# mental.doc.txt
#
#
#

The following data set represents a cross-classification of 1660 
individuals.  The rows represent the current mental status of the 
individuals, while the columns (A-F) reflect the socioeconomic status of 
their parents. ("Mild" and "Moderate" refer to severity of symptoms.)

		----------+-----------------------------------
		Mental    |
		Health    |    Parents Socioeconomic status   
		Status    |    A     B     C     D     E     F
		----------+-----------------------------------
		     Well |   64    57    57    72    36    21
		     Mild |   94    94   105   141    97    71
		 Moderate |   58    54    65    77    54    54
		 Impaired |   46    40    60    94    78    71
		----------+-----------------------------------
		Source: JASA (1997), p. 210.

Stata output from five models is included in an appendix [Appendix 2].

 1.  Give the usual names for Models [1] through [5]:
     
     	[1]  _________________________
     	[2]  _________________________
     	[3]  _________________________
     	[4]  _________________________
     	[5]  _________________________
     	
 2.	 Draw a diagram showing the nesting relationships between models [1] 
	 through [5].  Start with the saturated model at the top of your 
	 diagram.  If model X is nested within model Z, draw X at a lower level 
	 than Z and draw a line connecting X to Z.
     
 3.  The table of observed, fitted, and residual values is omitted after 
 	 Model [5].  Why?
     
 4.  The table of residuals after Model [1] indicates that the model does 
     not fit the data well.  How?
     
 5.  Suppose you were to calculate the chi-squared test of independence on 
     the data in the table above.  Without actually performing any 
     calculations, what would you expect that test to show?  Why?
     
 6.  Of interest is the extent to which parental SES can predict future 
     mental health problems in their children.  How would you address this 
     question using the results of the appendix?
     
 7.  In Model [4], interpret the coefficient of "ms" (0.091).
     
 8.  In Model [2], how would you interpret the coefficients associated 
     with as2 through as4?