Debian Codegraph @

tests/testthat/test_mlm.R

raw
1 context("mlm objects")
2 set.seed(20190513)
3
4 n <- nrow(iris)
5 lm_fit <- lm(cbind(Sepal.Length, Sepal.Width) ~ Species + Petal.Length, data = iris)
6 lm_A_fit <- lm(Sepal.Length ~ Species + Petal.Length, data = iris)
7 lm_B_fit <- lm(Sepal.Width ~ Species + Petal.Length, data = iris)
8 WLS_fit <- lm(cbind(Sepal.Length, Sepal.Width) ~ Species + Petal.Length, data = iris, weights = Petal.Width)
9 CR_types <- paste0("CR",0:4)
10
11 test_that("bread works", {
12
13 expect_equal(bread.mlm(lm_fit), sandwich:::bread.mlm(lm_fit))
14
15 y <- with(iris, as.vector(rbind(Sepal.Length, Sepal.Width)))
16 cluster <- rep(rownames(iris), each = ncol(residuals(lm_fit)))
17 expect_true(check_bread(lm_fit, cluster = cluster, y = y))
18
19 expect_true(check_bread(WLS_fit, cluster = cluster, y = y))
20
21 })
22
23
24 test_that("CR2 and CR4 are target-unbiased", {
25 expect_true(check_CR(lm_fit, vcov = "CR2"))
26 expect_true(check_CR(WLS_fit, vcov = "CR2"))
27 expect_true(check_CR(lm_fit, vcov = "CR4"))
28 expect_true(check_CR(WLS_fit, vcov = "CR4"))
29 })
30
31 test_that("vcovCR is mostly equivalent to vcovHC when clusters are all of size 1", {
32 library(sandwich, quietly=TRUE)
33 CR_mats <- sapply(c("CR0","CR2","CR3","CR1","CR1p","CR1S"),
34 function(t) as.matrix(vcovCR(lm_fit, type = t)),
35 simplify = FALSE, USE.NAMES = TRUE)
36 HC_mats <- sapply(c("HC0","HC2","HC3","HC1"),
37 function(t) vcovHC(lm_fit, type = t),
38 simplify = FALSE, USE.NAMES = TRUE)
39
40 expect_equal(CR_mats$CR0, HC_mats$HC0)
41 expect_equal(CR_mats$CR2, HC_mats$HC2)
42 expect_equal(CR_mats$CR3, HC_mats$HC3)
43
44 J <- nobs(lm_fit)
45 p <- ncol(model.matrix(lm_fit))
46 N <- nrow(model_matrix(lm_fit))
47 expect_equal(CR_mats$CR1 * (J - 1), HC_mats$HC1 * (J - p))
48 expect_equal(CR_mats$CR1p * (J - 2 * p), HC_mats$HC1 * (J - p))
49 expect_equal(CR_mats$CR1S * (J - 1) * (N - 2 * p) / (N - 1), HC_mats$HC1 * (J - p))
50
51 HC_A_mats <- sapply(c("HC0","HC2","HC3"),
52 function(t) vcovHC(lm_A_fit, type = t),
53 simplify = FALSE, USE.NAMES = TRUE)
54 HC_B_mats <- sapply(c("HC0","HC2","HC3"),
55 function(t) vcovHC(lm_B_fit, type = t),
56 simplify = FALSE, USE.NAMES = TRUE)
57 expect_equal(CR_mats$CR0[1:p,1:p], HC_A_mats$HC0, check.attributes = FALSE)
58 expect_equal(CR_mats$CR2[1:p,1:p], HC_A_mats$HC2, check.attributes = FALSE)
59 expect_equal(CR_mats$CR3[1:p,1:p], HC_A_mats$HC3, check.attributes = FALSE)
60 expect_equal(CR_mats$CR0[p + 1:p,p + 1:p], HC_B_mats$HC0, check.attributes = FALSE)
61 expect_equal(CR_mats$CR2[p + 1:p,p + 1:p], HC_B_mats$HC2, check.attributes = FALSE)
62 expect_equal(CR_mats$CR3[p + 1:p,p + 1:p], HC_B_mats$HC3, check.attributes = FALSE)
63 })
64
65 test_that("mlm is equivalent to lm with long data.", {
66 iris_long <- reshape(iris, c("Sepal.Length","Sepal.Width"),
67 direction = "long", times = "outcome")
68 iris_long$outcome <- paste0("Sepal.", iris_long$time)
69
70 lm_long <- lm(Sepal ~ 0 + outcome + outcome:Species + outcome:Petal.Length, data = iris_long)
71 i <- order(rep(1:2, 4))
72 expect_equal(coef_CS(lm_fit), coef(lm_long)[i], check.attributes = FALSE)
73
74 CR_fit <- lapply(CR_types, function(x) as.matrix(vcovCR(lm_fit, type = x)))
75 CR_long <- lapply(CR_types, function(x) vcovCR(lm_long, type = x, cluster = iris_long$id)[i,i])
76 expect_equivalent(CR_fit, CR_long)
77
78 test_fit <- lapply(CR_types, function(x) coef_test(lm_fit, vcov = x, test = "All", p_values = FALSE))
79 test_long <- lapply(CR_types, function(x) coef_test(lm_long, vcov = x, cluster = iris_long$id, test = "All", p_values = FALSE)[i,])
80 compare_ttests(test_fit, test_long)
81
82 CR_fit <- lapply(CR_types, function(x) as.matrix(vcovCR(lm_fit, type = x, cluster = iris$Petal.Length)))
83 CR_long <- lapply(CR_types, function(x) vcovCR(lm_long, type = x, cluster = iris_long$Petal.Length)[i,i])
84 expect_equivalent(CR_fit, CR_long)
85
86 test_fit <- lapply(CR_types, function(x) coef_test(lm_fit, vcov = x, test = "All", p_values = FALSE))
87 test_long <- lapply(CR_types, function(x) coef_test(lm_long, vcov = x, cluster = iris_long$id, test = "All", p_values = FALSE)[i,])
88 compare_ttests(test_fit, test_long)
89
90 })
91
92 test_that("Order doesn't matter.",{
93
94 skip_on_cran()
95 check_sort_order(WLS_fit, iris)
96
97 })
98
99 test_that("clubSandwich works with dropped covariates", {
100 dat_miss <- iris
101 dat_miss$Petal.Length[sample.int(n, size = round(n / 10))] <- NA
102 lm_dropped <- update(lm_fit, data = dat_miss)
103 dat_complete <- subset(dat_miss, !is.na(Petal.Length))
104 lm_complete <- update(lm_fit, data = dat_complete)
105
106 CR_drop <- lapply(CR_types, function(x) vcovCR(lm_dropped, type = x))
107 CR_complete <- lapply(CR_types, function(x) vcovCR(lm_complete, type = x))
108 expect_equal(CR_drop, CR_complete)
109
110 test_drop <- lapply(CR_types, function(x) coef_test(lm_dropped, vcov = x, test = "All", p_values = FALSE))
111 test_complete <- lapply(CR_types, function(x) coef_test(lm_complete, vcov = x, test = "All", p_values = FALSE))
112 expect_equal(test_drop, test_complete)
113 })
114
115
116 test_that("clubSandwich works with dropped outcomes", {
117 dat_miss <- iris
118 n <- nrow(dat_miss)
119 dat_miss$Sepal.Length[sample.int(n, size = round(n / 10))] <- NA
120 dat_miss$Sepal.Width[sample.int(n, size = round(n / 10))] <- NA
121 lm_dropped <- update(lm_fit, data = dat_miss)
122 dat_complete <- subset(dat_miss, !is.na(Sepal.Length) & !is.na(Sepal.Width))
123 lm_complete <- update(lm_fit, data = dat_complete)
124
125 CR_drop <- lapply(CR_types, function(x) vcovCR(lm_dropped, type = x))
126 CR_complete <- lapply(CR_types, function(x) vcovCR(lm_complete, type = x))
127 expect_equal(CR_drop, CR_complete)
128
129 test_drop <- lapply(CR_types, function(x) coef_test(lm_dropped, vcov = x, test = "All", p_values = FALSE))
130 test_complete <- lapply(CR_types, function(x) coef_test(lm_complete, vcov = x, test = "All", p_values = FALSE))
131 compare_ttests(test_drop, test_complete)
132 })
133
134 test_that("clubSandwich works with dropped outcomes, covariates, and weights", {
135 dat_miss <- iris
136 n <- nrow(dat_miss)
137 dat_miss$Sepal.Length[sample.int(n, size = round(n / 5))] <- NA
138 dat_miss$Sepal.Width[sample.int(n, size = round(n / 5))] <- NA
139 dat_miss$Petal.Length[sample.int(n, size = round(n / 5))] <- NA
140 dat_miss$Petal.Width[sample.int(n, size = round(n / 5))] <- NA
141 WLS_dropped <- update(WLS_fit, data = dat_miss)
142 dat_complete <- subset(dat_miss,
143 !is.na(Petal.Length) & !is.na(Petal.Width) &
144 !is.na(Sepal.Length) & !is.na(Sepal.Width))
145 WLS_complete <- update(WLS_fit, data = dat_complete)
146
147 CR_drop <- lapply(CR_types, function(x) vcovCR(WLS_dropped, type = x))
148 CR_complete <- lapply(CR_types, function(x) vcovCR(WLS_complete, type = x))
149 expect_equal(CR_drop, CR_complete)
150
151 test_drop <- lapply(CR_types, function(x) coef_test(WLS_dropped, vcov = x, test = "All", p_values = FALSE))
152 test_complete <- lapply(CR_types, function(x) coef_test(WLS_complete, vcov = x, test = "All", p_values = FALSE))
153 expect_equal(test_drop, test_complete)
154 })
155
156 test_that("weight scale doesn't matter", {
157
158 lm_fit_w <- update(lm_fit, weights = rep(10, nrow(iris)))
159
160 unweighted_fit <- lapply(CR_types, function(x) vcovCR(lm_fit, type = x))
161 weighted_fit <- lapply(CR_types, function(x) vcovCR(lm_fit_w, type = x))
162
163 expect_equal(lapply(unweighted_fit, as.matrix),
164 lapply(weighted_fit, as.matrix))
165
166 target <- rep(1 + rpois(nrow(iris), lambda = 8), each = ncol(residuals(lm_fit)))
167 unweighted_fit <- lapply(CR_types, function(x) vcovCR(lm_fit, type = x, target = target))
168 weighted_fit <- lapply(CR_types, function(x) vcovCR(lm_fit_w, type = x, target = target * 15))
169
170 expect_equal(lapply(unweighted_fit, as.matrix),
171 lapply(weighted_fit, as.matrix))
172
173 })
174
175 test_that("clubSandwich works with weights of zero.", {
176
177 data("LifeCycleSavings", package = "datasets")
178 n_life <- nrow(LifeCycleSavings)
179
180 LifeCycleSavings$cl <- substr(rownames(LifeCycleSavings), 1, 1)
181 table(LifeCycleSavings$cl)
182 LifeCycleSavings$wt <- rpois(nrow(LifeCycleSavings), lambda = 0.8)
183 table(LifeCycleSavings$wt)
184
185 lm_full <- lm(cbind(dpi, ddpi) ~ pop15 + pop75 + sr, data = LifeCycleSavings, weights = wt)
186 LCS_sub <- subset(LifeCycleSavings, wt > 0)
187 lm_sub <- lm(cbind(dpi, ddpi) ~ pop15 + pop75 + sr, data = LCS_sub, weights = wt)
188
189 CR_full <- lapply(CR_types, function(x) vcovCR(lm_full, type = x))
190 CR_sub <- lapply(CR_types, function(x) vcovCR(lm_sub, type = x))
191 expect_equal(CR_full, CR_sub, check.attributes = FALSE)
192
193 test_full <- lapply(CR_types, function(x) coef_test(lm_full, vcov = x, test = c("z","naive-t","Satterthwaite"), p_values = TRUE))
194 test_sub <- lapply(CR_types, function(x) coef_test(lm_sub, vcov = x, test = c("z","naive-t","Satterthwaite"), p_values = TRUE))
195 expect_equal(test_full, test_sub, check.attributes = FALSE)
196
197 CR_full <- lapply(CR_types, function(x) vcovCR(lm_full, cluster = LifeCycleSavings$cl, type = x))
198 CR_sub <- lapply(CR_types, function(x) vcovCR(lm_sub, cluster = LCS_sub$cl, type = x))
199 expect_equal(CR_full, CR_sub, check.attributes = FALSE)
200
201 test_full <- lapply(CR_types, function(x) coef_test(lm_full, vcov = x, cluster = LifeCycleSavings$cl, test = c("z","naive-t","Satterthwaite"), p_values = TRUE))
202 test_sub <- lapply(CR_types, function(x) coef_test(lm_sub, vcov = x, cluster = LCS_sub$cl, test = c("z","naive-t","Satterthwaite"), p_values = TRUE))
203 expect_equal(test_full, test_sub, check.attributes = FALSE)
204
205 dat_miss <- LifeCycleSavings
206 miss_indicator <- sample.int(n_life, size = round(n_life / 5))
207 dat_miss$pop15[miss_indicator] <- NA
208 dat_miss$cl[miss_indicator] <- NA
209 with(dat_miss, table(wt, is.na(pop15)))
210
211 lm_dropped <- lm(cbind(dpi, ddpi) ~ pop15 + pop75 + sr, data = dat_miss, weights = wt)
212 dat_complete <- subset(dat_miss, !is.na(pop15))
213 lm_complete <- lm(cbind(dpi, ddpi) ~ pop15 + pop75 + sr, data = dat_complete, weights = wt)
214
215 CR_drop <- lapply(CR_types, function(x) vcovCR(lm_dropped, type = x))
216 CR_complete <- lapply(CR_types, function(x) vcovCR(lm_complete, type = x))
217 expect_equal(CR_drop, CR_complete)
218
219 test_drop <- lapply(CR_types, function(x) coef_test(lm_dropped, vcov = x, test = "All", p_values = FALSE))
220 test_complete <- lapply(CR_types, function(x) coef_test(lm_complete, vcov = x, test = "All", p_values = FALSE))
221 expect_equal(test_drop, test_complete)
222
223 CR_drop <- lapply(CR_types, function(x) vcovCR(lm_dropped, cluster = dat_miss$cl, type = x))
224 CR_complete <- lapply(CR_types, function(x) vcovCR(lm_complete, cluster = dat_complete$cl, type = x))
225 expect_equal(CR_drop, CR_complete)
226
227 test_drop <- lapply(CR_types, function(x) coef_test(lm_dropped, vcov = x, cluster = dat_miss$cl, test = "All", p_values = FALSE))
228 test_complete <- lapply(CR_types, function(x) coef_test(lm_complete, vcov = x, cluster = dat_complete$cl, test = "All", p_values = FALSE))
229 expect_equal(test_drop, test_complete)
230
231 })