A dataset containing substance use behavior from the National Longitudinal Survey of Youth 1997 (NLSY97) for three years: 1998, 2003, and 2008. The dataset focuses on the youth born in 1984 and tracks three substance use behaviors: tobacco/cigarette smoking, alcohol drinking, and marijuana use.
Format
A data frame with 1004 rows and 38 columns:
- SEX
Respondent's sex
- RACE
Respondent's race
- ESMK_98, ESMK_03, ESMK_08
(Ever smoked) Ever smoked in 1998, 2003, and 2008 (0: No, 1: Yes)
- FSMK_98, FSMK_03, FSMK_08
(Frequent smoke) Monthly smokes in 1998, 2003, and 2008 (0: No, 1: Yes)
- DSMK_98, DSMK_03, DSMK_08
(Daily smoke) Daily smokes in 1998, 2003, and 2008 (0: No, 1: Yes)
- HSMK_98, HSMK_03, HSMK_08
(Heavy smoke) 10+ cigarettes per day in 1998, 2003, and 2008 (0: No, 1: Yes)
- EDRK_98, EDRK_03, EDRK_08
(Ever drunk) Have you ever drunk in 1998, 2003, and 2008? (0: No, 1: Yes)
- CDRK_98, CDRK_03, CDRK_08
(Current drinker) Monthly drinking in 1998, 2003, and 2008 (0: No, 1: Yes)
- WDRK_98, WDRK_03, WDRK_08
(Weakly drinker) 5+ days drinking in a month in 1998, 2003, and 2008 (0: No, 1: Yes)
- BDRK_98, BDRK_03, BDRK_08
(Binge drinker) 5+ drinks on the same day at least one time in the last 30 day (0: No, 1: Yes)
- EMRJ_98, EMRJ_03, EMRJ_08
(Ever marijuana used) Have you ever used marijuana in 1998, 2003, and 2008? (0: No, 1: Yes)
- CMRJ_98, CMRJ_03, CMRJ_08
(Corrent marijuana user) Monthly marijuana use in 1998, 2003, and 2008 (0: No, 1: Yes)
- OMRJ_98, OMRJ_03, OMRJ_08
(Occasional marijuana user) 10+ days marijuana use in a month in 1998, 2003, and 2008 (0: No, 1: Yes)
- SMRJ_98, SMRJ_03, SMRJ_08
(School/work marijuana user) Marijuana use before/during school or work in 1998, 2003, and 2008 (0: No, 1: Yes)
Similar naming conventions apply for the years 2003 and 2008, replacing '98' with '03' and '08', respectively.
References
Bureau of Labor Statistics, U.S. Department of Labor. National Longitudinal Survey of Youth 1997 cohort, 1997-2017 (rounds 1-18). Produced and distributed by the Center for Human Resource Research (CHRR), The Ohio State University. Columbus, OH: 2019.
Examples
library(magrittr)
nlsy_smoke <- slca(smk98(3) ~ ESMK_98 + FSMK_98 + DSMK_98 + HSMK_98) %>%
estimate(data = nlsy97, control = list(verbose = FALSE))
summary(nlsy_smoke)
#> Structural Latent Class Model
#>
#> Summary of analysis
#>
#> Number of observations 1004
#> Number of manifest variables 4
#> Number of latent class variables 1
#>
#>
#> Summary of model structure
#>
#> Latent variables (Root*):
#> Label: smk98*
#> nclass: 3
#>
#> Measurement model:
#> smk98 -> { ESMK_98, FSMK_98, DSMK_98, HSMK_98 } a
#>
#>
#> Summary of manifest variables
#>
#> Categories for each variable:
#> response
#> 1 2
#> ESMK_98 Yes No
#> FSMK_98 Yes No
#> DSMK_98 Yes No
#> HSMK_98 Yes No
#>
#> Frequencies for each categories:
#> response
#> 1 2 <NA>
#> ESMK_98 558 446 0
#> FSMK_98 413 591 0
#> DSMK_98 179 825 0
#> HSMK_98 115 889 0
#>
#>
#> Summary of model fit
#>
#> Number of free parameters 14
#> Log-likelihood -1536.221
#> Information criteria
#> Akaike (AIC) 3100.442
#> Bayesian (BIC) 3169.207
#> Chi-squared Tests
#> Residual degree of freedom (df) 1
#> Pearson Chi-squared (X-squared) 118.589
#> P(>Chi) 0.000
#> Likelihood Ratio (G-squared) 125.712
#> P(>Chi) 0.000
# \donttest{
# JLCA
model_jlca <- slca(
smk98(3) ~ ESMK_98 + FSMK_98 + DSMK_98 + HSMK_98,
drk98(3) ~ EDRK_98 + CDRK_98 + WDRK_98 + BDRK_98,
mrj98(3) ~ EMRJ_98 + CMRJ_98 + OMRJ_98 + SMRJ_98,
substance(4) ~ smk98 + drk98 + mrj98
) %>% estimate(data = nlsy97, control = list(verbose = FALSE))
summary(model_jlca)
#> Structural Latent Class Model
#>
#> Summary of analysis
#>
#> Number of observations 1004
#> Number of manifest variables 12
#> Number of latent class variables 4
#>
#>
#> Summary of model structure
#>
#> Latent variables (Root*):
#> Label: smk98 drk98 mrj98 substance*
#> nclass: 3 3 3 4
#>
#> Measurement model:
#> smk98 -> { ESMK_98, FSMK_98, DSMK_98, HSMK_98 } a
#> drk98 -> { EDRK_98, CDRK_98, WDRK_98, BDRK_98 } b
#> mrj98 -> { EMRJ_98, CMRJ_98, OMRJ_98, SMRJ_98 } c
#>
#> Structural model:
#> substance -> { smk98, drk98, mrj98 }
#>
#> Dependency constraints:
#> A B C
#> substance -> smk98 substance -> drk98 substance -> mrj98
#>
#> Tree of structural model:
#> substance -> smk98
#> -> drk98
#> -> mrj98
#>
#>
#> Summary of manifest variables
#>
#> Categories for each variable:
#> response
#> 1 2
#> ESMK_98 Yes No
#> FSMK_98 Yes No
#> DSMK_98 Yes No
#> HSMK_98 Yes No
#> EDRK_98 Yes No
#> CDRK_98 Yes No
#> WDRK_98 Yes No
#> BDRK_98 Yes No
#> EMRJ_98 Yes No
#> CMRJ_98 Yes No
#> OMRJ_98 Yes No
#> SMRJ_98 Yes No
#>
#> Frequencies for each categories:
#> response
#> 1 2 <NA>
#> ESMK_98 558 446 0
#> FSMK_98 413 591 0
#> DSMK_98 179 825 0
#> HSMK_98 115 889 0
#> EDRK_98 735 269 0
#> CDRK_98 521 483 0
#> WDRK_98 218 786 0
#> BDRK_98 288 716 0
#> EMRJ_98 383 621 0
#> CMRJ_98 226 778 0
#> OMRJ_98 92 912 0
#> SMRJ_98 98 906 0
#>
#>
#> Summary of model fit
#>
#> Number of free parameters 63
#> Log-likelihood -4069.738
#> Information criteria
#> Akaike (AIC) 8265.476
#> Bayesian (BIC) 8574.916
#> Chi-squared Tests
#> Residual degree of freedom (df) 4032
#> Pearson Chi-squared (X-squared) 290.581
#> P(>Chi) 1.000
#> Likelihood Ratio (G-squared) 304.295
#> P(>Chi) 1.000
param(model_jlca)
#> PI :
#> (substance)
#> class
#> 1 2 3 4
#> 0.2768 0.1218 0.4320 0.1693
#>
#> TAU :
#> (A)
#> parent
#> child 1 2 3 4
#> 1 0.3726 0.4380 0.0000 0.9863
#> 2 0.1008 0.2749 0.9330 0.0136
#> 3 0.5265 0.2871 0.0670 0.0000
#>
#> parent substance
#> child smk98
#> (B)
#> parent
#> child 1 2 3 4
#> 1 0.0447 0.9695 0.2330 0.4482
#> 2 0.0539 0.0100 0.6512 0.1996
#> 3 0.9014 0.0206 0.1158 0.3523
#>
#> parent substance
#> child drk98
#> (C)
#> parent
#> child 1 2 3 4
#> 1 0.5345 0.0000 0.0200 0.0000
#> 2 0.2876 0.7671 0.0000 0.2250
#> 3 0.1780 0.2329 0.9800 0.7750
#>
#> parent substance
#> child mrj98
#>
#> RHO :
#> (a)
#> class
#> response 1 2 3
#> 1(V1) 1.0000 0.0484 1.0000
#> 2 0.0000 0.9516 0.0000
#> 1(V2) 0.6234 0.0000 1.0000
#> 2 0.3766 1.0000 0.0000
#> 1(V3) 0.0000 0.0000 0.8504
#> 2 1.0000 1.0000 0.1496
#> 1(V4) 0.0000 0.0000 0.5463
#> 2 1.0000 1.0000 0.4537
#>
#> V1 V2 V3 V4
#> smk98 ESMK_98 FSMK_98 DSMK_98 HSMK_98
#> (b)
#> class
#> response 1 2 3
#> 1(V1) 1.0000 0.1912 1.0000
#> 2 0.0000 0.8088 0.0000
#> 1(V2) 0.5120 0.0000 1.0000
#> 2 0.4880 1.0000 0.0000
#> 1(V3) 0.0000 0.0000 0.6003
#> 2 1.0000 1.0000 0.3997
#> 1(V4) 0.0000 0.0000 0.7930
#> 2 1.0000 1.0000 0.2070
#>
#> V1 V2 V3 V4
#> drk98 EDRK_98 CDRK_98 WDRK_98 BDRK_98
#> (c)
#> class
#> response 1 2 3
#> 1(V1) 1.0000 1.0000 0.0217
#> 2 0.0000 0.0000 0.9783
#> 1(V2) 1.0000 0.3244 0.0000
#> 2 0.0000 0.6756 1.0000
#> 1(V3) 0.5851 0.0000 0.0000
#> 2 0.4149 1.0000 1.0000
#> 1(V4) 0.6233 0.0000 0.0000
#> 2 0.3767 1.0000 1.0000
#>
#> V1 V2 V3 V4
#> mrj98 EMRJ_98 CMRJ_98 OMRJ_98 SMRJ_98
# JLCPA
nlsy_jlcpa <- slca(
smk98(3) ~ ESMK_98 + FSMK_98 + DSMK_98 + HSMK_98,
drk98(3) ~ EDRK_98 + CDRK_98 + WDRK_98 + BDRK_98,
mrj98(3) ~ EMRJ_98 + CMRJ_98 + OMRJ_98 + SMRJ_98,
use98(5) ~ smk98 + drk98 + mrj98,
smk03(3) ~ ESMK_03 + FSMK_03 + DSMK_03 + HSMK_03,
drk03(3) ~ EDRK_03 + CDRK_03 + WDRK_03 + BDRK_03,
mrj03(3) ~ EMRJ_03 + CMRJ_03 + OMRJ_03 + SMRJ_03,
use03(5) ~ smk03 + drk03 + mrj03,
smk08(3) ~ ESMK_08 + FSMK_08 + DSMK_08 + HSMK_08,
drk08(3) ~ EDRK_08 + CDRK_08 + WDRK_08 + BDRK_08,
mrj08(3) ~ EMRJ_08 + CMRJ_08 + OMRJ_08 + SMRJ_08,
use08(5) ~ smk08 + drk08 + mrj08,
prof(4) ~ use98 + use03 + use08,
constraints = list(
c("smk98", "smk03", "smk08"),
c("drk98", "drk03", "drk08"),
c("mrj98", "mrj03", "mrj08"),
c("use98 ~ smk98", "use03 ~ smk03", "use08 ~ smk08"),
c("use98 ~ drk98", "use03 ~ drk03", "use08 ~ drk08"),
c("use98 ~ mrj98", "use03 ~ mrj03", "use08 ~ mrj08")
)
) %>% estimate(nlsy97, control = list(verbose = FALSE))
# }