EBP questions

mwhyett's version from 2017-05-21 20:05


Question Answer
What is the study population?The population from which the sample has been taken.
What is a sample?A number of units drawn from a population.
What does a sample represent?The characteristics of the population
What is randomisation?The process of randomly allocating participants to groups within a research study.
What 3 things can theories be?1. Explanations for observed facts. 2. Statements about the relationships between concepts. 3. Proposed explanations for observed phenomena.
What is a research hypothesis?A measurable and testable form of a theory.
What is operationalisation?The process of converting the general concept(s) of a theory into a specific measurable and therefore testable form.
What is a variable?A characteristic or property of a subject or object.
What is an independent variable?The variable which the researcher decides to manipulate.
What is a dependent variable?The outcome.
What is random variability or error due to?Chance.
What are confounding variables?Variables that the researcher failed to control.
What is a systematic error due to?The design of the study.
What is reliability?The extent to which the study would produce the same result if repeated under the same conditions.
What is variability?The extent to which the results of a study, or measurement, are accurate, reliable and free from bias.
What is an objective measurement?A measurement that is carried out without the influence of personal opinion.
What is a subjective measurement?A measurement that the result of opinion or personal view.
What is research?Planned, systematic method of scientific inquiry that adds to current knowledge.
What is data?Facts and statistics collected together for reference or analysis.
What is qualitative data?Data that is typically descriptive data and does not use numbers.
Give 2 examples of how to obtain qualitative data1. Open- answer questionnaires. 2. Interviews.
What is quantitative data?Data that is typically number based.
Give two examples of how to obtain quantitative data1. Experiments. 2. Observations. 3. Closed-answer questionnaires.
What would you use to study a cause-and-effect relationship?An experiment.
What would you do to find out people's opinions on something?A survey.
What would you use to explore a person's experiences?A phenomenological study.
What is a quasi-experimental design also known as?A field experiment.
What does a quasi-experiment lack?Random assignment.
What sort of design would be used if it is unethical to carry out a full experiment?A quasi-experiment.
What is a quasi-experiment?A design that is used instead of an experimental design as it would be unethical to do so.
What does a control group allow researchers to do?Eliminate confounding variables and bias.
What is a control group?A group that does not receive treatment and acts as a benchmark for other groups.
What is a double blind study?A study in which neither the researcher nor the participants know the true nature of the experiment (eg. not knowing which group receives the placebo).
What does a double blind study reduce?Bias.
What is randomisation?A method based on chance alone by which study participants are assigned to a treatment group.
What two methods can you choose to achieve external validity?1. A large sample size to reduce random error. 2. Using a sampling design to reduce systematic errors.
What determines how representative the sample is to the population?The amount of systematic and random error.
What is the definition of generalisability?The extent to which research findings can be applied to settings other than that in which they were originally tested.
What is sampling error inversely proportional to?The square root of the sample size.
What does the sample size do to the likelihood of error?The bigger the sample size the lower the random error.
What is systematic error?Error that systematically affects measurements in a particular direction.
What is systematic error due to?Poor study design.
How can you control systematic variability?By sampling correctly.
What sort of research designs commonly use small sample sizes?Qualitative designs.
What type of studies involve interpretation of spoken word?Qualitative designs.
What are the two main groups of sampling methods?Probability and non-probability methods.
What sort of sampling does probability methods use in participant selection?Random sampling.
What sort of sampling does non-probability methods use in participant selection?Non-random sampling.
Give two methods of random sampling in participant selection1. A random number table. 2. Numbers out of a hat.
Give two methods of non-random sampling in participant selection1. Volunteering. 2. Surveying the first to arrive in a group.
Is probability sampling biased or unbiased?Unbiased.
Can any method of sampling generate completely representative results?No.
Which type of sampling can produce a representative sample of the population?Probability sampling.
Which type of sampling requires a larger sample size in order to be representative?Non-probability sampling.
In which type of sampling can statistical tests be applied in order to assess the likelihood of random error?Probability sampling.
Can statistical tests be used in probability sampling or non-probability sampling?Both, but it can be argued that it is not possible in non-probability sampling.
In which type of sampling does each member of the study population have an equal chance of being selected?Random sampling.
Name three types of random sampling1. Simple. 2. Systematic. 3. Stratified.
In which type of sampling does each member of the study population have an unequal chance of being selected?Non-random sampling.
Give 5 types of non-random sampling1. Convenience. 2. Cluster. 3. Quota. 4. Judgemental. 5. Volunteer.
What is the preferred sampling method to ensure a representative sample is free from bias?Random sampling.
What is not a method of sampling?Randomisation.
What is randomisation?The allocation of volunteers into groups.
What is the objective of randomisation?To even out any systematic differences between groups.
At what point is randomisation used?After sampling.
What does RCT stand for?Randomised controlled trials.
Why is a small sample in an RCT unethical?An effect which may exist may not be demonstrated statistically.
Why is a large sample in an RCT unethical?Because more people than necessary will be exposed to the intervention/treatment.
What are the three main categories of experiments?1. Measurement. 2. Exploratory. 3. Hypothesis testing.
Why is hypothesis testing the method of choice?As is investigates a cause-effect relationship and can be controlled.
What type of experiments do not start with a prediction?Exploratory.
What are the three areas of classification for hypothesis testing experiments?1. Matched pairs. 2. Related design. 3. Unrelated design.
What are the ideal participants for a matched pairs design?Identical twins.
Why is a matched pairs design difficult to carry out?As matching participants on all factors is difficult. (e.g. Sex, age, disease progression).
What is a related design experiment?A sample design where the same participants are used for all parts of the experiment.
What is eliminated in a related design experiment?Selection bias.
What are the participiants at risk of in a related design experiment?Fatigue.
What is a crossover?A study in which the design of the experiment is done in a different order for both sets of participants.
Why is a crossover element useful?It can eliminate fatigue by amalgamation of both sets of results.
What is an unrelated design?A design that compares two or more groups with participants randomly allocated to the arms of the experiment.
What are the 5 features of a randomised controlled trial?1. Randomisation. 2. Control for other variables. 3. A Control group. 4. An experimental group. 5. Double blinding.
What do the features of a randomised controlled trial maximise?Objectivity and validity.
What do the features of a randomised controlled trial minimise?Bias.
Why is a Quasi-experimental design different to an experimental design?Not all of the features of the true experiment are included in the design as it would be unethical.
What is bracketing?The researcher ‘brackets’ their position with regard to the research environment. For example they might want to state their gender if they feel that it might have some bearing on the way they have approached their research study.
What is reflexivity?A process where the researcher acknowledges the influence they have had on the study and the effect which it has had on them.
What is triangulation?Simply the use of multiple methods to study the same complex phenomenon.
Why is triangulation used?To increase validity and reliability if they reach the same conclusions, due to multiple investigations into the same problem.
What is transferability?The ability to generalise findings back to the original population.
What is usually the goal of quantitative research?Transferability.
Why is transferability not an aim in qualitative research?Because the results would not be appropriate due to the small sample sizes and the types of sampling methods used.
Is qualitative research more cyclical or linear?Cyclical.
What is a phenomenological study interested in?The experience of a participant/patient.
What are two examples of the resulting format of a phenomonological study?1. Extended essays. 2. Whole books.
What is symbolic interactionism?A view of social behaviour that emphasizes linguistic or gestural communication and its subjective understanding.
What does symbolic interactionism emphasise?That a social system has meaning only in the way people define and interpret what is happening.
What is ethnography?A type of qualitative research often undertaken by anthropologists.
What are the three types of analysis?1. Content. 2. Thematic. 3. Theoretical.
What is content analysis?A method in which the number of times that a word or concept occurs is counted.
What is thematic analysis?A method in which the number of times a word is used, but only counted when there is meaning behind it.
What is theoretical analysis?An approach where the researcher develops theories from the data which may be tested against existing theories.
What sort of data do surveys normally collect?A mixture of both quantitative and qualitative data.
What should be done to all surveys and questionnaires before they are used?They should be piloted.
What do structured questionnaires or interviews consist of?Precise unambiguous questions, often referred to as closed questions.
What do unstructured questionnaires or interviews consist of?Open ended questions, which can probe in more depth and explanation, often referred to as open questions.
What are 3 advantages of open questions?1. Allows for shades of meaning. 2. Better when responses cover a wide range of topics. 3. Allows for in depth probing (interviews).
What is the mode?The number that occurs the most.
What is the median?The middle value.
What is the mean?The addition of all the values and the division of the total by how many numbers there were.
What is the central tendency?The "middle" value or a typical value of the data.
What are 4 measures of dispersion in numerical data?1. Range. 2. Variance. 3. Standard deviation. 4. Interquartile range.
What is the range?The difference between the highest and lowest values in a distribution.
What is the variance?The sum of the squared deviations about the mean divided by the number of values.
What is the standard deviation?The square root of the variance.
What is the interquartile range?The distance between the values which represent the 25th and 75th percentage points in a distribution.
What does a normal bell curve represent?A normal distribution.
What is a deviation?A measurement of the distance from a central value.
What do the deviations add up to in a normal distribution?Zero, because the positive and negative deviations will equal out.
What is always used with the standard deviation?The mean.
What is always used with the interquartile range?The median.
What two pieces of information does a correlation coefficient show?1. The strength of the relationship. 2. The direction of the relationship.
What is the definition of odds?The ratio of the probability of an event occurring and the probability of an event not occurring.
What is an odds ratio?The ratio of two odds.
What type of data do bar charts present?Discrete data.
What types of data do tables present?Most types, not just numerical.
What types of data do pie charts present?Proportional data.
What types of data do histograms show?Continuous data.
What type of data do frequency polygons show?More than one type of continuous data for comparison.
What two main ways can inferential analysis of data be obtained?1. Hypothesis testing. 2. Calculating a confidence interval.
What is a null hypothesis?A hypothesis which the researcher tries to disprove, reject or nullify.
Which hypothesis is tested against?The null hypothesis.
In what case is the alternative hypothesis accepted?If there is insufficient evidence in which to accept the null hypothesis.
When does a type one error occur?When the null hypothesis is rejected and it should have retained.
When does a type two error occur?When the null hypothesis is retained and it should have been rejected.
What are confidence intervals?A range of values, reflecting the imprecision between the sample statistic and the population parameter.
What happens to the confidence interval when the probability increases?It increases also.
What is ethnographic research?The study of people in their own environment using patient observation and interviews.

Recent badges