R 时间序列模拟（多次观测）

我试图用多个观测值来模拟一些时间序列数据。我确实想为每个人在他们自己的时间段内设置自动相关（r=.7）。时间段的大小不同：

size这与您打算做的接近吗？我不确定
id
代表什么

size <- c(10, 50, 100, 200, 300, 400, 440, 500)
set.seed(420)
results_a <- matrix(NA, nrow = max(size), ncol = length(size))
results_b <- matrix(NA, nrow = max(size), ncol = length(size))
for(i in 1:ncol(results)){
  a <- rnorm(size[i])
  ar.epsilon <- arima.sim(list(order = c(1,0,0), ar = 0.7), n = size[i], sd=20)
  b = size[i]*a + ar.epsilon
  results_id[]
  results_a[c(1:size[i]), i] <- a
  results_b[c(1:size[i]), i] <- b
}

colnames(results_a) <- paste0('id.a.', size)
colnames(results_b) <- paste0('id.b.', size)

result_final <- data.frame(results_a, results_b)
result_final <- result_final[, c(1, 9, 2, 10, 3, 11, 4, 12, 5, 13, 6, 14, 7, 15, 8, 16)]
head(result_final, 5)
     id.a.10    id.b.10    id.a.50    id.b.50    id.a.100  id.b.100   id.a.200  id.b.200   id.a.300   id.b.300
1  0.2677109   4.135141 -1.2479756 -117.59951  0.98359034  62.78846 -0.4334481 -80.73017 -1.2820512 -376.21611
2 -0.9367075 -31.289128 -2.8949090 -177.02084 -0.09517645 -24.60170 -0.2134596 -24.28731 -0.2437892 -105.31801
3  0.5962061  -2.716978  1.1995795   68.50393 -1.13753051 -91.86198  1.2898376 291.26922  0.5395736  118.88174
4 -0.3120436 -22.395355  0.2200063   55.90104 -0.23305847 -32.09204  0.7150280 168.96521 -0.1842391  -63.82123
5  0.3979791 -33.284591  0.9722208  102.26825 -0.45663605 -58.60094  0.4104681  70.51101  1.2605879  373.00674
     id.a.400    id.b.400  id.a.440  id.b.440   id.a.500  id.b.500
1 -0.81734653 -354.499825  1.416543  649.6649 -0.7634678 -399.9059
2  1.77813114  670.127238  0.301712  149.6443  0.4791241  210.1626
3 -1.13121629 -501.422591  2.129244  950.8821  1.4002161  710.6371
4  0.08281154   -2.199712  1.321002  610.5567  0.2423353  140.2799
5  0.68390623  262.957092 -1.161112 -497.6224 -0.3141071 -179.2746

size不必使用sapply（），也可以使用map\u dfr（）或replicate（）是的，这就是我要找的。非常感谢。
size <- c(10, 50, 100, 200, 300, 400, 440, 500)
set.seed(420)
results_a <- matrix(NA, nrow = max(size), ncol = length(size))
results_b <- matrix(NA, nrow = max(size), ncol = length(size))
for(i in 1:ncol(results)){
  a <- rnorm(size[i])
  ar.epsilon <- arima.sim(list(order = c(1,0,0), ar = 0.7), n = size[i], sd=20)
  b = size[i]*a + ar.epsilon
  results_id[]
  results_a[c(1:size[i]), i] <- a
  results_b[c(1:size[i]), i] <- b
}

colnames(results_a) <- paste0('id.a.', size)
colnames(results_b) <- paste0('id.b.', size)

result_final <- data.frame(results_a, results_b)
result_final <- result_final[, c(1, 9, 2, 10, 3, 11, 4, 12, 5, 13, 6, 14, 7, 15, 8, 16)]
head(result_final, 5)
     id.a.10    id.b.10    id.a.50    id.b.50    id.a.100  id.b.100   id.a.200  id.b.200   id.a.300   id.b.300
1  0.2677109   4.135141 -1.2479756 -117.59951  0.98359034  62.78846 -0.4334481 -80.73017 -1.2820512 -376.21611
2 -0.9367075 -31.289128 -2.8949090 -177.02084 -0.09517645 -24.60170 -0.2134596 -24.28731 -0.2437892 -105.31801
3  0.5962061  -2.716978  1.1995795   68.50393 -1.13753051 -91.86198  1.2898376 291.26922  0.5395736  118.88174
4 -0.3120436 -22.395355  0.2200063   55.90104 -0.23305847 -32.09204  0.7150280 168.96521 -0.1842391  -63.82123
5  0.3979791 -33.284591  0.9722208  102.26825 -0.45663605 -58.60094  0.4104681  70.51101  1.2605879  373.00674
     id.a.400    id.b.400  id.a.440  id.b.440   id.a.500  id.b.500
1 -0.81734653 -354.499825  1.416543  649.6649 -0.7634678 -399.9059
2  1.77813114  670.127238  0.301712  149.6443  0.4791241  210.1626
3 -1.13121629 -501.422591  2.129244  950.8821  1.4002161  710.6371
4  0.08281154   -2.199712  1.321002  610.5567  0.2423353  140.2799
5  0.68390623  262.957092 -1.161112 -497.6224 -0.3141071 -179.2746