Lesson 3 Flashcards
What is a survey?
- An investigation in which information is systematically collected but in which the experimental method is not used.
- May be conducted by face-to-face inquiry, self-completed questionnaires, telephone, postal service, or in some other way.
- The generalizability of results depends upon the extent to which the surveyed population (sample) is representative.
What is the purpose of surveys?
- Assess prevalence of disease - cross-sectional survey e.g. what is the prevalence of diabetes in Milton Keynes?
- Measure risk and protective factors of the respondent
- Measure outcomes
- Ad-hoc data – locally commissioned surveys provide an opportunity to collect information of interest not routinely collected
What are advantages of prevalence studies?
Cheap and quick
Useful for healthcare planning and investigating trends over time
Useful when routine data not available
What are disadvantages of prevalence studies?
Not usually useful for conditions with a short duration
Not really useful for investigating causality
Sampling and data collection need care
Define ‘population’
the group of people in whom we are interested in and wish to apply the results of the survey to
Define ‘sample’
group of individuals taken from larger population
Define ‘sampling frame’
list of everyone in the population from whom sample taken
Define ‘random (probability) sampling’
- everyone in the sampling frame has an equal probability of being chosen
- important to achieve a representative sample
Define ‘non-random (non-probability) sampling’
• easier and convenient
• Unlikely to be representative
– Beware self-selecting samples!
Explain simple random sampling
Each population member given an identifier and numbers selected at random
Explain stratified sampling
Divide population into strata (subgroups) and select sample from each using simple random sampling
Explain cluster sampling
Use natural ‘clusters’ in the population e.g. schools. Simple random sample of ‘clusters’ (e.g. schools). Study all individuals within clusters
Explain systemic sampling
Every Nth population member selected
Define validity
how well a test measures what it is purported to measure
the capacity of a test to give a true result
Define repeatability/reliability
the degree to which a measurement made on one occasion agrees with the same measurement on a subsequent occasion
Define random error
arandomimprecisionorvariable performance that is due to chance alone
Define bias
a systematic error in sampling or measurement
Define selection bias
error due to systematic differences in the characteristics of the groups being studied due to differences in the way they were selected
What are two types of selection bias?
Sampling bias - non-representative sampling
Non-response bias - respondents differ from non-responders
Define information (measurement) bias
error due to systematic differences in the measurement or classification of individuals in the groups being studied
What are two types of information bias?
Instrument Bias: systematic error due to inadequate design, calibration or maintenance of instruments
Inter-Observer Bias: systematic error between measurements of different interviewers e.g. due to training
Define ‘precision’
• if lots of variation (random error), precision is poor, if little random
variation, measurement is precise
• E.g. variation occurs in measuring blood pressure
Define ‘accuracy’
• How close the average result is to the true value, poor accuracy is systematic error (bias) • E.g. sphygmomanometer not calibrated and reading 10mmHg too high
What is ‘response rate’?
% of selected sample that take part in survey/study