Skip to main content

Table 2 Simulation experiment results: empirical squared error

From: Association of longitudinal pet ownership with wheezing in 3-year-old children using the distributed lag model: the Japan Environment and Children’s Study

time

γ=0

γ=0.975

γ=0.9999

Single

Multi

DLM

Single

Multi

DLM

Single

Multi

DLM

Scenario 1

 6

6.9

7.0

6.4

6.1

12.5

8.2

6.1

51.7

18.2

 12

7.1

7.2

4.4

6.1

15.2

4.4

6.0

61.3

12.1

 18

7.0

7.1

4.2

6.1

15.4

4.3

6.1

62.3

9.2

 24

7.4

7.4

3.6

6.0

14.9

3.5

6.1

61.5

7.8

 30

7.2

7.3

3.4

6.0

14.8

3.4

6.1

60.0

8.4

 36

7.4

7.3

3.7

6.1

14.9

3.9

6.1

63.6

9.2

 42

7.4

7.4

3.8

6.0

15.3

4.0

6.1

63.4

9.1

 48

7.1

7.1

3.5

6.0

15.1

3.1

6.1

59.4

8.4

 54

7.2

7.2

3.6

6.2

15.6

3.2

6.1

62.7

10.2

 60

6.9

7.0

5.7

6.0

12.4

7.1

6.1

51.9

17.5

Scenario 2

 6

7.2

7.2

6.7

6.5

12.8

8.5

6.1

51.3

17.4

 12

7.2

7.3

4.4

6.3

14.6

4.3

6.1

61.8

12.0

 18

7.2

7.2

4.2

6.3

14.9

4.4

6.1

61.0

9.2

 24

7.0

7.0

3.6

6.3

15.7

3.6

6.1

62.4

7.7

 30

7.2

7.2

3.4

6.4

15.2

3.4

6.1

61.7

8.4

 36

7.2

7.2

3.7

6.3

15.3

3.8

6.1

64.9

9.4

 42

7.1

7.1

3.8

6.3

15.2

3.8

6.1

61.6

9.3

 48

6.8

6.8

3.5

6.3

15.0

3.1

6.1

63.2

8.3

 54

7.5

7.6

3.9

6.3

15.2

3.3

6.0

62.5

9.8

 60

7.4

7.4

6.3

6.4

12.6

7.2

6.0

50.8

17.4

Scenario 3

 6

8.2

8.2

7.6

7.3

14.6

9.8

7.5

56.9

21.4

 12

8.0

8.0

5.1

7.3

16.9

5.1

7.5

67.9

14.5

 18

8.1

8.1

4.8

7.4

17.2

5.2

7.5

67.1

11.1

 24

7.8

7.8

4.0

7.4

17.4

4.2

7.4

69.4

9.7

 30

7.9

7.9

3.7

7.5

17.6

4.0

7.5

68.9

10.6

 36

7.6

7.6

4.0

7.3

17.4

4.6

7.5

68.3

11.6

 42

7.8

7.8

4.1

7.1

17.5

4.6

7.5

67.9

11.3

 48

7.9

8.0

3.9

7.2

17.6

3.6

7.4

67.7

10.0

 54

8.0

8.1

4.2

7.3

16.9

3.7

7.4

67.5

12.4

 60

8.2

8.2

6.7

7.2

14.4

8.5

7.4

56.5

22.2

  1. Empirical standard errors rounded to the fourth place and multiplied by \({10}^{2}\)
  2. Single, the exposure at each time point is used in a separate regression model; Multi, the exposures at each time point are simultaneously entered into a single regression model; DLM, the Distributed Lag Model
  3. γ represents the correlation used to generate data between exposures.
  4. Scenario 1: Exposure effects are constant regardless of time point. Scenario 2: Exposure effects’ magnitude is an upward convex quadratic curve. Scenario 3: Exposure effects exist only from \(t = 36 \text{ to } 47\)