Skip to main content

Table 4 Variance in bias (η2) explained by each study-arm manipulation, stratified by gender

From: Impact of different cover letter content and incentives on non-response bias in a sample of Veterans applying for Department of Veterans Affairs disability benefits: a randomized, 3X2X2 factorial trial

Characteristic as obtained from VA databases

What Veterans were told about content

How name was obtained

Honoraria

Men

Women

Men

Women

Men

Women

Age < 30

14.5%

24.2%

1.4%

0.1%

36.6%

0.9%

Non-white race

23.1%

38.9%*

0.7%

34.2%*

1.2%

0.0%

Combat exposure

31.2%

2.2%

0.0%

30.5%

18.1%

0.6%

Military sexual trauma exposure

25.6%

31.9%

43.0%

8.3%

10.2%

0.4%

Serious mental illness

12.4%

34.8%

9.1%

0.4%

4.1%

0.4%

Charlson Comorbidity Index > 0

8.5%

14.4%

17.4%

53.8%*

19.1%

4.3%

Any VA disability benefits

9.0%

52.0%*

3.1%

11.8%

0.7%

1.4%

VA disability benefits for PTSD

11.2%

17.4%

0.2%

15.5%

7.2%

8.6%

  1. VA Department of Veterans Affairs, PTSD posttraumatic stress disorder
  2. *Bold face font indicates there was a net non-response bias for that characteristic and study-arm manipulation at p < 0.05