EBP stuff

simple random sampling

every individual has an equal chance of being selected, like drawing names from a hat

quota sampling

the researcher identifies subgroups and selects participants until a quota for each subgroup is reached but not randomly. standing in a mall and recruiting until you have 10 teens and 10 adults

cluster/multi stage sampling

randomly selecting groups instead of individuals, then including everyone in the selected groups or selecting individuals within those groups. randomly selecting 10 schools then surveying all students in the schools

convenience sampling

selecting participants who are easy to reach or readily available

snowball sampling

used when the population is hard to locate, participants refer or recruit other participants

systematic sampling

selecting every x-y persons from a population list, from a list of 1,000 patients, selecting every 10th name

stratified random sampling

population is divided into subgroups(strata) based on characteristics, then random sampling occurs within each subgroup. equal numbers of male and female participants by randomly sampling from each group

consecutive sampling

every available subject who meets criteria is selected until the sample size is reached, includes every patient admitted to the ICU over 3 months who meets the inclusion criteria

experimental design (level IIIA)

a true experimental study, random assignment, control group, manipulation of an independent variable

correlation (level IV)

a correlation study examines the relationship between two or more variables with no intervention, manipulation or cause and effect conclusions

quasi-experimental design (level IIIB)

a study that includes an intervention but does not have random assignment, NON-EQUIVALENT. one unit gets new fall prevention and the other doesn’t but staff aren’t randomly assigned

qualitative (level V)

qualitative research explores experiences, perceptions and meanings using methods like interviews, focus groups and observations. it does not use numbers or statistics

probability sampling (simple random, stratified random, cluster, systematic)

every member of the population has a equal chance of being selected, uses random selection, reduces bias and results can often be generalized to the larger population

non-probability sampling (convenience, quota, snowball, consecutive,)

not everyone in the population has an equal chance of being selected, no random selection, more risk of bias

non experimental design

a research design in which the researcher does not manipulate variables or assign participants to groups, the researcher observes, measures and describes relationship or phenomena that naturally occur

longitudinal study

a study in which researchers observe the same participants repeatedly over a period of time to track change or developments in variables

repeated measures study

a study in which the same participants are measured on the same variables multiple times under different conditions or at different points in time

cross sectional study

a study that examines a population or a sample at a single point in time to assess prevalence, characteristics or relationships among variables, snapshot in time

operational definition

explains how the concept will be measured or observed in the study, it is specific and practical allowing other researchers to replicate the study

conceptual definition

explains what a concept means in theory, it is broad, abstract definition based on theory

meta synthesis

a qualitative research method that combines results from multiple qualitative studies to develop new interpretations or deeper understanding

research utilization

the process of applying research findings to clinical practice, involves taking results from on study and using them to improve patient care or procedures

paradigm

a set of beliefs, values and assumptions that guide how researchers view the world and conduct research

evidence based practice

a broader, systematic approach to clinical decision making that integrates best available research evidence, clinical expertise and patient preferences and values

quantitative

larger samples are required to ascertain statistical significance, large samples allow researchers to include more variables

qualitative

samples are usually small(10-30 participants) and include intensive interactions with each participant

effect size

strength of the relationship between the independent variable and the dependent variable

number of variable and subgroups

if comparing subgroups you need more subjects, minimum 30 people for each group. at least 30 subjects per variable