Table 3

Index group means and matching estimator results for days plucking tea and non-plucking days for women

Duration on ART

N

Days Plucking (IG Mean)\1

Estimated Mean Difference

(IG – CG)\1

P > |z|\2

95% CI LL\2

95% CI UL\2

Days Non-Plucking Tasks (IG Mean)

Estimated Mean Difference

(IG – CG)\1

P > |z|\2

95% CI LL\2

95% CI UL/2


-24

56

15.46

-1.75

0.24

-4.68

1.19

5.09

1.48

0.20

-0.79

3.75

-23

56

15.61

-1.31

0.34

-3.99

1.37

4.50

0.17

0.87

-1.81

2.15

-22

56

15.59

-1.35

0.36

-4.27

1.57

4.43

0.94

0.43

-1.39

3.27

-21

56

16.68

-1.17

0.44

-4.15

1.82

2.54

-0.77

0.46

-2.77

1.24

-20

56

16.93

-0.49

0.72

-3.18

2.21

3.59

-0.68

0.51

-2.69

1.32

-19

56

14.07

-2.77

0.05

-5.56

0.03

4.27

0.03

0.98

-2.22

2.27

-18

56

15.52

-1.84

0.20

-4.67

0.98

6.02

2.01

0.10

-0.35

4.37

-17

56

17.25

-0.06

0.97

-2.66

2.55

3.68

0.27

0.78

-1.63

2.18

-16

56

17.48

0.18

0.88

-2.26

2.63

4.84

1.03

0.34

-1.09

3.15

-15

56

16.77

-0.11

0.94

-2.72

2.50

3.96

0.07

0.95

-2.05

2.19

-14

56

14.16

-3.49

0.01

-6.11

-0.86

5.32

1.75

0.12

-0.46

3.96

-13

56

16.88

-0.44

0.75

-3.11

2.23

5.30

1.48

0.21

-0.85

3.80

-12

56

16.13

-1.65

0.24

-4.41

1.11

4.21

1.21

0.28

-0.96

3.38

-11

56

16.91

-1.79

0.21

-4.60

1.02

3.63

0.85

0.43

-1.28

2.98

-10

56

16.48

-2.26

0.11

-5.00

0.48

3.95

1.26

0.26

-0.92

3.43

-9

56

14.23

-4.82

0.00

-7.69

-1.95

4.63

2.12

0.08

-0.25

4.50

-8

56

14.21

-5.39

0.00

-8.16

-2.62

5.54

2.66

0.02

0.41

4.91

-7

56

14.07

-4.68

0.00

-7.72

-1.64

4.39

2.19

0.04

0.06

4.32

-6

56

14.23

-4.99

0.00

-7.72

-2.27

4.07

1.36

0.18

-0.60

3.32

-5

56

13.95

-5.21

0.00

-8.09

-2.33

5.18

2.55

0.02

0.45

4.65

-4

56

13.98

-4.77

0.00

-7.40

-2.15

5.75

2.87

0.01

0.65

5.09

-3

56

13.89

-3.32

0.03

-6.24

-0.40

4.80

1.96

0.07

-0.19

4.11

-2

56

14.36

-3.37

0.02

-6.20

-0.54

4.39

2.34

0.02

0.31

4.38

-1

56

14.20

-4.61

0.00

-7.21

-2.01

3.88

1.69

0.08

-0.21

3.59

0

56

6.00

-13.55

0.00

-15.58

-11.53

4.05

2.04

0.02

0.34

3.75

1

56

7.45

-10.90

0.00

-13.50

-8.30

4.70

2.60

0.01

0.78

4.42

2

56

9.27

-8.14

0.00

-10.96

-5.32

6.70

3.98

0.00

1.60

6.35

3/3

55

9.73

-8.84

0.00

-11.36

-6.32

6.38

3.09

0.01

0.82

5.36

4

54

11.65

-6.63

0.00

-9.45

-3.82

6.63

3.56

0.00

1.31

5.80

5

54

10.44

-6.35

0.00

-9.24

-3.45

6.59

3.95

0.00

1.94

5.96

6

54

11.83

-5.93

0.00

-8.60

-3.25

6.43

3.66

0.00

1.52

5.81

7

54

13.19

-5.34

0.00

-7.96

-2.73

5.91

3.89

0.00

1.70

6.08

8

54

12.65

-6.14

0.00

-8.59

-3.69

5.93

4.17

0.00

2.21

6.13

9

54

12.43

-5.77

0.00

-8.42

-3.12

6.22

4.44

0.00

2.34

6.54

10

54

10.93

-6.62

0.00

-9.41

-3.84

6.91

4.19

0.00

2.00

6.38

11

54

13.33

-4.99

0.00

-7.65

-2.33

5.54

2.98

0.01

0.92

5.04

12

54

12.85

-5.69

0.00

-8.43

-2.95

5.61

2.68

0.02

0.49

4.86


1/ / IG = index group, and CG = matching comparison group. The estimated mean difference is the bias-adjusted sample average treatment effect on the treated using nearest the neighbor matching estimator nnmatch in Stata 10, with 4 comparison workers matched to each index worker based on age, months of work experience, and gang.

2/ p-value for a z-test that mean difference = 0, rounded to two digits. 95% CI LL and UL are the lower and upper levels of the 95% confidence interval for the estimated average treatment effect on the treated.

3/ One index worker retired at the end of month 2 and month 3.

Larson et al. BMC Public Health 2009 9:240   doi:10.1186/1471-2458-9-240

Open Data