Research digest: sleep

Click to increase image sizeClick to decrease image size

Glossary

Actigraphy – a type of wearable sleep test that tracks one’s movements to determine when someone is asleep and when they are awake.

Bidirectional relationship – when there is movement in both directions.

Case-control study – subjects that can be grouped by one variable are identified, and their past exposure to suspected aetiological factors is compared with that of controls or referents who cannot be grouped in this way.

Control – participants who do not receive an intervention and so can be used as a comparison in an experimental study.

Cross-sectional analysis – looks at the data at one point in time, rather than over a period of time.

Dependent variable – the variable being tested or measured.

Distal variable – a variable that has an indirect effect.

Effect size – a number that shows the strength of a relationship between two variables.

Heterogeneity – the quality of having different characteristics or values.

Independent variable(s) – the variable(s) the researcher will change or manipulate.

Linear models – a way of describing a response variable, in terms of a linear combination of predictor variables.

Linear mixed model – an extension of simple linear models that allow both fixed and random effects. They are particularly used when there is non independence in the data, such as arises from a hierarchical structure.

Logistic regression analysis – used to understand the relationship between a dependent variable and one or more independent variables, by estimating probabilities using a logistic regression equation. This type of analysis can help predict the likelihood of an event happening or a choice being made.

Longitudinal study – a type of correlational research study that involves looking at variables over an extended period of time.

Meta-analysis – the examination of data from a number of different but similar studies, in order to determine trends and test for overall statistical significance.

Mind-mindedness – a concept in developmental psychology that refers to a caregiver’s tendency to view their child as an individual with a mind.

Mixed methods – combines quantitative and qualitative data collection and analysis in one study.

Multilevel model – a statistical model that varies at more than one level.

Multivariable risk – used to calculate each study subject’s predicted risks and benefits from treatment.

Multiwave prospective study – where participants are enrolled into the study before they develop the disease or outcome in question, and the same variables are repeatedly measured to determine their changes over time.

Observational study – where the effect of a variable is observed without trying to control who or what is exposed to it.

Prospective cohort study – a longitudinal cohort study that follows over time a group of similar individuals (cohorts) who differ with respect to certain factors under study, to determine how these factors affect rates of a certain outcome.

Proximal variable – a variable that has a direct effect.

Qualitative synthesis – a systematic search for research on a topic that draws the findings from individual studies together.

Randomised controlled trial – a study in which the population receiving the intervention and the control group are both chosen at random from the eligible population.

RAND/UCLA appropriateness method – an instrument that measures the overuse and underuse of interventions.

Repeated-measures multivariate analysis – subjects are measured at two or more times on the dependent variable, and data analysed is more than one type of measurement or observation.

Standardised mean difference – the size of the intervention effect in each study relative to the variability observed in that study.

Systematic review – the application of a clear and reproduceable methodology to identify and appraise all relevant literature in a chosen area.

Variance – a statistical measurement of the spread between numbers in a data set.