Skip to main content

Table 3 temperature effects and AR estimates from GAM and GAMAR(4)

From: Using a generalized additive model with autoregressive terms to study the effects of daily temperature on mortality

 

GAM

 

GAMAR(4)

 

Estimate

Se

Z

Pr(>|z|)

Estimate

Se

Z

Pr(>|z|)

ns(temp1,5)1

0.2443

0.0212

−11.5349

0.0000

−0.1947

0.0254

−7.6621

0.0000

ns(temp1,5)2

0.2668

0.0281

−9.4929

0.0000

−0.2290

0.0322

−7.1108

0.0000

ns(temp1,5)3

0.3278

0.0258

−12.6878

0.0000

−0.2989

0.0290

−10.3113

0.0000

ns(temp1,5)4

0.3422

0.0495

−6.9160

0.0000

−0.2898

0.0568

−5.1052

0.0000

ns(temp1,5)5

0.2254

0.0283

−7.9578

0.0000

−0.2569

0.0320

−8.0179

0.0000

ns(temp2,4)1

0.2355

0.0197

−11.9372

0.0000

−0.1833

0.0248

−7.3986

0.0000

ns(temp2,4)2

0.1599

0.0225

−7.1233

0.0000

−0.1430

0.0263

−5.4312

0.0000

ns(temp2,4)3

0.2472

0.0443

−5.5748

0.0000

−0.1978

0.0526

−3.7603

0.0002

ns(temp2,4)4

0.0752

0.0251

−3.0007

0.0027

−0.0559

0.0297

−1.8838

0.0596

AR1

    

0.1426

0.0211

6.7521

0.0000

AR2

    

0.0773

0.0223

3.4664

0.0005

AR3

    

0.1179

0.0221

5.3466

0.0000

AR4

    

0.1259

0.0223

5.6398

0.0000

  1. Estimate: estimate for a parameter.
  2. Se: Standard Error for a parameter.
  3. Z=Estimate/Se, which approximately follows N(0,1).
  4. Pr(>|z|): the probability of obtaining Z at least as extreme as the one that was actually observed, assuming that the true value is 0. This time P value is derived from N(0,1).
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us