Skip to main content

Table 3 Conditional logistic regression of the variables potentially affecting acne diagnosis

From: Acne Vulgaris and adherence to the mediterranean diet among university students: a case‒control study

 

Crude odds ration

Full model:

adjusted odds ratio (CI 95%)

Backward elimination model:

adjusted odds ratio (CI 95%)

Adherence to the MD

   

Low adherence

reference

reference

reference

High adherence

0.86 (0.46–1.60)

0.70

(0.34–1.37)

0.88

(0.47–1.62)

Family history of acne vulgaris

   

Negative family history

Reference

reference

reference

Positive family history

2.01* (1.17–3.44)

1.75

(0.91–3.13)

1.95*

(1.14–3.34)

Smoking status

   

Nonsmoker

reference

reference

-

Previous smoker

2.19 (0.19–24.83)

1.51 (0.12–18.64)

 

Current smoker

1.31 (0.51–3.35)

1.19 (0.45–3.17)

 

Milk Consumption

   

None

reference

reference

-

1–2 times a week

1.10 (0.56–2.17)

0.83 (0.42-2.00)

 

Daily intake

1.01 (0.54–1.85)

0.72 (0.41–1.83)

 
  1. - Abbreviations: CI: Confidence interval, MD: Mediterranean diet
  2. - Analysis was conducted by employing conditional logistic regression. The full regression model included potential confounders by clinical selection of variables based on the literature (family history of acne vulgaris, smoking status, and milk consumption). The second model used the backward elimination technique, and adherence to the MD and family history of acne vulgaris were the only two variables that fit the model
  3. - The Hosmer–Lemeshow test indicated a goodness of fit (p value > 0.05) for both models
Back to article page

Journal of Health, Population and Nutrition

ISSN: 2072-1315

Contact us