11skip_if_not_installed(" lmerTest" )
22skip_if_not_installed(" pbkrtest" )
33skip_if_not_installed(" lme4" )
4+ skip_if_not_installed(" glmmTMB" )
45
56mtcars $ cyl <- as.factor(mtcars $ cyl )
6- model <- suppressMessages(lme4 :: lmer(mpg ~ as.factor(gear ) * hp + as.factor(am ) + wt + (1 | cyl ), data = mtcars ))
7- model2 <- suppressMessages(lmerTest :: lmer(mpg ~ as.factor(gear ) * hp + as.factor(am ) + wt + (1 | cyl ), data = mtcars ))
7+ model <- suppressMessages(lme4 :: lmer(
8+ mpg ~ as.factor(gear ) * hp + as.factor(am ) + wt + (1 | cyl ),
9+ data = mtcars
10+ ))
11+ model2 <- suppressMessages(lmerTest :: lmer(
12+ mpg ~ as.factor(gear ) * hp + as.factor(am ) + wt + (1 | cyl ),
13+ data = mtcars
14+ ))
15+ model3 <- suppressMessages(glmmTMB :: glmmTMB(
16+ mpg ~ as.factor(gear ) * hp + as.factor(am ) + wt + (1 | cyl ),
17+ data = mtcars ,
18+ REML = TRUE
19+ ))
820
921mp0 <- model_parameters(model , digits = 5 , effects = " fixed" )
1022mp1 <- model_parameters(model , digits = 5 , ci_method = " normal" , effects = " fixed" )
1123mp2 <- model_parameters(model , digits = 5 , ci_method = " s" , effects = " fixed" )
1224mp3 <- model_parameters(model , digits = 5 , ci_method = " kr" , effects = " fixed" )
1325mp4 <- model_parameters(model , digits = 5 , ci_method = " wald" , effects = " fixed" )
26+ mp5 <- model_parameters(model3 , digits = 5 , ci_method = " kr" , effects = " fixed" )
1427
1528test_that(" model_parameters, ci_method default (residual)" , {
1629 expect_equal(
1730 mp0 $ SE ,
18- c(
19- 2.77457 ,
20- 3.69574 ,
21- 3.521 ,
22- 0.01574 ,
23- 1.58514 ,
24- 0.86316 ,
25- 0.02973 ,
26- 0.01668
27- ),
31+ c(2.77457 , 3.69574 , 3.521 , 0.01574 , 1.58514 , 0.86316 , 0.02973 , 0.01668 ),
2832 tolerance = 1e-3
2933 )
3034 expect_equal(mp0 $ df , c(22 , 22 , 22 , 22 , 22 , 22 , 22 , 22 ), tolerance = 1e-3 )
3135 expect_equal(
3236 mp0 $ p ,
33- c(
34- 0 ,
35- 0.00258 ,
36- 0.14297 ,
37- 0.17095 ,
38- 0.84778 ,
39- 0.00578 ,
40- 0.00151 ,
41- 0.32653
42- ),
37+ c(0 , 0.00258 , 0.14297 , 0.17095 , 0.84778 , 0.00578 , 0.00151 , 0.32653 ),
4338 tolerance = 1e-3
4439 )
4540 expect_equal(
4641 mp0 $ CI_low ,
47- c(
48- 24.54722 ,
49- 4.89698 ,
50- - 1.95317 ,
51- - 0.05493 ,
52- - 2.97949 ,
53- - 4.42848 ,
54- - 0.16933 ,
55- - 0.05133
56- ),
42+ c(24.54722 , 4.89698 , - 1.95317 , - 0.05493 , - 2.97949 , - 4.42848 , - 0.16933 , - 0.05133 ),
5743 tolerance = 1e-3
5844 )
5945})
6046
6147test_that(" model_parameters, ci_method normal" , {
6248 expect_equal(
6349 mp1 $ SE ,
64- c(
65- 2.77457 ,
66- 3.69574 ,
67- 3.521 ,
68- 0.01574 ,
69- 1.58514 ,
70- 0.86316 ,
71- 0.02973 ,
72- 0.01668
73- ),
74- tolerance = 1e-3
75- )
76- expect_equal(
77- mp1 $ df ,
78- c(22 , 22 , 22 , 22 , 22 , 22 , 22 , 22 ),
50+ c(2.77457 , 3.69574 , 3.521 , 0.01574 , 1.58514 , 0.86316 , 0.02973 , 0.01668 ),
7951 tolerance = 1e-3
8052 )
53+ expect_equal(mp1 $ df , c(22 , 22 , 22 , 22 , 22 , 22 , 22 , 22 ), tolerance = 1e-3 )
8154 expect_equal(
8255 mp1 $ p ,
8356 c(0 , 0.00068 , 0.12872 , 0.15695 , 0.846 , 0.00224 , 0.00029 , 0.31562 ),
8457 tolerance = 1e-3
8558 )
8659 expect_equal(
8760 mp1 $ CI_low ,
88- c(
89- 24.86326 ,
90- 5.31796 ,
91- - 1.5521 ,
92- - 0.05313 ,
93- - 2.79893 ,
94- - 4.33015 ,
95- - 0.16595 ,
96- - 0.04943
97- ),
61+ c(24.86326 , 5.31796 , - 1.5521 , - 0.05313 , - 2.79893 , - 4.33015 , - 0.16595 , - 0.04943 ),
9862 tolerance = 1e-3
9963 )
10064})
10165
10266test_that(" model_parameters, ci_method satterthwaite" , {
10367 expect_equal(
10468 mp2 $ SE ,
105- c(
106- 2.77457 ,
107- 3.69574 ,
108- 3.521 ,
109- 0.01574 ,
110- 1.58514 ,
111- 0.86316 ,
112- 0.02973 ,
113- 0.01668
114- ),
69+ c(2.77457 , 3.69574 , 3.521 , 0.01574 , 1.58514 , 0.86316 , 0.02973 , 0.01668 ),
11570 tolerance = 1e-3
11671 )
11772 expect_equal(mp2 $ df , c(24 , 24 , 24 , 24 , 24 , 24 , 24 , 24 ), tolerance = 1e-3 )
11873 expect_equal(
11974 mp2 $ p ,
120- c(
121- 0 ,
122- 0.00236 ,
123- 0.14179 ,
124- 0.16979 ,
125- 0.84763 ,
126- 0.00542 ,
127- 0.00136 ,
128- 0.32563
129- ),
75+ c(0 , 0.00236 , 0.14179 , 0.16979 , 0.84763 , 0.00542 , 0.00136 , 0.32563 ),
13076 tolerance = 1e-3
13177 )
13278 expect_equal(
13379 mp2 $ CI_low ,
134- c(
135- 24.57489 ,
136- 4.93385 ,
137- - 1.91805 ,
138- - 0.05477 ,
139- - 2.96368 ,
140- - 4.41987 ,
141- - 0.16904 ,
142- - 0.05117
143- ),
80+ c(24.57489 , 4.93385 , - 1.91805 , - 0.05477 , - 2.96368 , - 4.41987 , - 0.16904 , - 0.05117 ),
14481 tolerance = 1e-3
14582 )
14683})
14784
14885test_that(" model_parameters, ci_method kenward" , {
14986 expect_equal(
15087 mp3 $ SE ,
151- c(
152- 2.97608 ,
153- 6.10454 ,
154- 3.98754 ,
155- 0.02032 ,
156- 1.60327 ,
157- 0.91599 ,
158- 0.05509 ,
159- 0.01962
160- ),
88+ c(2.97608 , 6.10454 , 3.98754 , 0.02032 , 1.60327 , 0.91599 , 0.05509 , 0.01962 ),
16189 tolerance = 1e-3
16290 )
16391 expect_equal(
16492 mp3 $ df ,
165- c(
166- 19.39553 ,
167- 5.27602 ,
168- 23.57086 ,
169- 8.97297 ,
170- 22.7421 ,
171- 23.76299 ,
172- 2.72622 ,
173- 22.82714
174- ),
93+ c(19.39553 , 5.27602 , 23.57086 , 8.97297 , 22.7421 , 23.76299 , 2.72622 , 22.82714 ),
17594 tolerance = 1e-3
17695 )
17796 expect_equal(
17897 mp3 $ p ,
179- c(
180- 0 ,
181- 0.09176 ,
182- 0.19257 ,
183- 0.30147 ,
184- 0.84942 ,
185- 0.00828 ,
186- 0.15478 ,
187- 0.40248
188- ),
98+ c(0 , 0.09176 , 0.19257 , 0.30147 , 0.84942 , 0.00828 , 0.15478 , 0.40248 ),
18999 tolerance = 1e-3
190100 )
191101 expect_equal(
192102 mp3 $ CI_low ,
193- c(
194- 24.08091 ,
195- - 2.887 ,
196- - 2.88887 ,
197- - 0.06828 ,
198- - 3.01082 ,
199- - 4.5299 ,
200- - 0.29339 ,
201- - 0.05735
202- ),
103+ c(24.08091 , - 2.887 , - 2.88887 , - 0.06828 , - 3.01082 , - 4.5299 , - 0.29339 , - 0.05735 ),
203104 tolerance = 1e-3
204105 )
205106})
206107
207108test_that(" model_parameters, ci_method wald (t)" , {
208109 expect_equal(
209110 mp4 $ SE ,
210- c(
211- 2.77457 ,
212- 3.69574 ,
213- 3.521 ,
214- 0.01574 ,
215- 1.58514 ,
216- 0.86316 ,
217- 0.02973 ,
218- 0.01668
219- ),
111+ c(2.77457 , 3.69574 , 3.521 , 0.01574 , 1.58514 , 0.86316 , 0.02973 , 0.01668 ),
220112 tolerance = 1e-3
221113 )
222114 expect_equal(mp4 $ df , c(22 , 22 , 22 , 22 , 22 , 22 , 22 , 22 ), tolerance = 1e-3 )
223115 expect_equal(
224116 mp4 $ p ,
225- c(
226- 0 ,
227- 0.00258 ,
228- 0.14297 ,
229- 0.17095 ,
230- 0.84778 ,
231- 0.00578 ,
232- 0.00151 ,
233- 0.32653
234- ),
117+ c(0 , 0.00258 , 0.14297 , 0.17095 , 0.84778 , 0.00578 , 0.00151 , 0.32653 ),
235118 tolerance = 1e-3
236119 )
237120 expect_equal(
238121 mp4 $ CI_low ,
239- c(
240- 24.54722 ,
241- 4.89698 ,
242- - 1.95317 ,
243- - 0.05493 ,
244- - 2.97949 ,
245- - 4.42848 ,
246- - 0.16933 ,
247- - 0.05133
248- ),
122+ c(24.54722 , 4.89698 , - 1.95317 , - 0.05493 , - 2.97949 , - 4.42848 , - 0.16933 , - 0.05133 ),
249123 tolerance = 1e-3
250124 )
251125})
@@ -268,8 +142,10 @@ test_that("model_parameters, satterthwaite Conf Int-1", {
268142
269143test_that(" model_parameters, satterthwaite Conf Int-2" , {
270144 coef.table <- as.data.frame(summary(model2 )$ coefficients )
271- coef.table $ CI_low <- coef.table $ Estimate - (coef.table $ " Std. Error" * qt(0.975 , df = coef.table $ df ))
272- coef.table $ CI_high <- coef.table $ Estimate + (coef.table $ " Std. Error" * qt(0.975 , df = coef.table $ df ))
145+ coef.table $ CI_low <- coef.table $ Estimate -
146+ (coef.table $ " Std. Error" * qt(0.975 , df = coef.table $ df ))
147+ coef.table $ CI_high <- coef.table $ Estimate +
148+ (coef.table $ " Std. Error" * qt(0.975 , df = coef.table $ df ))
273149
274150 expect_equal(mp2 $ CI_low , coef.table $ CI_low , tolerance = 1e-4 )
275151 expect_equal(mp2 $ CI_high , coef.table $ CI_high , tolerance = 1e-4 )
0 commit comments