-
Chapter 1: Introduction
-
Chapter 2: Administration
-
Chapter 3: Scoring and Reports
-
Chapter 4: Interpretation
-
Chapter 5: Case Studies
-
Chapter 6: Development
-
Chapter 7: Standardization
-
Chapter 8: Reliability
-
Chapter 9: Validity
-
Chapter 10: Fairness
-
Chapter 11: Conners 4–Short
-
Chapter 12: Conners 4–ADHD Index
-
Appendices
Conners 4 ManualChapter 10: Critical & Indicator Items |
Critical & Indicator Items |
In addition to the investigation of measurement properties for the Conners 4 scale scores, the Conners 4 Critical & Indicator Items (i.e., Self-Harm Critical Items and Sleep Problems Indicator; note that the Severe Conduct Critical items were not explored separately, as these items are subsumed by the DSM Conduct Disorder Symptoms Scale) were also investigated for differences among various demographic groups (note that MI and DTF analyses are not item-level analyses and, therefore, are not included in this section).
To understand the potential for bias with the Critical & Indicator Items, differences are presented as Cliff’s delta effect size values (Cliff’s d), which compare the frequency of each response option between the two groups. Values closer to -1 indicate that the first group tends to endorse lower values than the second group, values closer to 1 indicate that the first group tends to endorse higher values than the second group, and values close to 0 represent little difference between the groups (Romano et al., 2006). The size of the group differences in terms of item-level endorsement between genders, racial/ethnic groups, country of residence, and PEL 1 was explored with the matched samples described in the corresponding analyses for the Conners 4 scales earlier in this chapter, drawing from the Conners 4 Normative Samples.
Results of these item-level analyses are presented in Table 10.34 (a to d) for the Self-Harm Critical Items and 10.35 (a to d) for the Sleep Problems Indicator. Effect sizes were negligible for nearly all comparisons for Parent and Teacher. Overall, the median effect size across all comparisons was Cliff’s d = .00 for Parent (ranging from -.08 to .17) and .00 for Teacher (ranging from -.06 to .05). For Self-Report, effect sizes were also negligible for the majority of the comparisons; however, there were a few small effects. The median effect size across all comparisons was -.01 for Self-Report (ranging from -.22 to .07). Overall, the effect sizes that were observed demonstrate how minimal the differences in distribution of response frequency are between the various demographic groups, such that responses to these items are not unduly influenced by the youth’s gender, race/ethnic group, country of residence, or PEL. The very small differences observed between demographic groups on the Conners 4 Self-Harm Critical Items and the Conners 4 Sleep Problems Indicator add support for the fair and generalizable use of the Conners 4 item-level indicators across diverse populations.
| Click to expand |
Table 10.34a. Demographic Group Differences in Self-Harm Critical Items: Gender
|
Form |
Self-Harm Critical Item Stem |
Endorsement (%) |
Cliff’s d |
|
|
Male |
Female |
|||
|
Parent |
Harming self deliberately |
4.5 |
4.7 |
.00 |
|
Talking about suicide |
4.7 |
3.3 |
−.01 |
|
|
Planning or attempting suicide |
3.3 |
3.3 |
.00 |
|
|
Teacher |
Harming self deliberately |
4.2 |
3.0 |
−.01 |
|
Talking about suicide |
3.6 |
3.0 |
−.01 |
|
|
Planning or attempting suicide |
2.5 |
3.0 |
.00 |
|
|
Self-Report |
Harming self deliberately |
16.8 |
16.1 |
.00 |
|
Planning or attempting to harm self |
14.9 |
15.5 |
−.01 |
|
|
Thinking about harming self |
16.5 |
21.1 |
−.04 |
|
Note. Self-Harm Critical Items are considered endorsed with an item response ≥ 1. Guidelines for interpreting Cliff’s |d|: negligible effect size < .15; small effect size = .15 to .32; medium effect size = .33 to .46; large effect size ≥ .47. Positive values indicate that the second group in the comparison provided higher ratings than the group listed first.
| Click to expand |
Table 10.34b. Demographic Group Differences in Self-Harm Critical Items: U.S. Race/Ethnicity
|
Form |
Self-Harm Critical Item Stem |
Endorsement (%) |
Cliff’s d |
Endorsement (%) |
Cliff’s d |
Endorsement (%) |
Cliff’s d |
|||
|
White |
Black |
White |
Hispanic |
White |
Asian |
|||||
|
Parent |
Harming self deliberately |
2.8 |
2.8 |
.00 |
4.3 |
4.8 |
.01 |
2.0 |
2.0 |
.00 |
|
Talking about suicide |
5.1 |
4.5 |
−.01 |
3.7 |
2.7 |
−.01 |
2.0 |
5.9 |
.04 |
|
|
Planning or attempting suicide |
4.0 |
4.0 |
.00 |
3.7 |
3.7 |
.00 |
2.0 |
3.9 |
.02 |
|
|
Teacher |
Harming self deliberately |
5.2 |
4.7 |
−.01 |
4.7 |
1.3 |
−.03 |
4.7 |
2.3 |
−.02 |
|
Talking about suicide |
2.1 |
4.7 |
.03 |
1.3 |
2.7 |
.01 |
2.3 |
4.7 |
.02 |
|
|
Planning or attempting suicide |
3.6 |
3.6 |
.00 |
2.7 |
1.3 |
−.01 |
2.3 |
7.0 |
.05 |
|
|
Self-Report |
Harming self deliberately |
17.8 |
16.3 |
−.02 |
16.3 |
18.4 |
.02 |
20.9 |
14.0 |
−.06 |
|
Planning or attempting to harm self |
13.2 |
16.3 |
.03 |
12.8 |
18.4 |
.06 |
14.0 |
16.3 |
.03 |
|
|
Thinking about harming self |
19.4 |
17.8 |
−.01 |
19.1 |
19.9 |
.01 |
18.6 |
16.3 |
−.02 |
|
Note. Self-Harm Critical Items are considered endorsed with an item response ≥ 1. Guidelines for interpreting Cliff’s |d|: negligible effect size < .15; small effect size = .15 to .32; medium effect size = .33 to .46; large effect size ≥ .47. Positive values indicate that the second group in the comparison provided higher ratings than the group listed first.
| Click to expand |
Table 10.34c. Demographic Group Differences in Self-Harm Critical Items: Country of Residence
|
Form |
Self-Harm Critical Item Stem |
Endorsement (%) |
Cliff’s d |
|
|
U.S. |
Canada |
|||
|
Parent |
Harming self deliberately |
5.4 |
8.1 |
−.03 |
|
Talking about suicide |
5.4 |
2.7 |
.03 |
|
|
Planning or attempting suicide |
5.4 |
4.1 |
.01 |
|
|
Teacher |
Harming self deliberately |
5.0 |
3.4 |
.02 |
|
Talking about suicide |
1.7 |
3.4 |
−.02 |
|
|
Planning or attempting suicide |
2.5 |
3.4 |
−.01 |
|
|
Self-Report |
Harming self deliberately |
17.5 |
23.8 |
−.07 |
|
Planning or attempting to harm self |
12.5 |
17.5 |
−.05 |
|
|
Thinking about harming self |
13.8 |
21.3 |
−.07 |
|
Note. Self-Harm Critical Items are considered endorsed with an item response ≥ 1. Guidelines for interpreting Cliff’s |d|: negligible effect size < .15; small effect size = .15 to .32; medium effect size = .33 to .46; large effect size ≥ .47. Positive values indicate that the second group in the comparison provided higher ratings than the group listed first.
| Click to expand |
Table 10.34d. Demographic Group Differences in Self-Harm Critical Items: Parental Education Level
|
Form |
Self-Harm Critical Item Stem |
Endorsement (%) |
Cliff’s d |
|
|
PEL 1–2 |
PEL 3–5 |
|||
|
Parent |
Harming self deliberately |
5.3 |
3.7 |
.02 |
|
Talking about suicide |
3.3 |
4.4 |
−.01 |
|
|
Planning or attempting suicide |
4.0 |
2.8 |
.01 |
|
|
Teacher |
Harming self deliberately |
— |
— |
— |
|
Talking about suicide |
— |
— |
— |
|
|
Planning or attempting suicide |
— |
— |
— |
|
|
Self-Report |
Harming self deliberately |
15.7 |
15.9 |
.00 |
|
Planning or attempting to harm self |
13.6 |
14.3 |
−.01 |
|
|
Thinking about harming self |
16.4 |
19.3 |
−.03 |
|
Note. Self-Harm Critical Items are considered endorsed with an item response ≥ 1. Guidelines for interpreting Cliff’s |d|: negligible effect size < .15; small effect size = .15 to .32; medium effect size = .33 to .46; large effect size ≥ .47. Positive values indicate that the second group in the comparison provided higher ratings than the group listed first.
| Click to expand |
Table 10.35a. Demographic Group Differences in Sleep Problems Indicator Items: Gender
|
Form |
Sleep Problems Indicator Item Stem |
Endorsement (%) |
Cliff’s d |
|
|
Male |
Female |
|||
|
Parent |
Having trouble sleeping |
11.4 |
10.8 |
−.01 |
|
Appearing tired |
6.5 |
7.3 |
.00 |
|
|
Teacher |
Appearing tired |
12.3 |
9.0 |
−.06 |
|
Self-Report |
Having trouble sleeping |
19.3 |
19.6 |
.01 |
|
Feeling tired |
12.4 |
13.7 |
−.09 |
|
Note. Sleep Problems Indicator items are considered endorsed with an item response ≥ 2 for trouble sleeping, and an item response of 3 for tiredness. Guidelines for interpreting Cliff’s |d|: negligible effect size < .15; small effect size = .15 to .32; medium effect size = .33 to .46; large effect size ≥ .47. Positive values indicate that the second group in the comparison provided higher ratings than the group listed first.
| Click to expand |
Table 10.35b. Demographic Group Differences in Sleep Problems Indicator Items: U.S. Race/Ethnicity
|
Form |
Sleep Problems Indicator Item Stem |
Endorsement (%) |
Cliff’s d |
Endorsement (%) |
Cliff’s d |
Endorsement (%) |
Cliff’s d |
|||
|
White |
Black |
White |
Hispanic |
White |
Asian |
|||||
|
Parent |
Having trouble sleeping |
10.2 |
11.4 |
.02 |
10.2 |
9.6 |
.02 |
9.8 |
3.9 |
.02 |
|
Appearing tired |
5.1 |
9.1 |
−.01 |
7.0 |
9.6 |
−.01 |
3.9 |
3.9 |
.17 |
|
|
Teacher |
Appearing tired |
8.3 |
11.5 |
.03 |
6.0 |
10.0 |
.04 |
2.3 |
9.3 |
.02 |
|
Self-Report |
Having trouble sleeping |
20.9 |
16.3 |
−.16 |
16.3 |
16.3 |
.02 |
14.0 |
23.3 |
.07 |
|
Feeling tired |
13.2 |
19.4 |
−.01 |
12.8 |
6.4 |
−.07 |
16.3 |
9.3 |
−.22 |
|
Note. Sleep Problems Indicator items are considered endorsed with an item response ≥ 2 for trouble sleeping, and an item response of 3 for tiredness. Guidelines for interpreting Cliff’s |d|: negligible effect size < .15; small effect size = .15 to .32; medium effect size = .33 to .46; large effect size ≥ .47. Positive values indicate that the second group in the comparison provided higher ratings than the group listed first.
| Click to expand |
Table 10.35c. Demographic Group Differences in Sleep Problems Indicator: Country of Residence
|
Form |
Sleep Problems Indicator Item Stem |
Endorsement (%) |
Cliff’s d |
|
|
U.S. |
Canada |
|||
|
Parent |
Having trouble sleeping |
12.2 |
13.5 |
−.08 |
|
Appearing tired |
6.8 |
9.5 |
.00 |
|
|
Teacher |
Appearing tired |
8.4 |
7.6 |
.01 |
|
Self-Report |
Having trouble sleeping |
15.0 |
17.5 |
.05 |
|
Feeling tired |
13.8 |
21.3 |
−.15 |
|
Note. Sleep Problems Indicator items are considered endorsed with an item response ≥ 2 for trouble sleeping, and an item response of 3 for tiredness. Guidelines for interpreting Cliff’s |d|: negligible effect size < .15; small effect size = .15 to .32; medium effect size = .33 to .46; large effect size ≥ .47. Positive values indicate that the second group in the comparison provided higher ratings than the group listed first.
| Click to expand |
Table 10.35d. Demographic Group Differences in Sleep Problems Indicator: Parental Education Level
|
Form |
Sleep Problems Indicator Item Stem |
Endorsement (%) |
Cliff’s d |
|
|
PEL 1–2 |
PEL 3–5 |
|||
|
Parent |
Having trouble sleeping |
12.4 |
11.8 |
−.02 |
|
Appearing tired |
7.5 |
8.2 |
−.03 |
|
|
Self-Report |
Having trouble sleeping |
16.9 |
19.1 |
−.01 |
|
Feeling tired |
12.9 |
14.0 |
−.08 |
|
Note. Sleep Problems Indicator items are considered endorsed with an item response ≥ 2 for trouble sleeping, and an item response of 3 for tiredness. Guidelines for interpreting Cliff’s |d|: negligible effect size < .15; small effect size = .15 to .32; medium effect size = .33 to .46; large effect size ≥ .47. Positive values indicate that the second group in the comparison provided higher ratings than the group listed first.
1 Given the small differences and mirroring what was done for the PEL invariance analyses earlier in this chapter, PEL was collapsed into two groups: (a) High school diploma or less (PEL 1 and PEL 2), and (b) some post-secondary education (PEL 3 to PEL 5).
| < Back | Next > |