Skip to main content

Table 5 Balancing tests

From: Food environment and childhood obesity: the effect of dollar stores

   

Movers & Stayers

Movers

Stayers

   

p-value

Mean % bias

N treated

N control

p-value

Mean % bias

N treated

N control

p-value

Mean % bias

N treated

N control

2 NN-nc

Non-Exp

BM

<0.001

8.37

660

16891

0.034

5.08

473

2064

<0.001

17.65

187

14827

  

AM

0.999

2.51

660

1203

0.995

3.58

472

681

0.978

4.77

186

292

 

Exp

BM

<0.001

13.19

684

6676

<0.001

10.80

463

469

<0.001

17.37

221

6204

  

AM

0.975

2.83

684

1103

0.582

6.58

463

309

0.830

7.50

221

345

5NN-nc

Non-Exp

BM

<0.001

8.37

660

16891

0.034

5.08

473

2064

<0.001

17.65

187

14827

  

AM

1.000

2.24

660

2682

0.978

3.24

472

1233

0.860

6.93

187

651

 

Exp

BM

<0.001

13.19

684

6676

<0.001

10.80

463

469

<0.001

17.37

221

6204

  

AM

0.243

5.13

684

2250

0.001

8.77

463

418

0.799

7.38

221

737

2 NN-1/4c

Non-Exp

BM

<0.001

8.37

660

16891

0.034

5.08

473

2064

<0.001

17.65

187

14827

  

AM

0.996

2.63

657

1200

0.997

3.62

468

678

0.997

4.34

161

285

 

Exp

BM

<0.001

13.19

684

6676

<0.001

10.80

463

469

<0.001

17.37

221

6204

  

AM

0.993

2.49

673

1099

0.709

6.25

455

309

0.992

5.85

209

338

5NN-1/4c

Non-Exp

BM

<0.001

8.37

660

16891

0.034

5.08

473

2064

<0.001

17.65

187

14827

  

AM

1.000

2.29

657

2677

0.993

3.10

468

1231

0.993

4.73

162

634

 

Exp

BM

<0.001

13.19

684

6676

<0.001

10.80

463

469

<0.001

17.37

221

6204

  

AM

0.425

4.68

673

2245

0.004

8.44

455

418

0.982

5.55

209

727

  1. Notes: Non-exp = non exposed, Exp exposed, BM = Before matching, AM = After matching, 2NN-nc = 2 Nearest Neighbors-no caliper, 5NN-nc = 5 Nearest Neighbors-no caliper, 2NN-1/4c = 2 Nearest Neighbors-caliper equal to 1/4 of the SD of the estimated propensity score, 5NN-1/4c = 5 Nearest Neighbors-caliper equal to 1/4 of the SD of the estimated propensity score, Mean % |b i a s|= mean standardized % absolute bias, N treat = N of observations in the treated group, N ctrl = N of observations in the control group
  2. Mean standardized % absolute bias is the mean absolute bias of the % difference of the sample means in the treated and non-treated sub-samples as a percentage of the square root of the average of the sample variances in the treated and non-treated groups [34]
  3. p-values are the p-values from a likelihood-ratio test of the joint significance of all the regressors (before and after matching)
Back to article page

Health Economics Review

ISSN: 2191-1991

Contact us