Week 5: Chapters 9 and 18
personal interview, telephone interview, self-administered questionnaire
modes of collecting survey data
clinical trials, evaluation research, nursing intervention research
studies that involve an intervention
history threat
other events co-occurring with causal factor that could also affect outcomes
selection bias, expectancy effect, enhanced internal validity
threats to external validity
low statistical power, weakly defined cause, unreliable implementation of a treatment
threats to statistical conclusion validity
cause must precede the effect, must be a demonstrated empirical relationship between the cause and effect, relationship cannot be explained by a third variable
three criteria for making causal inferences
nonequivalent control group, within-subjects
two main categories of quasi-experimental designs
case-control design
"cases" (e.g., those with lung cancer) are compared to "controls" (e.g., those without lung cancer) on prior potential causes (e.g., smoking habits).
experimental
INTERVENTION + RANDOMIZATION+ CONTROL
quasi-experimental
INTERVENTION BUT MISSING RANDOMIZATION OR CONTROL
nonexperimental
If there is no intervention, the study is ___________.
quasi-experiments
Involve an intervention but lack either randomization or control group
control
The researcher introduces controls, including the use of a control group.
selection threat
This is the single biggest threat to studies that do not use an experimental design
nonequivalent control group designs
Those getting the intervention are compared with a nonrandomized comparison group.
time series designs
gather pre-intervention and post-intervention data over longer period
phase 1
phase in a clinical trial that finalizes the intervention (includes efforts to determine dose, assess safety, strengthen the intervention)
phase 4
phase in a clinical trial that focuses on long-term consequences of the intervention and on generalizability; sometimes called an effectiveness study
phase 3
phase in a clinical trial that fully tests the efficacy of the treatment via a randomized clinical trial (RCT), often in multiple sites; sometimes called an efficacy study
phase 2
phase in a clinical trial that seeks preliminary evidence of effectiveness—a pilot test; may use a quasi-experimental design
maturation threat
processes that result simply from the passage of time
make the groups equal with regard to all other factors except receipt of the intervention
purpose of randomization
random assignment
putting subjects in random groups once you have them in your study
random sampling
random subjects pulled from population
outcome research, surveys, secondary analysis, methodologic research
studies that do not involve an intervention
single blind
subjects don't know which group they are in (e.g., placebo or sham used)
descriptive correlational research
the purpose is to describe whether variables are related, without ascribing a cause-and-effect connection.
selection bias
the sample selected for the study does not accurately represent target population.
temporal ambiguity
unclear whether presumed cause occurred before outcome
statistical conclusion validity
the ability to detect true relationships statistically
internal validity
the extent to which it can be inferred that the independent variable caused or influenced the dependent variable
external validity
the generalizability of the observed relationships to the target population
cross-sectional data
Data are collected at a single point in time
outcome analysis
Seeks preliminary evidence about program success
intervention fidelity
whether the treatment as planned was actually delivered and received.
correlational design
Cause-probing questions (e.g., prognosis or harm/etiology questions) for which manipulation is not possible are typically addressed with a:
longitudinal design
Data are collected two or more times over an extended period.
outcomes research
Designed to document the quality and effectiveness of health care and nursing services
between-subjects design
Different people are compared
evaluation research
Examines how well a specific program, practice, procedure, or policy is working
factorial design
More than one independent variable is experimentally manipulated
experimental condition
Must be designed with sufficient intensity and duration that effects might reasonably be expected
nonexperimental
NO INTERVENTION; observational or descriptive May have random SAMPLING—NOT same as random ASSIGNMENT!
survey research
Obtains information (via self-reports) on the prevalence, distribution, and interrelations of variables in a population
outcomes research
Often focuses on parts of a health care quality model developed by Donabedian
within-subjects designs
One group is studied before and after the intervention.
pretest-posttest design
Outcome data collected both at baseline and after the intervention
posttest only design
Outcome data collected only after the intervention
A
Researchers tested whether Healing Touch sessions would reduce anxiety among patients with cancer. Which of the following is an example of a threat to the study's internal validity? A. Study participants had low baseline anxiety levels. B. The study sample was too homogeneous. C. The study was conducted in the country of Turkey. D. There is no proof that Healing Touch reduces anxiety
B
Researchers wonder whether providing healthier food choices in a middle school cafeteria and vending machines would reduce total caloric intake and percent of sugar and salt students consume. They compare students' baseline daily calorie, salt and sugar intake before and after introducing healthier food and beverage choices. Why is this considered a quasi-experimental rather than an experimental study? A. There is no intervention. B. There is no random assignment. C. It is prospective. D. It's only done in one school.
within-subjects design
Same people compared at different times or under different conditions
survey research
Secures information about people's actions, intentions, knowledge, characteristics, opinions, and attitudes
clinical trials
Studies that develop clinical interventions and test their efficacy and effectiveness
methodologic research
Studies that focus on the ways of obtaining, organizing, and analyzing data
secondary analysis
Study that uses previously gathered data to address new questions
crossover design
Subjects are exposed to 2+ conditions in random order; subjects "serve as their own control"
biologic plausibility
The causal relationship should be consistent with evidence from basic physiologic studies.
coherence
The evidence about the existence of a relationship should come from multiple sources
randomization/random assignment
The researcher assigns subjects to groups at random.
manipulation
The researcher does something to some subjects—introduces an intervention (or treatment).
B
Which of the following is an example of a mortality threat to the internal validity of a study? A. Survey sent to 1500 nurses with 1200 completing the questionnaire. B. 100 subjects enrolled to test effects of text messaging to improve diet with 70 completing. C. Study comparing length of stay in the ICU preceding discharge to hospice versus no-hospice for patients with advanced cancer. D. 30 subjects complete a smoking cessation study.
B
Which of the following is most likely to be an example of a "true experiment"? A. "The effects of sunlight exposure on Vitamin D levels in preschool children: A retrospective study." B. "The impact of melatonin on sleep regulation in blind adults: A randomized, placebo-controlled study." C. "National survey of children's second-hand smoke exposure in households of smoking adults." D. "Comparison of hospitals with Magnet status versus those without on nursing turnover."
A
Which of the following provides the best example of meeting criteria to determine causality? A. Intestinal distress occurs after subjects diagnosed with Celiac disease ingest gluten. B. Intuition that computer screen time impairs vision. C. Prospective study showing high correlation between stress and anxiety. D. Increased sodium intake predicted to lower blood pressure.
B
Which of the following research methods is most appropriate to answer the research question: "What is the daily protein intake of homeless inner-city adults?" A. Phase I study B. Face-to-face survey C. Phase IV study D. Telephone survey
A
Which of the following studies is most likely to provide evidence of a cause and effect relationship? A. Double-blind, randomized controlled trial of peppermint oil for improving IBS symptoms. B. Retrospective chart review examining predictors of depression in nursing home residents. C. Living with chronic fatigue syndrome: A Grounded Theory study. D. Survey of patients' understanding of routine hospital discharge instructions.
A
Which phase of development is the following clinical trial most likely to be? "Pharmacokinetic study to determine dose levels of the anti-diabetic agent AGN29." A. Phase I B. Phase II C. Phase III D. Phase IV
prospective correlational design
a potential cause in the present (e.g., experiencing vs. not experiencing a miscarriage) is linked to a hypothesized later outcome (e.g., depression 6 months later).
correlation
an association between variables and can be detected through statistical analysis.
retrospective correlational design
an outcome in the present (e.g., depression) is linked to a hypothesized cause occurring in the past (e.g., having had a miscarriage).
longitudinal data
are better at showing patterns of change and at clarifying whether a cause occurred before an effect
randomized control trial
best type of study to prove causality
selection threat
biases arising from pre-existing differences between groups being compared
prospective designs
called a cohort study by medical researchers
mortality threat
differential loss of participants from different groups (by dropping out for any reason)
structure of care, processes, outcomes
key concepts of outcomes research
retrospective
looking backward
prospective
looking forward
expectancy effect
makes effects observed in a study unlikely to be replicated in real life.
randomization, subjects as own controls, homogeneity, matching, statistical control
methods on controlling intrinsic factors
double blind
neither researchers nor subjects know what group subjects are assigned to
experimental designs
offer the strongest evidence of whether a cause (an intervention) results in an effect (a desired outcome).