NURS 316 - Research Flashcards
Theory
Abstract generalization of a phenomenon and how is interrelates
Descriptive theory
Accounts for & describes the phenomenon
Conceptual model
deal with abstractions that are assembled because of their relevance to a common theme
Conceptual models are:
Loosely structured
interrelated to a phenomenon
reflects assumptions and philosophical views of the model designer
Two types of research models:
Statistical and Schematic
Schematic models visually represent…
relationships among phenomenon
used in quantitative and qualitative research
Pender’s Health promotion model
Model explaining and predicting the health-promotion component of lifestyle
A scientific theory is used to explain what?
Principle or body of principles to explain a phenomenon
Theories are collections of hypothesis
True
Grand theory
broad scope, most abstract
mid-range theory
narrower in scope
bridges grand theory and practice
Practice theories
Most narrow scope and least abstract
Framework
Conceptual underpinning of a study
Every study has…
a framewrok
Theoretical framework is
based on a theory
A studies framework is often _____ .
implicit
Framework is part of the research tradition in what type of study?
Qualitative
Grounded theory researchers often incorporate what in their studies?
Sociological principles
Four concepts central to nursing research models
1 - human beings
2 - environment
3 - health
4 - nursing
Jean Watson’s Caring Science Theory:
- Interpersonal
- Carative factors
- Promotes health and family growth
- Accept a person as what he/she may become
development of potential…best action…at a given point of time - Caring is healthogenic
- Central to nursing
Roy’s adaptation model
Humans viewed as biopsychosocial adaptive systems who cope with environmental change through the process of adaptation
Nursing interventions take form as _____ (what factors for adaptation)?
- increasing
- decreasing
- modifying
- removing
- maintaining internal and external stimuli that affect adaptation
Nola Pender’s Health Promotion Model (HPM) focuses on ______
Explaining health=promoting behaviors, using wellness orientation
Michel’s Uncertainty in illness theory
Focuses on the concept of uncertainty
Counterfactual
what happens to same people simultaneously exposed and not exposed to the causal factor
Crossover design
exposed to more than one experimental condition in random order and serve as their own controls
Quasiexperiment
Trials without randomization
Lacks comparison group
Time-series design
outcome data collected over a period of time as well as before and after
Quantitative researchers strive to ____ external factors that could affect the outcome
control
Becker’s Health Belief Model
framework: people’s health related behavior
Transtheoretical Model reflects
5 stages of change
Within-subjects
Same people at different times or under different conditions
Students being looked at twice; once for one condition and the second for a different condition
Between -subject designs
Different people are compared;
Group A takes actual study drug; group B take placebo
Control group conditions
No intervention
Alternative intervention used
Placebo
Standard methods of care (usual care)
Different dose or different intensity of treatment
Prospective correlational design reflects that a potential cause is
linked to a hypothesized later outcome
Descriptive research
describe whether variables are related without ascribing a cause and effect connection
Asking people and relying on their word
Cross-sectional design
Data collected at a single point in time
Not following the subject; looking at the present and not the future for that one person
longitudinal design
trend studies: same population
Panel studies: same type of people
Follow-up studies: same subject now and the future
constancy of condition
Steps taken to minimize situational contaminants to achieve this
internal validity
extent to which it can be inferred that the IV caused or influenced the DV
External validity
generalizability of the observed relationships to the target population
Construct validity
degree to which key constructs are adequately captured in the study
Statistical conclusion validity
ability to detect true relationships statistically
Temporal ambiguity
unclear whether presumed cause occurred before outcome
Which on came first?
Selections threat
bias arising from pre-existing differences between groups being compared
The groups are not the same
BIGGEST THREAT TO NON-EXPERIMENTAL STUDIES
History threat
other events co-occurring with causal factor that could also affect outcomes
Maturation threat
processes that result simply from the passage of time
Ex. does neosporin truly heal a cut faster?
Mortality threat
differential loss of participants from different groups
Drop outs and not necessarily death
Expectancy effect
Hawthorne Effect
Hawthorne effect
if people are aware the study is being conducting they might change their behavior
Low statistical power
To small of a sample
Weakly defined “cause”
IV not powerful enough
Full Clinical Trial Phases - Phase I
Finalizes intervention (includes efforts to determine dose, assess safety, strengthen the intervention)
Full Clinical Trial Phases - Phase II
Seeks preliminary evidence of effectiveness
A pilot test, may use a quasi-experimental design
Full Clinical Trial Phases - Phase III
Fully tests the efficacy of the treatment via RCT; multiple sites
Sometimes referred to as “efficacy study”
Full Clinical Trial Phases - Phase IV
Focuses on the long term consequences of the intervention and on generalizability; sometimes called the effectiveness study
Evaluation research
Examines how ell the practice, policy is working
Outcome Analysis
Seeks preliminary evidence about program success
Outcomes research
Structure
Process
Outcomes
Survey research
Obtains information on the prevalence, distribution and intervals of population variabnce
Modes of collecting survey information
- Personal (face-to-face) interviews
- Telephone interviews
- Self-administered questionarres
Secondary analysis
Cochrane Reviews
May not be aware of problems that occurred during the initial data collection
methodologic research
Involves investigating the methods for conducting rigorous research
List some advantages of mixed methods research:
- complimentarity of the qualitative and quantitative data
- practicality of using methods that best address a question
Mixed methods research are designed as either _____ or _____
sequential, concurrent
Survey research examines what?
People’s characteristics, behaviors, intention, opinions
Convergent parallel design
- to obtain complementary but different data
- AKA triangulation design
Population
Is the “P” in PICO
Is the entire group of interest
Accessible population
Portion of the portion of the target population that is accessible to the researcher
People within a specific and accessible place (e.g. at a nursing home meeting the criteria)
Sample is the ____
subset of a population
Strata
mutually exclusive segments of a population based on a specific characteristic
Representative sample
More easily achieved with:
Probability sampling
Probability sample
eliminated biases and closest to the target population
MUST have “RANDOM” in it
sampling bias
over / under representation of segments of the population on key variables
Sampling error
Difference between value and the population
non-probability sampling
Does not involve elements of randomization
Convenience sampling
selecting the most conveniently available people as participants
Ex. front row because they were closer
May include too many of one type of demographic than another type (e.g. 100 women; 5 men)
Snowball sampling (network)
people already in the sample
Used to identify people with specific characteristics
Referral to enter study from someone other than the researcher
quota sampling
Figuring how many people are needed for a sample
purposive sampling (AKA… judgmental sampling)
Researchers hand-pick sample based on knowledge of participants
A word of mouth sampling is also known as
Snowball sampling
4 types of probability sampling
Simple random
Stratified random
Cluster (multistage) sampling
Systematic random sampling
systematic random
every th number: 5th…10th…15th…
Simple random sample
have a population and picking a random number
sample in a hat and drawn at random
Stratified random sample
put in groups then randomly select group
Cluster random group
larger group to small group
Small group to smaller group
Smaller group to tiny group…etc
Sample size
adequacy is a key determinant of sample quality in the quantitative research
Involve power analysis
data collection plan
new data
collected specifically for research
existing data
open-ended data
qualitative data
objective data
quantitative data
Dichotomous questions
yes / no
multiple choice questions
a, b, c, d,
cafeteria questions
pick all that apply
rank-order questions
top 3 reasons
forced-choice questions
Ex. how many hours would you be willing to work over time?
rating questions
1 - 5, 1 = never; 5 = always
Psychosocial scales
Likert
Semantic scales
Likert scale
Several declartive statements
responses are agree/disagree
summed to compute a total score
Research scales
to make fine quantitative discriminations among people with different attitudes, perceptions, traits
In vivo measurement
performed directly on or within the body
In vitro measurement
performed outside of the body = lab work
measurement
assigned numbers to represetn the amount of an attribute
Nominal
Assigning number to classify a catagory
Ordinal
Fairly low level
Provides some ranking
Interval
objects ordered on a scale that has equal distances between points on a scale
ratio
there is a rationale
meaningful zero
equal distance between score units
what is the measurement level?
Anxiety as measured by summed score of 10-item likert response questionairre
Sum scale
what is the measurement level?
heart rate
Interval
what is the measurement level?
depression as a score of 16 on CES-D questionairre
interval ratio
what is the measurement level?
Gender
nominal
what is the measurement level?
Age in years
interval ratio
what is the measurement level?
Age as young adult, middle adult, and elderly
ordinal
weight in pounds
interval ratio
obtained score
actual sdata value for a participant
true score
score that would be obtained w/infallible measure
Error
measurement caused by factors that distort measurement
An experimental and quasi-experimental study always has a what?
An IV and a DV
Descriptive statistics
used to describe and synthesize data
Inferential statistics
used to make inferences about the population based on sample data
Parameter
descriptor for a population
Statistic
descriptor for a sample
Frequency distributions can be described in terms of:
Shape
central tendencies
variability
Positively skewed data long tail points which direction?
to the right
Negatively skewed long tail points which direction?
Left
Mode
Most frequently occurring score in distribution
Median
The middle number of the distribution:
2, 3, 3, 3, 4, / 5, 6, 7, 8, 9, = 4.5
Mean
equals the sum of the scores divided by the total number of scores
inferential statistics are based on what
laws of probability
Mean, Median, Range & SD are what?
Descriptive statistics
Estimating parameters, testing statistical hypothesis are what type of statistic?
Inferential Statistics
sample mean = 48.5 years, SD 7.5
Descriptive statistics
mean age of experimental grp = 48.5, SD = 10.2, control = 51.2 yrs, SD = 5.7, df = 119, p = .315, a = .05
Inferential statistics
df
degrees of freedom
parametric statistics
stronger more powerful; focus on bell curve; interval/ratio data; normal distribution
non-parametric statistics
nominal /ordinal data; not normally distributed
a =
significance criterion; .o5 is usually the standard
Accepting the null hypothesis means
rejecting the research
Research hypothesis acceptance equals…
rejecting the null hypothesis
null hypothesis refers to
general statement or default position that there is no relationship between two measured phenomena, or no difference among the groups
P value gets compared to what
alpha level
Hypothesis is tested on the
null hypothesis
Chi-Square
tests the difference in proportions in categories within a contingency table
Describe Chi-squared
Non-parametric; measured at nominal and ordinal
H-O is the
Null hypothesis
H-A is the
research hypothesis
Chi squared is what type of statistic?
test statistic
p
Statistically significant and lower than the alpha level
Statistically significant means that the ______ was rejected and the ____ was accepted
null hypothesis, research hypothesis
Pearson’s r, T-test, and ANOVA are what
Bivariate statistical tests
Parametric statistics
Rule of 68%, 95%, and 99% is
Normal distribution
Pearson’s r
correlation coefficient by itself; inferential statistic; measured on interval levels
t-Test design works on what types of tests?
Experimental or comparative; quasi or experimental
Variable must be dependent in what type of test?
t=Test
ANOVA
Analysis of the variance
Which bivariate test is used to test the mean between more than two groups?
ANOVA (analysis of variance)
ANOVA dependent variable must be…
interval/ratio data
Which descriptive statistic is the arithmetic average in a distribution of scores?
Mean
the value that occurs most frequently in a distribution
Mode
an index of variability
Range
the point in a distribution above which and below which 50% of the cases fall.
Median
In a sampling distribution of the mean, the standard error of the mean gets smaller (estimates of the mean get more accurate) as
The sample size gets larger
