Ecological fallacy, Advanced Statistics

The term used when the aggregated data (for instance, aggregated over different areas) are analysed and the results supposed to apply to the relationships at the individual level. In most of the cases analyses based on aggregated level means give conclusions very different
from those which would be obtained from the analysis of unit level data. An instance from the literature is the correlation coefficient of 0.11 between illiteracy and being born in foreign calculated from person level data, compared by the value of -0.53 between percentage illiterate and percentage foreign born at the State level.

Posted Date: 7/27/2012 6:43:42 AM | Location : United States

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

Write discussion on Ecological fallacy
Your posts are moderated
Related Questions
Demographic data: Age: continuous variable Gender: categorical variable with males coded 1, females coded 2. Relationship status: categorical variable 1 to 5. Rational

how to constuct design matrix

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

Isobologram  is a diagram used to characterize the interactions among jointly administered drugs or the chemicals. The contour of the constant response (that is the isobole), which

Median absolute deviation (MAD) : It is the very robust estimator of the scale given by the following equation   or, in other words we can say that, the median of the absolute

A value related with the square matrix which represents sums and products of its elements. For instance, if the matrix is   then the determinant of A (conventionally written as

An analyst counted 17 A/B runs and 26 time series observations. Do these results suggest that the data are nonrandom? Explain

Ordination is the procedure of reducing the dimensionality (that is the number of variables) of multivariate data by deriving the small number of new variables which contain much

I need help solving a problem using excel.

Gllamm is a program which estimates the generalized linear latent and mixed models by the maximum likelihood. The models which can be fitted include structural equation models mul