Ó£»¨ÊÓƵ

Skip to main content

Table 5 Performance of the propensity score matching: quality measurements

From: Impact of partner alcohol use on intimate partner violence among reproductive-age women in East Africa Demographic and Health Survey: propensity score matching

Variable

Sample

Mean

% bias reduction

%bias

t- statistic

p-value

Treated

Control

Age

Unmatched

1.19

1.03

20.3

0.911

26.40

&±ô³Ù; 0.001

Ìý

Matched

1.18

1.18

-0.1

0.935

99.7

0.08

Partner

Age

Unmatched

1.22

1.14

11.6

0.94

15.15

&±ô³Ù; 0.0001

Ìý

Matched

1.22

1.22

0.1

0.920

99.3

0.10

Media

exposure

Unmatched

0.65

0.62

0.9

-1.46

1.22

0.223

Ìý

Matched

0.65

0.65

0.2

0.822

79.4

0.22

Partner education

Unmatched

1.23

1.31

-10.1

0.81

-13.05

&±ô³Ù; 0.0001

Ìý

Matched

1.23

1.23

-0.2

0.812

98.1

0.24

Residence

Unmatched

1.72

1.69

5.9

0.95*

7.75

&±ô³Ù; 0.0001

Ìý

Matched

1.71

1.71

-0.0

0.962

99.3

0.065

Sex household

Unmatched

1.30

1.28

5.9

1.05*

7.74

&±ô³Ù; 0.0001

Ìý

Matched

1.30

1.30

0.1

0.933

98.8

0.08