matched pairs

matched pairs

[′macht ′perz]
(statistics)
The design of an experiment for paired comparison in which the assignment of subjects to treatment or control is not completely at random, but the randomization is restricted to occur separately within each pair.
References in classic literature ?
"Now by all the wedding bells that ever were rung!" quoth Robin boldly, "this is the worst matched pair that ever mine eyes beheld!"
Two-sample t-test is used when the data of two samples are statistically independent, while the paired t-test is used when data is in the form of matched pairs. There are also some technical differences between them.
ABB says as one of the only companies manufacturing both variable-speed drives (VSDs) and low voltage AC motors, it is able to offer customers perfectly designed, tested and approved matched pairs.
Both matched pairs showed a marked difference between the conventional treatment and the use of TTO dressing.
The physical and cognitive development was compared among the matched pairs to determine the effect, if any, of the cancer and its treatment.
An innovative research design (four matched pairs of case studies) was used to study changes in the quality of employment systems in American and German call centres.
I have two piles in my dresser drawer, one with matched pairs, the other with what I call "loners." We never throw them away, in hopes that their counterparts will turn up somewhere in the house.
Other researchers (and the authors) have not been able to reproduce the findings when using HA and NA matched pairs from viruses chosen on the basis of geography and time and correctly have pointed out errors in the data set that make the original conclusions invalid.
The present paper describes the recruitment and site selection process that has been underway since January 2011, with particular emphasis on the use of Mahalanobis distance score to determine matched pairs of sites prior to randomization to treatment and control groups.
Six matched pairs of IBS patients (aged 23-58 yrs) were randomly assigned to either a gut-directed hypnotherapy (6 Ss) or to a symptom monitoring wait-list control condition (6 Ss) in a multiple baseline across Ss design.
Researchers randomly assigned treatment within 74 matched pairs of communities, representing more than 118,000 households in seven Mexican states, and measured outcomes in a baseline survey and a follow-up survey 10 months later in 50 of the pairs.
The Restaurant Opportunities Center of New York spent the last two years canvassing restaurants, setting up focus groups and sending 43 matched pairs into restaurants.