Additional
Statistics
Knowledge Item: CA-Program Satisfaction-10
Model 2: Gender as the First Split
of the Sample
As an alternative to the exhaustive
CHAID (CHi-square Automatic
Interaction Detector) model shown in the Extended
Results section of this Knowledge Item, an alternate model was
calculated. As opposed to the other, purely empirical model, in this
model, the first predictive factor was specified to be patient gender.
Then, for each gender, a purely empirical model was developed. The
resulting model is shown in the figure below. As can be seen, the
differences in overall satisfaction related to criminal justice
involvement are pronounced for
male patients but not for female patients.
While the sample
can be split on several factors to yield groups of patients who are
relatively more or less satisfied, it should be recognized that the
vast majority of all patients are highly satisfied with their
services. Note that
in the following CHAID diagram, green bars
represent the distribution among clients of total satisfaction scores. Click
graphic to expand. (IE 6 users may also have to click the graphic expansion button in the new window.)
More Information:
CHAID and CHAID Diagram
Click
here for a list of the possible predictor variables that would have been
entered, if statistically significant, into this CHAID model, and a discussion of several important methodological issues about these indicators.
Note on CHAID models:
CHAID is a useful method of summarizing data, and can show major natural divisions of the sample by various defining variables. It must be
recognized, however, that CHAID is analogous to a "forward"
stepwise regression analysis and has all of the possible inferential
difficulties of such stepwise regression methods. The statistical significance tests are sequential ones dependent on prior splits of the sample. In many cases, the models presented should be considered as suggestive, but not absolutely definitive as there may be alternate models that also fit these data in a statistically or theoretically acceptable manner. This model may have been manually altered very slightly from the automated CHAID modeling trees; specifically, categories for "missing values" may have been separated (or re-split) from categories for actual values with which they were statistically merged if the authors judged this would give a more clear interpretation of the data; the separation may result in a "missing category" with only a few cases that could be statistically merged with one of the other categories. [In those cases where the "missing value" category is combined with actual values, it was judged that the automated split was a better representation of these data.] The use of Bonferroni confidence intervals to correct for the potentially large number of statistical tests in this model building method and the use of more stringent alpha levels results in relatively conservative data representations. All patient-client model analyses were conducted by the senior author [GH] so that consistent data fitting techniques and judgments would be employed in the different areas studied. In many cases, alternate models are presented so that the viewer can judge the appropriateness of one or more ways of looking at the same data.
Appendix:
Charts showing the relationship of each service need and
vulnerability to the Total Satisfaction Score.
Model 3: Heroin Use as the First
Split of the Sample
As an alternative to the exhaustive
CHAID (CHi-square Automatic
Interaction Detector) model shown in the Extended
Results section of this Knowledge Item, an alternate model was
calculated. As opposed to the other, purely empirical model, in this
model, the first predictive factor was specified to be heroin use
pattern.
Then, heroin users and nonusers were further divided into crack users
and nonusers. The
resulting model is shown in the figure below. As can be seen, active
drug users are somewhat less, but highly, satisfied than individuals
who do not abuse drugs. Note
that in the following CHAID diagrams, green
bars represent the distribution among clients of total satisfaction
scores.
Click graphic to expand. (IE 6 users may also have to click the graphic expansion button in the new window.)
More Information:
CHAID and CHAID Diagram
Click
here for a list of the possible predictor variables that would have been
entered, if statistically significant, into this CHAID model, and a discussion of several important methodological issues about these indicators.
Appendix:
Charts showing the relationship of each service need and
vulnerability to the Total Satisfaction Score.
Alternate Models
Click
graphic to expand. (IE 6 users may also have to click the graphic expansion button in the new window.)
More Information:
CHAID and CHAID Diagram
Appendix to CHAID
Analyses on Needs and Vulnerabilities:
Relationship of the Individual Needs and Vulnerabilities to the Total
Satisfaction Score
The following graphics show the
relationship between the presence or absence of each of the needs and
vulnerability indicators and the Total Satisfaction Score for male and
female patients. These
results supplement the CHAID analysis but are not a formal part of it.
In each set, the first
chart is an error bar plot which shows the mean of the Total
Satisfaction Score and the 95%
confidence interval around the mean. This plot is useful for examining the
central tendency in the scores as related to the indicator against which it is
plotted. The second chart in the set is a boxplot. The boxplot represents the
median score for each group, and the total distribution of scores using the
convention that the box represents the 25th to the 75th percentile and the
whiskers represent the expected "tails" of the distribution. After
each chart there is hyperlink to a description of how to interpret that type
of chart.
Managed Care: Race-Ethnicity
and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Sexual
Orientation and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Age
and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Primary
Language and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Childcare
Needs and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Highest
Grade Completed and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Employment
Status and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Insurance
Coverage and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Alcohol
Problem and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Heroin
Use and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Crack
Use and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Other
Drug Use and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Criminal
Justice System Involvement and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Sex
Work and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Sex
with Injection Drug User and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Housing
Status and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Dependent
Upon Public Supported Medical Services and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Drug
Abuse and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Type
of Clinic and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Managed Care: Site
Code and Total
Satisfaction Score
More Information:
Error Bar Chart
More Information:
Boxplot
Means
Total Satisfaction Score by
Race-Ethnicity
by Gender
Total Satisfaction Score by
Sexual Orientation
by Gender
Total Satisfaction Score by
Age
by Gender
Total Satisfaction Score by
Primary Language
by Gender
Total Satisfaction Score by
Childcare Needs
by Gender
Total Satisfaction Score by
Highest Grade Completed
by
Gender
Total Satisfaction Score by
Employment Status
by Gender
Total Satisfaction Score by
Insurance Coverage
by Gender
Total Satisfaction Score by
Alcohol Problem
by Gender
Total Satisfaction Score by
Heroin Use
by Gender
Total Satisfaction Score by
Crack Use
by Gender
Total Satisfaction Score by
Other Drug Use
by Gender
Total Satisfaction Score by
Criminal
Justice System Involvement
by Gender
Total Satisfaction Score by
Sex Work
by Gender
Total Satisfaction Score by
Sex with Injection
Drug User
by Gender
Total Satisfaction Score by
Housing Status
by Gender
Total Satisfaction Score by
Dependent Upon Public
Supported Medical Services
by Gender
Total Satisfaction Score by
Drug Abuse
by Gender
Last Updated:
March 25, 2005; data through June 15, 1999; analyses conducted October 1999 and March - May 2000. |
