Skip to main content

Table 3 Final logistic regression model of the most important predictors of being offered a 60-hour stay in hospital following delivery (n = 1212a)

From: Longer postpartum hospitalization options – who stays, who leaves, what changes?

Predictors

Adjusted Odds Ratio b

95% Confidence Interval

Site

1

1.00

-

4

7.37

(4.66, 11.68)

2

13.22

(8.29, 21.09)

5

14.84

(9.13, 24.14)

3

33.68

(33.68, 115.3)

Mother has a family physician:

No

1.00

-

Yes

2.45

(1.28, 4.69)

Ethnic or cultural group:

Other

1.00

-

Canadian

1.84

(1.26, 2.70)

Final Logistic Regression Model Statistics: Rho-square = 0.25 (a pseudo R2, values between 0.2 and 0.4 suggest a very good fit)

Hosmer and Lemeshow Goodness-of-fit test = 0.98 (values greater than 0.25 indicate good fit) 74.3% correctly classified

  
  1. a Eighteen of the 1230 (1.5%) mothers had missing values for one or more of the variables included in the final model.
  2. b Odds ratios for categorical variables represent comparisons with the referent group (OR = 1.00) after adjustment for all other variables in the model.