OMbook_glossary

I

Item cueing

This is about whether an item in a multi-item self-report questionnaire is cued negatively, e.g....

Internal reliability / consistency

There's a sometimes heated debate about whether the term "consistency" is or isn't more appropriate...

Item response theory (IRT)

Oversimplifying only a little, IRT, with Classical Test Theory (CTT), makes the two main, and...

Intervals: terminology and symbols

This is a little bit esoteric and mathematical perhaps but I keep forgetting the symbols Details An...

Interval censored data

Censored data (see entry) is data where at least some values are not know accurately...

Imputation

No, not when someone imputes malevolent intention to your attempt to help! In research...

Intercept

The intercept, with the slope, define a linear regression. Details It's just this point (in the plot...

Interview measures

What it says: an interview that produces a measure score, or, reifying things a bit,...

Intention to treat (ITT) analyses

You may come across this in reports of controlled trials of therapies (or of anything...

IPD: Individual Participant/Patient Data

You may hit this term in systematic review and meta-analyses. It's the latest, and...

Idiographic vs. nomothetic: history

There are separate entries (see "try also") for idiographicm, sometimes spelled "ideographic", and nomothetic measures,...

Investigator bias/allegiance

Researcher bias/allegiance are synonyms. Basically the simple idea that investigators/researchers tend to hold views that constitute...

Independence of observations

This is an absolutely fundamental aspect of all statistical methods: the idea that all the...

Inferential testing, "tests"

This approach to evaluating findings starts out with an idea that it is worth investigating...

Inter-rater agreement/reliability

One way to assess how good, how usable, a rating system is is to get...

Invalidity

Contamination of scores by systematic error, see large entry for validity and entries for its...

Internal vs. external analyses

Most thinking about change/outcome data is of "internal" analyses: analyses within one local dataset and...

Interval scaling

his is about Stevens' typology of scales and most of the time it's a red...

Inter-quartile range (IQR)

[see quartiles!] The “interquartile range” is the distance between the 25th centile (the score such that...

Interaction

In statistics, Interaction describes the situation in which two Predictor Variables combine to have a...

Independent variable

Term sometimes used for Predictor variable when looking at the relationship with a Dependent variable....

Informed consent

When we seek consent from our clients for participating in a treatment or in a...

Idiographic measure, Idiographic methods

An idiographic measure gives a picture (“graphic”) unique to the individual (“idio”). For example, a...