Skip to main content

Table 7 Ordinal regression with interest in becoming an engineer as the dependent variable

From: The impact of country of schooling and gender on secondary school students’ conceptions of and interest in becoming an engineer in Ireland, Kenya and Sweden

 

Model 1

Model 2

Model 3

W (df)

B (SE)

OR (95% CI)

W (df)

B (SE)

OR (95% CI)

W (df)

B (SE)

AOR (95% CI)

Gender

16.345 (1)**

− 0.421 (0.104)

0.657 (0.535, 0.805)

   

12.058 (1)**

− 0.364 (0.105)

0.695 (0.566, 0.853)

Country (Ireland), Ref = Sweden

   

0.029 (1)

− 0.022 (0.132)

0.978 (0.756, 1.266)

0.001 (1)

− 0.005 (0.132)

0.995 (0.768, 1.288)

Country (Kenya), Ref = Sweden

   

94.866 (1)**

1.313 (0.135)

3.718 (2.855, 4.843)

93.285 (1)**

1.302 (0.135)

3.677 (2.823, 4.790)

Country (Ireland), Ref = Kenya

   

109.392 (1)**

− 1.336 (0.128)

0.263 (0.205, 0.338)

104.760 (1)**

− 1.307 (0.128)

0.271 (0.211, .348)

Full model -2 Log likelihood

100.860

232.399

400.284

Full model likelihood ratio

χ2(1) = 16.389, p < 0.001

χ2(2) = 132.256, p < 0.001

χ2(3) = 144.268, p < 0.001

Cox and Snell R2

0.014

0.106

0.115

Nagelkerke R2

0.014

0.111

0.120

McFadden R2

0.004

0.036

0.039

  1. *p < 0.05. **p < 0.01. Independent variable = Interest in becoming an engineer measured through a 5-point Likert item (1 = not at all interested, 5 = very interested). W = Wald. df = degrees of freedom. SE = standard error. OR = odds ratio. AOR = adjusted odds ratio. CI = confidence interval. Gender reference = male. Intercept calculated with Sweden as the reference country. Model 3 coefficients are adjusted for all covariates. N/A coefficients due to no drawings coded as scientists in the Irish sample