
Appropriate use: information about the stability of the trait over time
164
Describe parallel forms reliability
Situation: testing the same people on different but comparable forms of the test
Procedure: correlate the scores from the two tests which yield a coefficient of equivalence
Meaning: The consistance of response to different item (testing is immediate) samples and across occasions (testing is delayed)
Appropriate use: to provide info about the equivalence of forms
165
Describe inter-rater reliability
Situation: having a sample of test papers scored independently by two examiners
Procedure: correlate the two sets of scores
Meaning: measure of scorer reliability which yield the coefficient of concordance
Appropriate use: for ensuring consistency between raters
166
Define validity
Measurement: are the observations directly and truly linked to the dimension or concept claimed?
Research design: how well does the experiment or study control the situation so that we are confident that the relationships or results observed were due to the impact of the independent variable?
167
What is content validity and how do you improve it?
Are all aspects of the dimension or concept covered?
Are any aspects over or under emphasized
Does the measure differentiate this dimension from other similar ones
Improve by thorough search of the literature and consult with experts who disagree with you persepective
168
What is face validity?
Indeed that a test is valid by definition
| It is clear that the test measures what it is supposed to
169
What is construct validity?
Refers to the general validity of the measurement tool
| Does the instrument measure that construct that it is intended to?
170
What is a construct and what two properties do they all share?
Are ideas that help summarize a group of related phenomenon or objects
1. Are abstract summaries of some regularity in nature
2. Related with concrete, observable entities
171
What is criterion validity?
A measure is valid if it has a strong relationship to an external criterion
Eg. A music audition is valid if it selects the better player over those with less ability
172
What is predictive validity?
The extent to which scores on the scale are related to and predictive of, some future outcome that is of practical utility
Eg. A GRE is a valid measure if people do well on the GRE succeed in graduate school
173
What are basic steps of predictive validity?
1. Obtain test scores from a group of respondents, but do not use the test in making a decision
2. At some late time, obtain a performance measure for those respondents, and correlate these measures with test scores to obtain predictive validity
174
What is concurrent validity?
Does this measure correlate strongly with something that it logically should right now?
Compares measure taken at the same time unlike predictive
Eg. Obesity and skinfold thickness
175
What factors influence validity?
```
Inadequate sample
Items that do not function as intended
Improper arrangement/unclear directions
Two few items for interpretation
Improper test administration
Scoring that is subjective
```
176
What did James lind contribute to epidemiology?
```
Epidemiologic questions/hypotheses
Clinical observation
Study design
Source of disease: place, time, season
Replication
```
177
What is the purpose of randomization?
Make the treatment groups comparable
178
What is a randomized controlled trial?
A study in which a group of investigators study an intervention in a series of individuals who receive the intervention in a random order
Intervention to be tested is experimental group
Other is the control group
Control can be conventional practice, a placebo, or no intervention at all
179
What is RCT the most powerful tool in modern clinical research?
Prospective
Controlled
Unbiased
180
What are RCT studies without concurrent controls?
Case Aries studies
Historical controls:
- type of patient may change, due to eligibility criteria
- environment changes
- data quality often quite different between groups
181
What is random allocation?
All participants have the same chance of being assigned to each of the study groups
The purpose is to keep both groups as similar to each as possible at the start of the trial
182
Hat are the practical steps about randomization?
1. Randomize at last possible moment to reduce change of subject withdrawing from study
2. Avoid quasi randomization schemes that involve some kind of alteration
3. Randomize at a location that is removed from the treatment centre to preclude knowledge from reaching doctors
4. Create sequence by generating numbers randomly to allocate patients to treatment groups
183
What are the different types of randomization?
1. Simple randomization
2. Restricted randomization
3. Stratified randomization
184
What is stratified randomization?
Random assignment within groups defined by participant characteristic such as age or disease severity, intended to ensure good balance of these factors across intervention groups
185
Define compliance
The willingness of the participants to carry out the procedures according to the established protocols
186
What are drop outs and drop ins?
Drop outs: participants who do not adhere to the experimental regimen during the follow up
Drop ins: participants who do not adhere to the control regimen during the follow up
187
What is masking/blinding?
Used to increase the objectivity of the persons dealing with the randomized study
Can be done to participants, treaters, data collectors, data analysts, and investigators
188
Define a placebo
A medical treatment which is administered as if it were a therapy, but which has no therapeutic value other than the placebo effect
189
Define nocebo
Treatment like a placebo but which has a harmful result
190
Why is blinding difficult?
Having a placebo that same shape, formula and taste is very costly and time consuming
Drug side effects
Impossible if surgical and medical treatments are compared
The need for urgent unblinking code in case of serious side effects
191
What are the different types of RCTs?
Open trials
Single blind trials
Double blind trials
Triple blind trials
192
What are the disadvantages of RCTs?
Expensive
Volunteer bias
Ethically problematic at times
193
What are the biases in RCT?
Selection bias: due to lack of concealment of allocation, attrition and differential losses
Information bias: participant response bias and outcome ascertainment bias
Bias due to competing interests
Reporting bias: publication bias, time lag bias, outcome reporting bias
194
What are the steps to RTC?
```
Set up a protocol
Recruit patients
Randomize
Follow up
Analyze data
Publish
```
195
What is primary data analysis?
Intention to treat
| Analyze according to original allocation, net effect of non-complience is to reduce the observed differences
196
What is secondary data anaylsis?
Actual treatment received
Based on observed data
No benefit of randomization
197
Define efficacy
Does the intervention work in the people who actually receive it
Tend to be explanatory
Goal is high compliance
198
Define effectiveness
How does the intervention work in those offered it?
| Tends to be pragmatic
199
What are the different RCT study designs?
Parallel treatment or simple
Crossover (planned or unplanned)
Factorial
200
When is it ethical to randomize?
Uncertainty principle
| Clinical equipoisep
201
Define sampling
A means of selecting a subset of units from a population for the purpose of collecting information from those units to draw inferences about that population as a whole
202
What are parameters?
Characteristic of a population
203
What 3 factors influence sample representativeness?
Sampling procedure
Sample size
Participation
204
When might you sample the entire population?
When your population is very small
When you have extensive resources
When you don't expect a very high response
205
What is a sample frame?
The target population you wish to research
206
Define census
All the respondents in the sample frame participating in the research
207
What is probability sampling?
Relies on probability theory to describe the odds of individual being sampled
Sampling frame provides an extensive and up to date list of all members of the population
Every unit has a chance of being selected
208
Describe probability sampling
Selection of units based on randomized chance
Complex, time consuming, and costly
Inclusion probability can be calculated
Prevalence, incidence, and sampling error can be calculated
Inferences can be made about population since they are randomly selected and have a zero inclusion probability
209
What are the different types of probability sampling?
```
Bernoulli
Simple random
Systematic
Cluster
Probability proportion to size
The random method of PPS
The systematic method
Stratisfied
Multi-stage
```
210
Describe Bernoulli sampling
Useful in moderate to large size samples from very large populations
To draw a sample size n from a file size N it is sufficient to draw a random number R between 1 and the sampling fraction f=n/N
Equal Probabiliy and without replacement
Sample sizes are not fixed
211
How do you determine who is included in a sample in Bernoulli sampling?
Ex. F=15/60=0.25
<= 0.25 included
> 0.25 not included
212
Describe random sampling
Selected by using chance or random numbers
All units have equal chance of being selected
Ex. Drawing names out of a hat
Full list is required
213
Describe simple random sampling
One step selection method ensures every possible sample of size n has an equal chance
Each unit has equal inclusion probability
Can be done with or without replacement
Needs sampling frame with units numbered 1 to N
First n units make up the sample
214
What are some advantages of random sampling?
Can estimate the size of sampling error
| The sample size needed for good representation of the population is smaller
215
What are some disadvantages of random sampling?
Need to be able to list every member of the population
Usually either to use conveniently available groups
May need to select replacements for some cases
216
Describe systematic sampling
Ex. Every third person on a list
Select a random starting point and then select every kth subject in the population
Simple to use so used often
217
Describe cluster sampling
Might not be possible to sample individual units
Randomly select complete groups of population units from the sampling frame
Can derive estimates at a cluster level
218
What are the two steps to cluster sampling?
Indemnify clusters
| Select a sample of clusters then interview individuals within a cluster
219
Describe cluster random Sampling
Groups are selected for their geographical location
| Ex. School is the cluster with the children being randomly selected randomly from within the cluster
220
Describe stratisfied sampling
Not a selection method but a way to organize the population in homogeneous mutually exclusive categories
Divide the population into at least 2 groups with common characteristics then draw some from each group
Results in a more representative sample
Same as quota sampling but each quota is filled randomly
221
What is stratisfied sampling good for?
Skewed populations and to ensure adaquate sample sizes for domains of interest
222
What are some advantages of stratisfied random sampling?
The important groups can be proportionally represented
| The exact representativeness of the sample is known
223
What are disadvantages of stratisfied random sampling?
Need list of all members of a population and their characteristics
Cost
Gain in sample accuracy often small in comparison to simple random sampling
224
What is non probability sampling?
Choose individuals in a selective way
Probability of selection cannot be accurately determined
Some elements have no chance of selection (uncovered)
Allows the estimation of sampling error
225
Describe probability-proportion-to-size sampling
Can yield increases in precision
| Commonly use random method, systematic method, and randomized systematic method
226
Describe multi-stage sampling
Selecting a sample in two or more successive stages
Primary sampling unit at first stage and second stage units at second
Units are each stage are different in structure and are hierarchical
Common design involves two stage cluster sampling using an area frame at the first stage and then a systematic sample of dwellings within a region at a second stage
227
What are the different types of non-probability sampling?
```
Convenient or haphazard
Judgment
Volunteer
Quota
Modified probability
Snowball
```
228
Describe convenient sampling
Use subjects that are easily accessible
Ex. Family members or students in a class room
Cannot make generalizations about the total population - non representativeness
229
Describe volunteer sample
Respondents are volunteers
Sometimes screening must be done to make sure they have certain conditions
Maybe subject to important bias - difficulties in generalizing
230
Describe judgement sample
Based on previous ideas of population composition
Expert with knowledge of population often decides on which individuals should be sampled
Can be helpful for exploratory studies, focus group studies, or in depth interviews to test aspects of questions
231
Describe quota sampling
Segmented into mutually exclusive subgroups
Then judgement used to select subjects or units from each segment based on specified proportions
Selection of the sample is non random
Contacted individuals who don't participate are replaced by those who are willing to - can introduce nonresponse bias
232
Describe modified probability sample
Includes multiple stages
First stages based on probability sampling
Latter stages case on non-probability sampling
233
Describe snowball sampling
Useful for small and hard to reach populations
Researchers asks to be out in touch with any friends or associates who also have similar situation
Not représentative
234
Define estimation
Technique for producing information on population of interest based on data gathered from sample of population
235
What is the first step in estimation?
Assign a weight to each sampled unit
236
How do you calculate variance?
Calculate the mean
For each number subtract the mean and square the result
Find the average of those calculate values
* when working with a sample divide by n-1 not n
237
What is the formula for variance of proportion?
Population
Variance= p x (1-p)/N
Sample
Variance= p x (1-p)/(N-1)
