# Multilevel Model - Alternative Ways of Analyzing Hierarchical Data

Alternative Ways of Analyzing Hierarchical Data

There are several alternative ways of analyzing hierarchical data, although most of them have some problems. First, traditional statistical techniques can be used. One could disaggregate higher-order variables to the individual level, and thus conduct an analysis on this individual level (for example, assign class variables to the individual level). The problem with this approach is that it would violate the assumption of independence, and thus could bias our results. This is known as atomistic fallacy. Another way to analyze the data using traditional statistical approaches is to aggregate individual level variables to higher-order variables and then to conduct an analysis on this higher level. The problem with this approach is that it discards all within-group information (because it takes the average of the individual level variables). As much as 80-90% of the variance could be wasted, and the relationship between aggregated variables is inflated, and thus distorted. This is known as ecological fallacy, and statistically, this type of analysis results in decreased power in addition to the loss of information.

Another way to analyze hierarchical data would be through a random-coefficients model. This model assumes that each group has a different regression model - with its own intercept and slope. Because groups are sampled, the model assumes that the intercepts and slopes are also randomly sampled from a population of group intercepts and slopes. This allows for an analysis in which one can assume that slopes are fixed but intercepts are allowed to vary. However this presents a problem, as individual components are independent but group components are independent between groups, but dependent within groups. This also allows for an analysis in which the slopes are random; however, the corrrelations of the error terms (disturbances) are dependent on the values of the individual-level variables. Thus, the problem with using a random-coefficients model in order to analyze hierarchical data is that is still not possible to incorporate higher order variables.

### Famous quotes containing the words alternative, ways, analyzing, hierarchical and/or data:

If the alternative is to keep all just men in prison, or give up war and slavery, the State will not hesitate which to choose.
Henry David Thoreau (1817–1862)

The people of the United States have been fortunate in many things. One of the things in which we have been most fortunate has been that so far, due perhaps to certain basic virtues in our traditional ways of doing things, we have managed to keep the crisis of western civilization, which has devastated the rest of the world and in which we are as much involved as anybody, more or less at arm’s length.
John Dos Passos (1896–1970)

If when a businessman speaks of minority employment, or air pollution, or poverty, he speaks in the language of a certified public accountant analyzing a corporate balance sheet, who is to know that he understands the human problems behind the statistical ones? If the businessman would stop talking like a computer printout or a page from the corporate annual report, other people would stop thinking he had a cash register for a heart. It is as simple as that—but that isn’t simple.
Louis B. Lundborg (1906–1981)

Authority is the spiritual dimension of power because it depends upon faith in a system of meaning that decrees the necessity of the hierarchical order and so provides for the unity of imperative control.
Shoshana Zuboff (b. 1951)

Mental health data from the 1950’s on middle-aged women showed them to be a particularly distressed group, vulnerable to depression and feelings of uselessness. This isn’t surprising. If society tells you that your main role is to be attractive to men and you are getting crow’s feet, and to be a mother to children and yours are leaving home, no wonder you are distressed.
Grace Baruch (20th century)