Skip to main content
. Author manuscript; available in PMC: 2024 May 1.
Published in final edited form as: Soc Forces. 2022 May 19;101(3):1422–1459. doi: 10.1093/sf/soac043

Table 6.

Multilevel Mixed Effects Ordered Probit Models Predicting Frequency of Happiness in Past 2 Weeks, with Gender Interactions

Model 1: Global Quality Model 2: Validation Model 3: Frequency of disagreements Model 4: All
Fixed effects Estimate p (RSE) Estimate p (RSE) Estimate p (RSE) Estimate p (RSE)
Survey wave 0.01 * (0.01) 0.01 * (0.01) 0.01 (0.01) 0.01 * (0.01)
Female −0.24 (0.24) −0.36 ** (0.13) −0.22 (0.14) −0.12 (0.29)
Partnership quality
Within global quality 0.37 *** (0.07) 0.24 ** (0.07)
Between global quality 0.47 ** (0.16) 0.20 (0.20)
Within validation 0.71 *** (0.11) 0.49 *** (0.12)
Between validation 1.00 ** (0.29) 0.65 (0.38)
Within frequency of disagreements −0.20 * (0.08) −0.16 * (0.08)
Between frequency of disagreements −0.50 ** (0.18) −0.38 * (0.18)
Partnership quality interacted with sex
Within global quality × female 0.00 (0.08) 0.05 (0.08)
Between global quality × female 0.07 (0.19) 0.12 (0.24)
Within validation × female −0.19 (0.13) −0.22 (0.15)
Between validation × female 0.07 (0.37) 0.07 (0.48)
Within frequency of disagreements × female 0.02 (0.08) 0.08 (0.10)
Between frequency of disagreements × female −0.01 (0.23) 0.04 (0.23)
Random effects ([co=]variances) Estimate (RSE) Estimate (RSE) Estimate (RSE) Estimate (RSE)
Intercept 1.04 (0.13) 0.97 (0.12) 1.02 (0.13) 0.95 (0.12)
Within partnership quality 0.07 (0.03) 0.17 (0.07) 0.10 (0.04) 0.06 (0.02)
Intercept & w/in partnership quality −0.09 (0.05) −0.17 (0.09) 0.15 * (0.07) −0.11 * (0.05)

Source: mDiary Study of Adolescent Relationships and FFCWS

Notes:

*

p < 0.05;

**

p < 0.01;

***

p < 0.001;

p < 0.10.

All models also include the same control variables as in Table 4 (not shown). In Models 1–3, the random effect for “partnership quality” corresponds to the within partnership quality measure being used in the model. In Model 4, random effects are included for only global quality, not validation and frequency of disagreements.