Skip to main content

Table 8 Linear regression: Residuals predicted by ethnicitya

From: Measurement invariance testing of the PHQ-9 in a multi-ethnic population in Europe: the HELIUS study

 

Item:

1

2

3

4

5

6

7

8

9

 

Unstandardized regression coefficients

Men:

Dutch (ref)

–

–

–

–

–

–

–

–

–

South-Asian Surinamese

0.040

0.014

0.021

0.023

0.110

0.011

-0.072

-0.006

-0.083

African Surinamese

0.133

0.056

0.017

-0.045

0.086

0.085

-0.053

0.041

-0.048

Ghanaians

0.250

0.172

-0.000

0.207

0.178

0.050

0.021

0.050

-0.012

Turks

0.016

-0.006

-0.033

0.033

0.083

-0.054

-0.051

0.058

-0.025

Moroccans

0.058

-0.016

-0.014

-0.019

0.131

-0.043

-0.009

-0.024

0.000

R2

0.008

0.005

0.000

0.007

0.004

0.004

0.001

0.001

0.001

Women:

Dutch (ref)

–

–

–

–

–

–

–

–

–

South-Asian Surinamese

0.059

0.051

-0.070

0.019

0.010

-0.029

-0.030

0.022

-0.083

African Surinamese

0.103

0.065

-0.016

0.016

0.063

-0.022

-0.007

0.019

-0.092

Ghanaians

0.354

0.242

-0.077

0.120

0.128

0.054

0.004

0.113

-0.011

Turks

0.095

0.046

-0.080

0.162

0.109

-0.057

-0.064

0.109

-0.069

Moroccans

0.062

0.015

-0.073

0.114

0.105

-0.075

-0.017

0.017

-0.106

R2

0.012

0.006

0.001

0.005

0.003

0.002

0.001

0.003

0.002

  1. Bold coefficients were significant at p < 0.05, R2 = explained variance by ethnicity variable
  2. aResiduals were obtained in a logistic regression models with PHQ-9 item scores as outcome variables, and PHQ-9 factor score as the predictor