search

tmatta / lsasim

Simulate large scale assessment data
6 stars 5 forks source link

c_mean & sigma & cor_matrix & rho #20

Closed wleoncio closed 3 years ago

wleoncio commented 3 years ago

0. Setup

I've tested most values below. Not all testings are shown in this report. I only included the testings that are showing errors/warnings or inconsistent results.

cluster_gen_2 <- function(...) {
  cluster_gen(..., verbose = FALSE, calc_weights = FALSE)
}
set.seed(12334)
n1 <- c(3, 6)
n2 <- c(groups = 4, people = 2)
n3 <- c(school = 3, class = 2, student = 5)
n4 <- c(20, 50)
n5 <- list(school = 3, class = c(2, 1, 3), student = c(20, 20, 10, 30, 30, 30))
n5a <- list(school = 3, class = c(2, 3, 3), student = c(20, 20, 10, 30, 30, 30))
n6 <- list(school = 3, class = c(2, 1, 3), student = ranges(10, 50))
n6a <- list(school = 3, class = c(2, 3, 3), student = ranges(10, 50))
n7 <- list(school = 10, student = ranges(10, 50))
n8 <- list(school = 3, student = c(20, 20, 10))
n8a <- list(school = 3, class = c(2, 2, 2),student = c(20, 20, 10))
n8b <- list(school = 3, class = c(2, 3, 3),student = c(20, 20, 10, 5))
n8c <- list(school = 3, class = c(2, 1, 3),student = c(20, 20, 10))
n9 <- list(school = 10, class = c(2,1,3,1,1,1,2,1,2,1), student = ranges(10, 50))
n10 <- list(country = 2, school = 10, class = c(2,1,3,1,1,1,2,1,2,1), student = ranges(10, 50))
n11 <- list(culture = 2, country = 2, school = 10, class = c(2,1,3,1,1,1,2,1,2,1), student = ranges(10, 50))
n12 <- list(culture = 2, country = 2, district = 3, school = 10, class = c(2,1,3,1,1,1,2,1,2,1), student = ranges(10, 50))
N1 <- c(100, 20)

10. c_mean & sigma & cor_matrix & rho

Error and warning messages

# m1 <- matrix(c(1, 0.2, 0.3, 0.4,
#                0.2, 1, 0.5, 0.7,
#                0.3, 0.5, 1, 0.8,
#                0.4, 0.7, 0.8, 1), 4, 4)
# m2 <- matrix(c(1, 0.5, 0.6,
#                0.5, 1, 0.9,
#                0.6, 0.9, 1), 3, 3)
# m3 <- matrix(c(1, 0.55, 0.77,
#                0.55, 1, 0.33,
#                0.77, 0.33, 1), 3, 3)
# m4 <- matrix(c(1, 0.55,
#                0.55, 1), 2, 2)
set.seed(12334)
csc1 <- cluster_gen_2(n7, n_X=4, n_W=0, c_mean=c(10, 20, 30, 40), sigma=c(1, 2, 3, 4), cor_matrix=m1)
summarize_clusters(csc1)
## Summary statistics for all schools
##        q1               q2              q3              q4
##  Min.   : 5.604   Min.   :11.11   Min.   :16.87   Min.   :21.97
##  Mean   : 9.996   Mean   :20.02   Mean   :30.00   Mean   :40.03
##  Max.   :14.203   Max.   :29.76   Max.   :44.40   Max.   :58.43
##
##  Stddev.: 1       Stddev.: 2      Stddev.: 3.01   Stddev.: 4
##
##
##
##  Heterogeneous correlation matrix
##           q1        q2        q3        q4
## q1 1.0000000 0.1976569 0.2936843 0.3976172
## q2 0.1976569 1.0000000 0.4994958 0.6963824
## q3 0.2936843 0.4994958 1.0000000 0.8025765
## q4 0.3976172 0.6963824 0.8025765 1.0000000
set.seed(12334)
csc2 <- cluster_gen_2(n7, n_X=1, n_W=2, c_mean=100, sigma=3, cor_matrix=m2)
summarize_clusters(csc2)
## Summary statistics for all schools
##        q1         q2       q3
##  Min.   : 88.10   1:8938   1:9287
##  Mean   : 99.99   2:6253   2:9602
##  Max.   :111.85   3:5416   3:4939
##                   4:2724   4:2076
##  Stddev.: 3.01    5:3401   5: 828
##
##                   Prop.    Prop.
##                   1:0.334  1:0.347
##                   2:0.234  2:0.359
##                   3:0.203  3:0.185
##                   4:0.102  4:0.078
##                   5:0.127  5:0.031
##
##
##
##  Heterogeneous correlation matrix
##           q1        q2        q3
## q1 1.0000000 0.3881865 0.4714790
## q2 0.3881865 1.0000000 0.4695883
## q3 0.4714790 0.4695883 1.0000000
#           q1        q2        q3
# q1 1.0000000 0.3881865 0.4714790
# q2 0.3881865 1.0000000 0.4695883
# q3 0.4714790 0.4695883 1.0000000

set.seed(12334)
csc3 <- cluster_gen_2(n7, n_X=2, n_W=1, c_mean=c(100, 150), sigma=c(3, 4), cor_matrix=m3)
summarize_clusters(csc3)
## Summary statistics for all schools
##        q1               q2        q3
##  Min.   : 87.42   Min.   :132.6   1:8323
##  Mean   : 99.96   Mean   :150.0   2:8848
##  Max.   :111.85   Max.   :166.7   3:4952
##                                   4:2345
##  Stddev.: 3.02    Stddev.: 3.98   5:2264
##
##                                   Prop.
##                                   1:0.311
##                                   2:0.331
##                                   3:0.185
##                                   4:0.088
##                                   5:0.085
##
##
##
##  Heterogeneous correlation matrix
##           q1        q2        q3
## q1 1.0000000 0.5561502 0.6428390
## q2 0.5561502 1.0000000 0.2826637
## q3 0.6428390 0.2826637 1.0000000
#           q1        q2        q3
# q1 1.0000000 0.5561502 0.6428390
# q2 0.5561502 1.0000000 0.2826637
# q3 0.6428390 0.2826637 1.0000000

set.seed(12334)
csc4 <- cluster_gen_2(n7, n_X=2, n_W=0, c_mean=c(210, 310), sigma=c(2, 5), cor_matrix=m4)
summarize_clusters(csc4)
## Summary statistics for all schools
##        q1              q2
##  Min.   :202.1   Min.   :290.1
##  Mean   :210.0   Mean   :310.0
##  Max.   :218.4   Max.   :331.5
##
##  Stddev.: 2      Stddev.: 4.97
##
##
##
##  Heterogeneous correlation matrix
##           q1        q2
## q1 1.0000000 0.5416685
## q2 0.5416685 1.0000000
## c_mean & sigma & rho
set.seed(12334)
csr1 <- cluster_gen_2(n7, n_X = 5, c_mean = list(15,c(10, 55, 0.21, 2.34, 5000)), sigma = list(20,c(40, 100, 0.11, 3, 1500)), rho = c(0.2, 0.15))
## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables

## Warning: c_mean recycled to fit all continuous variables
csr2 <- cluster_gen_2(n7, n_X = 5, c_mean = c(10, 55, 0.21, 2.34, 5000), sigma = c(40, 100, 0.11, 3, 1500), rho = 0.2)

summarize_clusters(csr1) #c_mean recycled to fit all continuous variables  ???????????
## Summary statistics for all schools
##        q1                 q2                q3                q4                q5          q6       q7
##  Min.   :-101.105   Min.   :-63.083   Min.   :-86.418   Min.   :-62.080   Min.   :-85.171   1:8077   1:8481
##  Mean   :   6.599   Mean   : 21.657   Mean   :  6.479   Mean   : 21.475   Mean   :  6.515   2:3475   2:5126
##  Max.   : 100.521   Max.   :109.721   Max.   :112.948   Max.   :103.093   Max.   : 93.233   3:4010   3:4979
##                                                                                             4:4068   4:8146
##  Stddev.: 24.44     Stddev.: 21.15    Stddev.: 24.49    Stddev.: 21.24    Stddev.: 24.56    5:7102
##                                                                                                      Prop.
##                                                                                             Prop.    1:0.317
##                                                                                             1:0.302  2:0.192
##                                                                                             2:0.13   3:0.186
##                                                                                             3:0.15   4:0.305
##                                                                                             4:0.152
##                                                                                             5:0.266
##
##
##  q8       q9       q10
##  1:6682   1:8214   1:9791
##  2:3912   2:3429   2:4765
##  3:3740   3:3279   3:3299
##  4:4686   4:5394   4:8877
##  5:7712   5:6416
##                    Prop.
##  Prop.    Prop.    1:0.366
##  1:0.25   1:0.307  2:0.178
##  2:0.146  2:0.128  3:0.123
##  3:0.14   3:0.123  4:0.332
##  4:0.175  4:0.202
##  5:0.288  5:0.24
##
##
##
##  Heterogeneous correlation matrix
##              q1          q2           q3          q4          q5           q6            q7            q8
## q1   1.00000000 -0.08398416  0.508207863  0.06542001  0.34002031 -0.156453037 -0.0720938896  0.0667830332
## q2  -0.08398416  1.00000000 -0.181446612  0.03275459 -0.03289630  0.136797185  0.1020320661  0.0269577527
## q3   0.50820786 -0.18144661  1.000000000  0.01935718  0.21956124 -0.006159808 -0.0619505597  0.0418274746
## q4   0.06542001  0.03275459  0.019357180  1.00000000 -0.19924574 -0.079334094 -0.0644787608  0.0175913508
## q5   0.34002031 -0.03289630  0.219561242 -0.19924574  1.00000000 -0.058997081  0.1254168383 -0.0781227527
## q6  -0.15645304  0.13679718 -0.006159808 -0.07933409 -0.05899708  1.000000000  0.2338897980  0.1129173028
## q7  -0.07209389  0.10203207 -0.061950560 -0.06447876  0.12541684  0.233889798  1.0000000000 -0.0004633439
## q8   0.06678303  0.02695775  0.041827475  0.01759135 -0.07812275  0.112917303 -0.0004633439  1.0000000000
## q9   0.08501818 -0.05332360 -0.025095683  0.25049001 -0.12740201 -0.010156144 -0.0983115671  0.1349301095
## q10 -0.10226289 -0.25383610 -0.077594083  0.01144076 -0.04463091  0.057364760  0.0817635201 -0.0745905308
##              q9         q10
## q1   0.08501818 -0.10226289
## q2  -0.05332360 -0.25383610
## q3  -0.02509568 -0.07759408
## q4   0.25049001  0.01144076
## q5  -0.12740201 -0.04463091
## q6  -0.01015614  0.05736476
## q7  -0.09831157  0.08176352
## q8   0.13493011 -0.07459053
## q9   1.00000000  0.15011053
## q10  0.15011053  1.00000000
summarize_clusters(csr2)
## Summary statistics for all schools
##        q1                 q2                q3               q4               q5           q6       q7
##  Min.   :-173.796   Min.   :-380.03   Min.   : 9.487   Min.   :-3.026   Min.   :-6048.19   1:7774   1:7564
##  Mean   :   4.876   Mean   :  14.28   Mean   : 9.980   Mean   :10.030   Mean   :   -9.13   2:5273   2:5693
##  Max.   : 189.074   Max.   : 464.33   Max.   :10.483   Max.   :25.877   Max.   : 6499.38   3:8521   3:8311
##
##  Stddev.: 42.34     Stddev.: 103.31   Stddev.: 0.12    Stddev.: 3.3     Stddev.: 1616.6    Prop.    Prop.
##                                                                                            1:0.36   1:0.351
##                                                                                            2:0.244  2:0.264
##                                                                                            3:0.395  3:0.385
##
##
##
##
##
##
##  q8        q9       q10      q11      q12
##  1:13503   1:5836   1:6503   1:5761   1:8492
##  2: 8065   2:2504   2:3918   2:6822   2:3519
##            3:4896   3:4309   3:8985   3:4634
##  Prop.     4:3627   4:6838            4:4923
##  1:0.626   5:4705            Prop.
##  2:0.374            Prop.    1:0.267  Prop.
##            Prop.    1:0.302  2:0.316  1:0.394
##            1:0.271  2:0.182  3:0.417  2:0.163
##            2:0.116  3:0.2             3:0.215
##            3:0.227  4:0.317           4:0.228
##            4:0.168
##            5:0.218
##
##
##
##  Heterogeneous correlation matrix
##              q1          q2          q3            q4            q5          q6          q7          q8
## q1   1.00000000 -0.12408092  0.14077536 -0.0124256860 -0.1687128998  0.09753099  0.18880415  0.03466961
## q2  -0.12408092  1.00000000 -0.01137658  0.0685733929 -0.0782305676  0.08562449 -0.03817721  0.05654488
## q3   0.14077536 -0.01137658  1.00000000  0.0299012540  0.0567025159 -0.02003248  0.07016994 -0.06132604
## q4  -0.01242569  0.06857339  0.02990125  1.0000000000 -0.0006220862 -0.04782257  0.05491068  0.14081331
## q5  -0.16871290 -0.07823057  0.05670252 -0.0006220862  1.0000000000 -0.18136474 -0.04701187  0.01391599
## q6   0.09753099  0.08562449 -0.02003248 -0.0478225680 -0.1813647359  1.00000000  0.02234744  0.21841098
## q7   0.18880415 -0.03817721  0.07016994  0.0549106750 -0.0470118715  0.02234744  1.00000000 -0.16921709
## q8   0.03466961  0.05654488 -0.06132604  0.1408133105  0.0139159894  0.21841098 -0.16921709  1.00000000
## q9   0.10497556  0.02318908  0.09679445 -0.1620541177  0.1010814626 -0.00430923  0.06681029 -0.08596421
## q10 -0.01412272  0.09942506 -0.07094439 -0.0089832243  0.1129473936 -0.11037703  0.02178161 -0.01427074
## q11  0.05094050  0.01341756  0.03410649 -0.0207544848  0.0591466533 -0.05902103 -0.11831901  0.03955630
## q12  0.13361571 -0.06687255 -0.03959208 -0.0671169395 -0.0821746196  0.16478817  0.14618056  0.01335425
##              q9          q10         q11          q12
## q1   0.10497556 -0.014122724  0.05094050  0.133615710
## q2   0.02318908  0.099425061  0.01341756 -0.066872554
## q3   0.09679445 -0.070944390  0.03410649 -0.039592078
## q4  -0.16205412 -0.008983224 -0.02075448 -0.067116939
## q5   0.10108146  0.112947394  0.05914665 -0.082174620
## q6  -0.00430923 -0.110377028 -0.05902103  0.164788174
## q7   0.06681029  0.021781614 -0.11831901  0.146180564
## q8  -0.08596421 -0.014270744  0.03955630  0.013354248
## q9   1.00000000  0.052845398 -0.05621468  0.063894860
## q10  0.05284540  1.000000000  0.02327423 -0.008651702
## q11 -0.05621468  0.023274230  1.00000000 -0.162352387
## q12  0.06389486 -0.008651702 -0.16235239  1.000000000