Skip to main content

Table 14 Inverse-variance weighted regression analyses – never smokers

From: Indirectly estimated absolute lung cancer mortality rates by smoking status and histological type based on a systematic review

 

Males

Females

 

All

Squamous

Adeno

All

Squamous

Adeno

Overall deviance (d.f.)

1525 (128)

196 (42)

254 (42)

2766 (90)

319 (37)

1040 (37)

Drop in deviance and p valuea from including:

      

Trendb (1 d.f.)

324***

4

50**

612***

1

185**

Continentc (3 d.f.)

687***

47*

127***

2283***

205***

832***

Trend given continent (1 d.f.)

81***

1

30**

57**

27**

18(*)

Continent given trend (3 d.f.)

445***

44*

107***

1729***

231***

665***

Residual devianced (d.f.)

756 (124)

148 (38)

97 (38)

426 (86)

87 (33)

190 (33)

Deviance explained

50.4%

24.5%

61.8%

84.6%

72.7%

81.7%

Means (SEs)d:

      

Constant

4.24 (0.18)

3.74 (0.49)

2.89 (0.43)

4.10 (0.12)

3.77 (0.28)

3.59 (0.31)

Trend

0.15 (0.04)

0.04 (0.11)

0.35 (0.10)

0.09 (0.03)

-0.21 (0.07)

0.14 (0.08)

Asia (not China)

-0.97 (0.18)

-1.44 (0.63)

-0.35 (0.31)

-0.70 (0.08)

-1.28 (0.29)

-0.49 (0.15)

Europe

-0.42 (0.12)

-0.93 (0.35)

-1.33 (0.26)

-1.04 (0.08)

-0.85 (0.19)

-1.32 (0.21)

America

-0.73 (0.10)

-0.83 (0.27)

-1.08 (0.19)

-1.12 (0.07)

-1.38 (0.15)

-1.27 (0.12)

Drop in deviance and p valuea from adding:e

      

10 level regionf (6 d.f.)

103**

37

21

43

28(*)

21

5 level periodg (3 d.f.)

111***

34*

12

11

10

19

Interactions of trend and continent (3 d.f.)

22

7

15

55

9

7

  1. a p values are coded as *** p < 0.001, ** p < 0.01, * p < 0.05, (*) p < 0.1. If no code is shown p ≥ 0.1. d.f. = degrees of freedom.
  2. b Linear trend in period scoring 1 = 1930–60, 2 = 1961–70, 3 = 1971–80, 4 = 1981–90, 5 = 1991–99.
  3. c Continent defined as China, Asia (not China), Europe or America.
  4. d For model including linear trend in period and continent. Note that estimates for Asia (not China), Europe and America are relative to rates for China.
  5. e Drop in deviance from adding the specific variable to the model including linear trend in period and continent.
  6. f Levels as shown in Tables 10, 11, 12 and 13.
  7. g This tests for departure from linear trend.