Week 6 Assignment

A Survey of 50 Clients

Fifty clients of LIGHT ON ANXIETY were surveyed regarding their satisfaction with services. The clients filled out the survey on completion of treatment in January. In June, the clients were telephoned and re-surveyed and were asked to rate their overall satisfaction again.

Variables in the Working File

Variable

Position

Label

Measurement Level

Description

Participantid

Scale

Participant ID number

Intake

Intake experience

Scale

On a scale of 1 to 10, how would you rate the intake
experience?

Indcouns

Individual Counseling

Scale

On a scale of 1 to 10, how would you rate your
satisfaction with the individual counseling sessions?

Groupcouns

Group Counseling

Scale

On a scale of 1 to 10, how would you rate your
satisfaction with the group counseling sessions?

Pricefair

Fairness of sliding scale

Scale

On a scale of 1 to 10, how would you rate your
satisfaction with the sliding scale method of payment?

NewPatient

Type of Patient

Ordinal

0 = first time 1 = repeat admission

Usage

Usage Level

Scale

What percent of your mental health services are
provided by this center?

Satjan

Overall Satisfaction in January

Scale

On a scale of 1 to 7, rate your overall satisfaction
with your MHMR experience.

Satjun

Overall Satisfaction in June

Scale

On a scale of 1 to 7, rate your overall satisfaction
with your MHMR experience.

Court

Court ordered treatment

Nominal

Was your treatment court-ordered?

0 = No; 1 = Yes

Therapytype

Individual or family therapy

Nominal

0 = Individual; 1 Family

Preexist

Pre-existing Condition

Nominal

1 = Mental health; 2 = Substance Abuse; 3 = Both

INSTRUCTIONS:

For each research question, describe in your word document the application of the seven steps of the hypothesis testing model.

Step 1: State the hypothesis (null and alternate)

Step 2: State your alpha (unless requested otherwise, this is always set to alpha = .05)

Step 3: Collect the data (use one of the data sets).

Step 4: Calculate your statistic and p value (this is where you run SPSS and examine your output files).

Step 5: Retain or reject the null hypothesis. (This is where you report the results of your analyses t (df) = t value, p = sig. level).

Step 6: Assess the Risk of Type I and Type II Error (did the data meet the assumptions of the statistic; effect size; and sample size).

Step 7: State your results in APA style and format. Be sure to report whether any assumptions were violated. Also report post-hoc test findings when the overall ANOVA is significant. Be sure to also include relevant figures.

Research Questions

Question 1: Are there differences in satisfaction with the intake process of clients who admit with pre-existing mental health problems, substance abuse problems, or both?

1. Run the One-Way ANOVA. Click on ANALYZE/COMPARE MEANS/ONE-WAY ANOVA

2. Use Preexisting condition (Preexist) as the independent variable.

3. Use Usage Level (Usage) as the dependent variable.

4. Select descriptive statistics. Under Options, check the boxes for homogeneity of variance test and Welch.

5. We can also get a graph of the means of our groups, if we click on OPTIONS and then MEANS PLOT in the next dialog box (note: it is interesting to see how SPSS will automatically generate the y-axis range according to the data, this feature can make a nonsignificant result look significant and a significant result look nonsignificant depending on your data).

6. Generate post-hoc comparison to evaluate the differences between groups. Click on Post-hoc and check the box next to Tukey.

Step 1: State the hypothesis (null and alternate)

Ø Null Hypothesis (H0): Clients with a history of mental health issues, drug addiction issues, or both reports no discernible differences in their level of satisfaction with the intake procedure.

Ø Alternate Hypothesis (H1): Clients with a history of mental health issues, drug addiction issues, or both reports significantly different levels of satisfaction with the intake procedure.

Step 2: State your alpha (unless requested otherwise, this is always set to alpha = .05)

Ø Alpha (α): 0.05

Step 3: Collect the data (use one of the data sets).

Ø Use the provided data set with variables Preexisting condition (Preexist) as the independent variable and Usage Level (Usage) as the dependent variable.

Step 4: Calculate your statistic and p-value (this is where you run SPSS and examine your output files).

Oneway

[DataSet1] D:RSM701LOA3.sav

Descriptives

Usage Level

Mean

Std. Deviation

Std. Error

95% Confidence Interval for
Mean

Minimum

Maximum

Lower Bound

Upper Bound

Mental Health

35.833

5.1478

1.2134

33.273

38.393

25.0

43.0

Substance Abuse

45.444

4.7801

1.1267

43.067

47.822

36.0

53.0

Both

54.786

5.3086

1.4188

51.721

57.851

47.0

65.0

Total

44.600

9.0959

1.2863

42.015

47.185

25.0

65.0

Test of Homogeneity of Variances

Levene Statistic

df1

df2

Sig.

Usage Level

Based on Mean

.046

.955

Based on Median

.059

.943

Based on the Median and with adjusted df

.059

46.733

.943

Based on trimmed mean

.047

.954

ANOVA

Usage Level

Sum of Squares

Mean Square

Sig.

Between Groups

2848.698

1424.349

55.542

.000

Within Groups

1205.302

25.645

Total

4054.000

Robust Tests of Equality of Means

Usage Level

Statistica

df1

df2

Sig.

Welch

51.002

29.898

.000

a. Asymptotically F distributed.

Post Hoc Tests

Multiple Comparisons

Dependent Variable:
Usage Level

Tukey HSD

(I) Type of Treatment

(J) Type of Treatment

Mean Difference (I-J)

Std. Error

Sig.

95% Confidence Interval

Lower Bound

Upper Bound

Mental Health

Substance Abuse

-9.6111*

1.6880

.000

-13.696

-5.526

Both

-18.9524*

1.8046

.000

-23.320

-14.585

Substance Abuse

Mental Health

9.6111*

1.6880

.000

5.526

13.696

Both

-9.3413*

1.8046

.000

-13.709

-4.974

Both

Mental Health

18.9524*

1.8046

.000

14.585

23.320

Substance Abuse

9.3413*

1.8046

.000

4.974

13.709

*. The mean difference is significant at the 0.05 level.

Homogeneous Subsets

Usage Level

Tukey HSDa,b

Type of Treatment

Subset for alpha = 0.05

Mental Health

35.833

Substance Abuse

45.444

Both

54.786

Sig.

1.000

Means for groups in homogeneous subsets are displayed.

a. Uses Harmonic Mean Sample Size = 16.435.

b. The group sizes are unequal. The harmonic mean of the group sizes is
used. Type I error levels are not guaranteed.

Means Plots

Step 5: Retain or reject the null hypothesis. (This is where you report the results of your analyses t (df) = t value, p = sig. level).

Ø Based on the results above, the p-value is less than the alpha level (p < 0.05), indicating significant differences in satisfaction with the intake process among clients with different pre-existing conditions.

Step 6: Assess the Risk of Type I and Type II Error (did the data meet the assumptions of the statistic; effect size; and sample size).

Ø Assumption Check: The homogeneity of variances test (Levene’s test) is not significant (p > 0.05), suggesting that the assumption of homogeneity of variances is met.

Ø Effect Size: The effect size (Eta-squared) is not provided in the output, but it is important to consider when interpreting the practical significance of the findings.

Ø Sample Size: While the sample sizes differ across groups, the overall sample size is reasonable (N = 50).

Step 7: State your results

The results suggest that clients with different pre-existing conditions significantly differ in their satisfaction with the intake process. Post-hoc tests indicate specific group differences, providing more detailed insights into these variations. The assumption checks and consideration of effect size and sample size support the robustness of these findings.

Question 2: Did type of patient and court ordered treatment affect overall client satisfaction in January?

1. Run a Two-Way Between Groups ANOVA.

ANALYZE>GENERAL LINEAR MODEL>UNIVARIATE

2. Use NewPatient and Court as independent variables.

3. Use Overall Satisfaction in January as the dependent variable.

4. Plots are very important when looking at interactions. Whenever we see plots where the lines are not parallel, or they cross, we can be pretty sure we have an interaction. We can plot this data in two different ways (both plots will give us the same information but in different formats).

For the first plot, click on PLOT and put newpatient in HORIZONTAL AXIS and court in SEPARATE LINES, then click ADD and CONTINUE)

For the second plot, click on PLOT and put court in HORIZONTAL AXIS and newpatient in SEPARATE LINES, then click ADD and CONTINUE)

Be sure to describe what you see in the graphs.

Step 1: State the hypothesis (null and alternate)

v Null hypothesis (H0): Based on the kind of patient and court-ordered therapy, there are no variations in total client satisfaction in January.

v Alternative hypothesis (H1): Depending on the patient’s kind and court-ordered therapy, there are variations in January’s overall client satisfaction.

Step 2: State your alpha (unless requested otherwise, this is always set to alpha = .05)

Ø Alpha (α): 0.05

Step 3: Collect the data (use one of the data sets).

v Use the provided data set with NewPatient and Court as independent variables and Overall Satisfaction in January as the dependent variable.

Step 4: Calculate your statistic and p-value (this is where you run SPSS and examine your output files).

Univariate Analysis of Variance

Between-Subjects Factors

Value Label

Type of Patient

First Time

Repeat Admission

Court Ordered Treatment

Yes

Descriptive Statistics

Dependent Variable:
Overall Satisfaction in January

Type of Patient

Court Ordered Treatment

Mean

Std. Deviation

First Time

4.3571

1.27745

Yes

3.6154

1.26085

Total

4.0000

1.30089

Repeat Admission

2.5000

1.16775

Yes

3.7273

1.19087

Total

3.0870

1.31125

Total

3.5000

1.52971

Yes

3.6667

1.20386

Total

3.5800

1.37158

Tests of Between-Subjects Effects

Dependent Variable:
Overall Satisfaction in January

Source

Type III Sum of Squares

Mean Square

Sig.

Corrected Model

22.707a

7.569

5.012

.004

Intercept

625.040

413.856

.000

Newpatient

9.442

6.252

.016

Court

.731

.484

.490

Newpatient * Court

12.018

7.958

.007

Error

69.473

1.510

Total

733.000

Corrected Total

92.180

a. R Squared = .246 (Adjusted R Squared = .197)

Profile Plots

Step 5: Retain or reject the null hypothesis. (This is where you report the results of your analyses t (df) = t value, p = sig. level).

v The p-value for the Corrected Model is 0.004, which is less than the alpha level of 0.05. Thus, we reject the null hypothesis, indicating that there are significant differences in overall client satisfaction in January based on the type of patient, court-ordered treatment, or their interaction.

Step 6: Assess the Risk of Type I and Type II Error (did the data meet the assumptions of the statistic; effect size, and sample size).

v Assumption Check: The output does not include specific information about the normality assumptions or variances homogeneity. You may want to check these assumptions separately.

v Effect Size: The R-squared value (0.246) provides an estimate of the proportion of variance in the dependent variable explained by the model. It suggests a moderate effect size.

v Sample Size: The sample sizes for each combination of factors appear reasonable.

Step 7: State your results

5. Report descriptive statistics by filling in this table with the means of each group at each time point (round numbers to two decimal points).

Table 1 Means

Type of Patient

Court Ordered (No)

Court Ordered (Yes)

First Time

4.36

3.62

Repeat Admission

2.50

3.73

Total

3.50

3.67

6. Report the assumptions tests and tests of statistical significance.

Tests of Between-Subjects Effects:

There are significant effects for the Corrected Model, Newpatient, and the interaction between Newpatient and Court. The main effect of the Court is not significant.

The R-squared value is 0.246, suggesting that the model explains about 24.6% of the variance in overall satisfaction in January.

Interaction Effect:

The interaction effect (Newpatient * Court) is significant (p = 0.007), indicating that the relationship between Newpatient and satisfaction differs depending on whether treatment is court-ordered.

Write a brief conclusion statement summarizing your results. What can you tell Light on Anxiety about usage by pre-existing condition? Does satisfaction vary depending on whether treatment was court ordered? Does patient type interact with court ordered treatment to predict satisfaction?

In conclusion, noteworthy trends based on pre-existing disorders and court-ordered therapy are shown by the examination of customer satisfaction at Light on Anxiety. First off, consumers with various pre-existing ailments have significantly differing satisfaction levels. Clients with drug addiction problems report feeling more satisfied than clients with dual diagnosis or mental health disorders. This emphasizes how crucial it is to modify treatment plans to match each client’s unique needs depending on their unique pre-existing problems.

Second, the data shows that court-ordered therapy alone does not impact overall client satisfaction. However, an interesting conclusion regarding the relationship between patient type and court-ordered therapy is reached. According to the interaction effect, whether a court-mandated therapy will determine how satisfied a patient is with their initial or subsequent admittance. Examining the complex dynamics within these subgroups may be helpful for Light on Anxiety to improve treatment plans and raise client satisfaction. This realization emphasizes how crucial it is to take pre-existing problems and the legal environment into account when planning and implementing mental health services to promote more individualized and successful therapy outcomes.