Skip to main content

Table 3 Linear multi-level regressions with face mask use as the dependent variable

From: Face mask use during the COVID-19 pandemic: how risk perception, experience with COVID-19, and attitude towards government interact with country-wide policy stringency

 

Model 1

Model 2

Model 3

Coeff.

SE

p-value

Coeff.

SE

p-value

Coeff.

SE

p-value

Intercept

3.26

0.31

< 0.001

2.98

0.19

< 0.001

1.68

0.28

< 0.001

Risk perception COVID-19 (individual level)

 Self-related

   

0.14

0.02

< 0.001

0.14

0.02

< 0.001

 Other-related

   

0.03

0.02

0.15

0.03

0.02

0.15

Experience COVID-19 (individual level)

 Direct experience

   

−0.06

0.06

0.27

−0.06

0.06

0.27

 Indirect experience

   

0.01

0.04

0.80

0.01

0.04

0.80

Government attitude (individual level)

 Government trust

   

−0.03

0.02

0.17

− 0.03

0.02

0.17

 Perceived clarity communication

   

−0.03

0.02

0.17

−0.03

0.03

0.18

Policy stringency (country level)

         

 Stringency facemask regulations

   

0.90

0.20

0.002

   

 Stringency: medium (vs. low)

      

1.48

0.37

0.005

 Stringency: high (vs. low)

      

2.35

0.40

< 0.001

Controls (individual level)

 Female

   

0.34

0.04

< 0.001

0.34

0.04

< 0.001

 Age

   

0.01

0.02

0.55

0.01

0.01

0.54

 International student

   

0.66

0.05

< 0.001

0.66

0.05

< 0.001

Variance individual level

2.02

0.03

 

1.92

0.03

 

1.92

0.03

 

Variance country level

0.95

0.43

 

0.35

0.18

 

0.23

0.13

 

Pseudo R2 individual level

   

0.05

  

0.05

  

Pseudo R2 country level

   

0.63

  

0.76

  

Deviance

24,496

  

24,166

  

24,160

  

AIC / BIC

24,502

24,523

 

24,192

24,281

 

24,188

24,284

 

Number of individuals

6905

  

6905

  

6905

  

Number of countries

10

  

10

  

10

  
  1. SE=Kenward-Roger standard error. Restricted maximum likelihood is used. Estimates in bold represent p-values< 0.05. Each model includes a country-level random intercept