Matching, Advanced Statistics

Matching is the method of making a study group and a comparison group comparable with respect to the extraneous factors. Generally used in the retrospective studies when selecting cases and controls to control variation in a response variable due to sources other than those which are taken immediately under investigation. Numerous kinds of matching can be recognized, the most common of which is when each case is individually matched with the control subject on the matching variables, for instance sex, age, occupation, etc. When the variable on which the matching takes place is continuous it is generally transformed into a series of categories (such as age), but the second process is to say that two values of the variable match if their difference lies between the defined limits.

This technique is known as caliper matching. Also significant is group matching in which distributions of the extraneous factors are made similar in the groups to be compared.

Posted Date: 7/30/2012 3:12:14 AM | Location : United States







Related Discussions:- Matching, Assignment Help, Ask Question on Matching, Get Answer, Expert's Help, Matching Discussions

Write discussion on Matching
Your posts are moderated
Related Questions
The graphical method for studying the behavior of the seasonal time series. In such a plot, the January values of seasonal component are graphed for the upcoming years, then the

A test for equality of the variances of the two populations having normal distributions, based on the ratio of the variances of the sample of observations taken from each. Most fre

Mann Whitney test is a distribution free test which is used as an alternative to the Student's t-test for assessing that whether the two populations have the same median. The test

Paul Jordan has just been hired as a management analyst at Digital Cell Phone Inc. Digital Cell manufactures a broad line of phones for the consumer market. Paul's boss, John Smith

MAZ experiments : The Mixture-amount experiments which include control tests for which the entire amount of the mixture is set to zero. Examples comprise drugs (some patients do no

Prevalence : The measure of the number of people in a population who have a certain disease at a given point in time. It c an be measured by two methods, as point prevalence and p

Normality - Reasons for Screening Data Prior to analyzing multivariate normality, one should consider univariate normality Histogram, Normal Q-Qplot (values on x axis

1) Question on the first day questionnaire asked students to rate their response to the question Are you deeply moved by the arts or music? Assume the population that is sampled

Confidence profile method : A Bayesian approach to meta-analysis in which the information in each piece of the evidence is captured in the likelihood function which is then used al

Categorizing continuous variables : A practice which involves the conversion of the continuous variables into the series of the categories, which is common in the field of medical