Areas = 50 Individuals = 970 | Model 1 (null model) | Model 2 (plus age, sex, and household income) | Model 3 (plus area disadvantage) | |||
---|---|---|---|---|---|---|
*The grocery purchasing index ranged from 0–100, with higher scores indicating a greater compliance with dietary guideline recommendations. †Expressed as a two standard deviation effect size. ‡See Snijders and Bosker (page 57) for a discussion of why level 2 random effects variance can be estimated as zero48 §The proportion of the total variance in grocery purchasing behaviour that is between the census collectors districts (small urban areas). | ||||||
Constant | 51.40 | 46.80 | 41.72 | |||
Fixed effects | Est | 95%CI | Est | 95% CI | ||
Age of main food purchaser | 0.21 | 0.14 to 0.29 | 0.21 | 0.14 to 0.28 | ||
Sex of main food purchaser (male) | −4.49 | −7.10 to −1.88 | −4.47 | −7.08 to −1.86 | ||
Household income | ||||||
$52000 or more | – | – | – | – | ||
$36400–51999 | −5.46 | −8.48 to −2.44 | −5.30 | −8.35 to −2.25 | ||
$20800–36399 | −6.98 | −9.86 to −4.12 | −6.69 | −9.65 to −3.74 | ||
⩽$20799 | −9.22 | −12.54 to −5.91 | −8.74 | −12.26 to −5.23 | ||
Area socioeconomic disadvantage† | 0.94 | −1.35 to 3.23 | ||||
Random effects variance | Est | SE | Est‡ | SE | Est | SE |
Level 2 (areas) | 2.84 | 3.73 | 0.00 | 0.00 | 0.00 | 0.00 |
Level 1 (individual) | 307.33 | 14.30 | 288.80 | 13.55 | 288.61 | 13.10 |
Deviance | 8317.05 | 8248.53 | 8247.88 | |||
Intraclass correlation (%)§ | 0.91 | 0.00 | 0.00 |