Skip to main content
. Author manuscript; available in PMC: 2010 Nov 30.
Published in final edited form as: Psychiatry Res. 2009 Sep 30;170(1):86–90. doi: 10.1016/j.psychres.2009.03.006

Table 2.

Hierarchical regression results for recurrent suicide attempt, self-injury, and highest lethality of suicide attempt or self-injury with age, type of Axis I disorder and current AN, BN or BED as predictors.

Suicide Attempt Self-Injury Highest Lethality of suicide Attempt or Self-Injury

Variable NR2a ORb 95thCIc NR2 OR 95thCI Δ R2d βe

Block 1: 0.02 0.17 0.00
 Age 1.01 0.95–1.07 0.88*** 0.83–0.94 −0.01
Block 2: 0.24 0.38 0.20
 Mood Disorders 0.72 0.26– 2.01 2.81 0.99 –7.99 −0.003
 Anxiety Disorders 1.17 0.43– 3.18 1.44 0.52–3.96 −0.002
 Substance Abuse & Dependence 0.23** 0.09 –0.62 0.12*** 0.04–0.33 −0.40***
 Psychotic Disorders 1.70 0.58 – 4.95 0.36 0.10–1.30 0.14
 Somatization Disorders 34.91** 3.35– 452.70 1.21 0.19–7.56 0.21*
Block 3: 0.33 0.45 0.22
 Anorexia Nervosa 3.04 0.56–26.47 15.35* 1.29–182.98 0.06
 Bulimia Nervosa 18.66* 1.78 –195.41 0.62 0.09–4.06 −0.13
 Binge-Eating Disorder 0.36 0.02 – 6.08 0.26 0.03–2.06 −0.03
a

NR 2= Nagelkerke’s R squared which estimates strength of association between predictors in each step for the hierarchical logistic regression.

b

OR=Odds Ratio which is an estimate of effect size for each predictor from the final hierarchical logistic regression model generated.

c

95th CI = 95th Confidence Interval for each predictor from the final hierarchical logistic regression model generated.

d

R2 =indicates the amount of variance accounted for by each additional step in the hierarchical linear regression.

e

β =standardized beta estimates for the final hierarchical linear regression model generated are presented as an estimate of effect size.

*

P<0.05,

**

P<0.01,

***

P<0.001