Brainscape's Knowledge GenomeTM

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


See full index

Statistics > Chapters 13, 14, 15, 16 > Flashcards

Chapters 13, 14, 15, 16 Flashcards

1
Q

Describe the purpose of descriptive research

A
  • To document the factors that describe characteristics, behaviors and conditions of individuals and groups.
  • Descriptive data supply the foundation for classifying individuals, for identifying relevant variables, and for asking new research questions.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Describe the purpose of developmental research

A
  • Describes developmental change - for instance, change in motor development in infants and children
  • Describes sequencing of behaviors in people over time
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Describe the purpose of normative research

A
  • To describe typical or standard values for characteristics of a given population
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Describe the purpose of qualitative research

A
  • to describe the complex nature of humans and how individuals perceive their experiences within a social context
  • to explore and understand human behavior
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Describe approaches to qualitative research

A
  • Phenomenology
  • Ethnography
  • Grounded Theory
  • Constant comparative analysis
  • Observation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Discuss analysis issues in qualitative research

A
  • -Involves many hours of sifting through narratives, coding, and organizing. Computer programs have been developed to help organize the data , not to analyze data as this would promote a loss of intimacy with the data as well as confidentiality and security of participants.
  • In qualitative research, the concept of measurement must be examined in terms of judgments rather than numerical equivalency.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Describe the role of descriptive surveys in research

A
  • Present group characteristics, weaknesses: accuracy of information, bias of sample, example of foot strike and minimalist shoes
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Discuss the purpose of case studies

A
  • provides an opportunity for understanding the totality of an individual’s condition outcomes and care
  • Understanding unusual patient conditions
  • Examples of innovative or creative therapies
  • Generating and testing theory
  • Providing future research directives
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Describe the structure of case studies

A
  • Involve an in-depth description of an individual’s condition or response to treatment; however, case studies can also focus on a group, institution, or other social unit, such as a particular school, healthcare setting, community or family. A description of interesting, new, and unique cases is necessary to build a foundation for clinical science and as a means of sharing special information among professional colleagues.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What are the Six types of descriptive research

A
  • Developmental
  • Natural History
  • Normative research
  • Qualitative research
  • Surveys
  • Case Studies
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Describe the Phenomenology approach to qualitative research

A
  • Drawing meaning from complex realities through careful analysis of first-person narrative material. I.e. illness, physical disability, and childbirth…book example of family with autistic child and how making life very routine was helpful
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Describe the Ethnography approach to qualitative research

A
  • The study of attitudes, beliefs, and behaviors of specific people within their own cultural milieu…researchers become immersed in culture to see how culture effects beliefs and attitudes…i.e. pregnancy and childbirth in Native American women
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Describe the Grounded Theory approach to qualitative research

A
  • The researcher collects, codes, and analyzes data simultaneously
  • Facilitates the identification of relevant variables, and using an inductive process, identification of theoretical concepts that are “grounded” in the observations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Describe the Constant Comparative analysis approach to qualitative research

A
  • As data are collected, they are analyzed and theories are tested. Theories evolve as research is ongoing. I.e. Jensen’s 2007 publication theory of what constituted expert practice in PT
  • At any point in the study, if data do not support the theory, the data are not discarded, but the theory is refined so that it fits the existing data
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Describe the Observation approach to qualitative research

A
  • non-participant, strictly observing or can be combined with interviews
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Describe the techniques for ensuring trustworthiness of qualitative data

A
  1. Triangulation: process by which concepts are confirmed by using more than one source of data, more than one data collection method, or more than one set of researchers. For example, a researcher may identify a specific concept through an interview, by direct observation of group performance, and by analysis of written material. If comparable conclusions are drawn, then internal validity is strengthened.
  2. Audit trail: a clear description and documentation of the thought processes used to interpret data assists in improving the validity of the findings as the reader can follow the investigators logic.
  3. Other strategies for improving accuracy include the involvement of more than one investigator to confirm ideas, and confirmation of conclusions with the subject of the study through member checks, and analysis until data saturation (no new themes identified)is reached.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Define exploratory research

A
  • The systematic investigation of relationships among two or more variables. Researchers use this approach to predict the effect of one variable on another or test relationships that are supported by clinical theory.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Compare and contrast longitudinal research with cross-sectional research

A
  • In longitudinal studies, the researcher follows a cohort of subjects over time performing repeated measures at prescribed intervals.
  • In cross sectional studies, a researcher studies a stratified group of subjects at one point in time and draws conclusions about a population by comparing the characteristics of those strata.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Explain correlation and regression

A
  • Correlation is the foundation of exploratory studies. It’s the measure of the degree of association among variables. Correlation is a function of covariation, that is, the extent to which one variable varies directly or indirectly with another variable. Example: You could examine the effect of nutritional status, depression, and sleep on fatigue in elderly patients.
  • Regression is used to establish the accuracy of prediction (predictive correlational studies are designed to predict a behavior or response based on the observed relationship between the behavior and other variables. These designs can be used to develop models such as clinical prediction rules.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Describe a case control study

A
  • A case control is a method of epidemiologic investigation in which groups of individuals are selected on the basis of whether or not they have the disorder under study. Cases are those with the disorder while controls are those without the disorder acting as the comparison.
  • The investigator then looks back in time interview, questionnaire, or chart review to determine if the groups differ with respect to exposure or characteristics that may put the person at risk for developing the condition of interest.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Outline considerations for selection of subjects in case control and cohort studies

A
  • Case control studies subjects selected based on whether or not they have disorder
  • Cohort studies subjects selected based on exposure rather than outcome/ development of the disorder
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What are the advantages and disadvantages of Longitudinal Research

A

Advantages:

  • Ability to accumulate data through intensive documentation of growth and change on the same individual allowing for observations of patterns of change and suggest causal relationships between variables
  • collected in time sequence allowing for documentation of direction as well as magnitude of change

Disadvantages:

  • extended obligation to a single project requiring long term commitment of resources
  • subjects can’t be replaced and compliance must be ensured
  • internal validity can be threatened by repeated testing, attrition secondary to extended data collection timeframe, and confounding variables that may affect the developmental sequence that’s being evaluated
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What are the advantages and disadvantages of Cross Sectional Research

A

Advantages:

  • More efficient than longitudinal study
  • Internal validity isn’t threatened by testing or history effects because subjects are tested only once at one point in time.

Disadvantage:
-Major threat to validity is selection as it’s difficult to know to what extent results reflect the effects of age or the passage of time versus the effects of extraneous variables.

*Many of the extraneous variables pertain to cohort effects which are not age specific but are due to a subjects generation or time of birth (exposure to health info, education, historical events that influenced life choices).

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

Describe a Cohort Study

A
  • A Cohort is defined as a group of individuals who are followed over time. The most common type of cohorts are geographic cohorts such as residents of a community or birth cohorts (baby boomers).
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

What are developmental and historical cohorts

A
  • Historical cohorts of those who experienced a common event (WWII veterans, experienced natural disaster)
  • Developmental cohorts are based on life changes (getting married, moving to nursing home)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

What are the five criteria to provide evidence for cause and effect

A
  • Time sequence
  • Strength of the association
  • Biologic credibility
  • Consistency (with other studies)
  • Dose-response relationship
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

Contrast Case control studies and Cohort Studies

A
  • Case controls are usually retrospective and work well for rare conditions
  • Cohorts are usually prospective and work well for common conditions
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

What are the potentials for bias in case control studies

A
  • Selection Bias
  • Misclassification Bias
  • Observational Bias
  • Interviewer Bias
  • Recall Bias
29
Q

What are the potentials for bias in cohort studies

A
  • Bias is of less of a concern in prospective cohorts than in retrospective case controls, however..
  • Misclassification of either exposure or disease can play a role and
  • because of the longitudinal nature of prospective cohorts, they are prone to attrition
30
Q

Describe Selection Bias

A
  • In order to avoid selection bias, cases and controls must be chosen regardless of their exposure history, otherwise it will not be possible to determine if the exposure is truly related to the disease. Also when samples are composed of subjects who consented, self-selection bias can occur.
31
Q

Describe Misclassification Bias

A
  • Misclassification bias can occur if the subjects who have the disease are mistakenly put in the control or vice versa. If this misclassification is random, and equally present in both groups, it’s considered nondifferential misclassification. If you have differential misclassification, the results may over or under estimate the relationship.
32
Q

Describe Observational Bias

A
  • Observational Bias occurs when there is systematic differences in the way the information about disease or exposure is obtained from study groups.
33
Q

Describe Interviewer Bias

A
  • Interviewer Bias is introduced when the individual gathering data elicits, records, or interprets information differentially from controls or cases.
34
Q

Describe Recall Bias

A
  • Recall Bias occurs when subjects who have experienced a specific disorder remember their exposure history differently from those who aren’t affected. It’s not unusual for individuals who have a disease to analyze their habits or past experiences with greater depth or accuracy than those who are healthy.
35
Q

Describe the role of surveys in clinical research

A
  • Surveys are a series of questions posed to a group and in research are often concerned with describing current practices, attitudes, and values, or characteristics of specific groups (can be experimental, exploratory, or descriptive). For example, surveys have been used to compare medication, manipulation, and acupuncture for chronic lower back pain.
36
Q

Describe the basic structure of survey instruments

A
  • Interviews: The researcher asks the respondents specific questions and records their answers for later analysis
  • Questionnaires: structured surveys that are self-administered using pen and paper or electronic format.
  • Both are self administered making them vulnerable to recall bias
37
Q

Describe the process of designing a survey

A
  • Determine the research question
  • Define the purpose of the survey through a series of guiding questions or objectives that delineate what the what the researcher is trying to find out (focuses the content of the questionnaire)
  • Determine your hypothesis in order to guide statistics and conclusions
  • Design the instrument (survey) by writing a series of questions that address each behavior, knowledge, skill, or attitude reflected in the guiding questions.
  • Send preliminary drafts to a panel of colleagues who review
  • Pilot test on similar sample
38
Q

Discuss the characteristics of good survey questions

A

-Questions should be simple, succinct, grammatically correct, and unambiguous.
-Avoid the use of double barreled questions (using “or” or “and” to assess two things in a single question.
-Frequency and time measures should be defined appropriately within questions
Consider what you want (age, mileage,etc) and provide appropriate ranges of values or fill in the blank
-Sensitive questions should be phrased to put the respondent at ease such as “Many people forget to take their medication” when investigating compliance with med useage. Also, these questions should come toward the end of survey.
Demographics at beginning…don’t offend. (pilot test for sensitive questions)

39
Q

Distinguish between summative and cumulative scales

A
  • Summative is one that presents a total score with all items contributing equal weight to the total.
  • Cumulative scale demonstrates an accumulated characteristic, with each item representing an increasing amount of the attribute being measured.
    Example: Rasch Analysis: statistically manipulates ordinal data to create a linear measure on an interval scale. (Functional Independence Measure) If a scale truly represents a functional construct it should meet 3 measurement principles:
    1. Total score should level of function implied by the items
    2. Items will range in difficulty
    3. The rank order of difficulty should not change person to person
40
Q

Describe a Likert Scale

A
  • The Likert scale is a summative scale, most often used to assess attitudes or values. A series of statements are presented expressing a viewpoint and respondents are asked to select an appropriately ranked response that reflects their agreement or disagreement with each one. ie: Strongly agree, agree, neutral, disagree, Strongly Disagree
41
Q

Describe a Semantic Differential Scale

A
  • Semantic Differential: this method tries to measure the individuals feelings about a particular object or concept based on a continuum that extends between two extreme opposites. For example, we could ask respondents to rate their feelings about natural childbirth by checking the space that reflects their attitude on the scale ranging from negative (1) to positive (7).
  • Uses opposite adjectives
42
Q

Describe a Visual Analog Scale

A
  • A line is drawn , usually fixed at 100 mm in length, with word anchors on either end that represents extremes of the characteristic. Scored by measuring the distance of the mark from the left hand anchor in mm.
43
Q

What are some advantages and disadvantages of Interviews as survey instruments

A
  • Advantage: In depth analysis, data quality

- Disadvantage: cost/time, lack of anonymity

44
Q

What are some advantages and disadvantages of Questionnaires as survey instruments

A

Advantage:

  • More efficient as respondents complete them on their own time
  • Data can be gathered from large sample across a wide geographical area in a relatively short period of time.
  • Standardized so everyone is exposed to same questions
  • Questions allow for anonymity
  • Useful for phenomena that can be assessed through self observation

Disadvantages:

  • Potential for misunderstanding questions
  • Unknown accuracy or motivation of the respondent
  • Is the sample representative of the population
45
Q

Discuss advantages and disadvantages and when to use open ended vs closed ended questions

A
  • Open ended questions are useful in probing opinion and feelings without bias
  • Useful when researcher isn’t sure of all possible responses, however; difficult to code and analyze because so many different answers are obtained.
  • May be misunderstand therefore information gained is irrelevant. “What types of exercises do you do regularly?”
  • Closed ended questions are easily coded and provide greater uniformity across responses. The disadvantage is that it doesn’t allow the respondent to express their own personal viewpoints and therefore may provide a biased response set.
    a. Responses must be exhaustive
    b. Response categories must be mutually exclusive (if answers are close ask for the one best answer)
    c. Avoid leading the respondent by way of the order of answers
    d. If multiple answers are desired ask respondents to mark each choice individually (yes or no) rather than just having them mark “all answers that apply). (makes it easier to code)
46
Q

How is the Semantic differential scale different from the Likert scale

A

Different from the likert in 2 ways
- Only 2 extremes are labeled
- The continuum isn’t based on agree/disagree
Adjectives used in this scale fall along 3 underlying dimensions
1.Evaluation (nice-awful, good-bad, clean-dirty)
2.Potency (big-little, powerful-powerless, strong-weak)
3.Activity (fast-slow, alive-dead, noisy-quiet)

47
Q

Define Systematic Review

A
  • Refers to a rigorous process of searching, appraising, and summarizing existing information on a selected topic
48
Q

Define Meta Analysis

A
  • Combines studies using a quantitative index to develop a single overall estimate of the intervention effect
  • Used when selected studies provide common estimates of the same variables, the separate samples in each study can be viewed as part of one larger target population, allowing for synthesis of results
49
Q

Discuss how selection criteria are applied in the development of a systematic review

A
  • Selection criteria specify inclusion and exclusion requirements for studies to be used for the review
  • Based on type of study, level of evidence, participants, interventions, and outcome measures
50
Q

Categorize levels of evidence

A
  • Level One:
    a. SR of RCT
    b. RCT with narrow confidence interval
  • Level Two:
    a. SR of Cohort study
    b. Individual Cohort or low quality RCT
  • Level Three:
    a. SR of Case Control Studies
    b. Individual case control
  • Level Four:
    Case series or low quality cohort or case control
  • Level Five:
    Expert opinion or Bench research
51
Q

Discuss issues in searching the literature for references for systematic reviews

A
  • Describe the search strategy and find a comprehensive list of relevant documents to be considered
  • Indicate which databases were used and specific search terms entered
  • Include list of excluded studies with specific reasons for their exclusion
52
Q

What are the scales for assessing methodologic quality of research studies when conducting a systematic review

A
  • Jadad Scale
  • PEDro Scale
  • QUADAS Scale
53
Q

Discuss how effect size is used to compare studies for meta-analysis

A
  • Larger the difference, the greater the effect
  • Each study adds to the population parameter with
    effect size index
  • Leads to a more precise overall estimate
  • Means for quantitative variables
  • Proportions for frequencies for categorical data
  • Correlation values for measures of association
54
Q

Describe the purpose of sensitivity analysis

A
  • Because there are so many differences in study designs and methods of data synthesis, there is a question regarding the sensitivity of results of a SR
  • It is a technique that assesses if findings would change when key assumptions or decisions differ
  • Key assumptions include inclusion and exclusion criteria for SR and for Meta-Analysis involves reanalyzing data using different statistical approaches or accounting for inconsistencies in reporting of results in individual studies.
55
Q

Discuss the criteria for appraising systematic reviews and meta-analyses

A
  • Because Systematic Reviews and Meta analyses are seen as the highest form of evidence, a checklist has developed to help the reader decide if the review is valid in their presentation and findings
    1. Are the results of the study valid?
    2. What are the results?
    3. Will the results help me in caring for my patients?
56
Q

Who founded the town of Pinehurst, NC and in what year?

A
  • James Walker Tufts

- 1895

57
Q

Who is Donald Ross

A
  • Golf course designer from scotland

- Designed Pinehurst No’s 1, 2, and 3

58
Q

Identify and Describe the types of bias possible when conducting a systematic review

A
  • Publication Bias:
  • Selection Bias:
  • Performance Bias:
  • Attrition Bias:
  • Detection Bias:
59
Q

Describe the Jadad Scale

A
  • Instrument to measure the likelihood of bias
  • Composed of three questions
    1. Was the study described as randomized
    2. Was the study described as double blind
    3. Was there a description of withdrawals and dropouts
  • Two other parts concerned with randomization and blinding
  • Maximum score of 5
60
Q

Describe the PEDro Scale

A
  • Contains items related to:
    1. Randomization
    2. Blinding
    3. Attrition
    4. Analysis of design and statistics
  • 10 criteria, 1 point for yes, 0 for no
  • Maximum score of 10
61
Q

Describe the QUADAS Scale

A
  • Scale to review studies of diagnostic test accuracy

- 14 item scale

62
Q

Define Attrition Bias

A
  • Related to the differential loss of subjects across comparison groups
63
Q

Define Detection Bias

A
  • Occurs if outcome assessment differs across comparison groups
64
Q

What are the Effect Size and Effect Size Index

A
  • Effect size is an estimate of the magnitude of difference between groups or the effect of the intervention
  • Effect size index is created for the data in each study that allows comparison across studies
  • Based on means for quantitative variables, proportions or frequencies for categorical data, and correlation values for measures of association
65
Q

What is a forest plot

A
  • Shows the results of the Systematic Review
  • Outcome of each study shown by small square icon
  • Horizontal line represents the confidence interval
  • Size of square corresponds to weight of the study, based on sample size
  • Confidence interval for the total combined value of all studies in the review indicated by a diamond shape at the bottom of the plot
66
Q

What is Grey Literature

A
  • Unpublished studies or studies that are available through sources other than the customary journals
67
Q

What is Performance Bias

A
  • Refers to the differences in the provision of care to experimental and control groups in a study
68
Q

What is Publication Bias

A
  • Occurs wen researchers fail to submit the results of studies where the results are not statistically significant or editors decline to publish such studies
69
Q

How can you avoid Selection Bias

A
  • Random allocation and concealment of allocation to ensure bias is not introduced
  • Such bias will decrease internal validity of a study

Statistics (7 decks)

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