data.timss07.G4.lee: TIMSS 2007 Mathematics 4th Grade (Lee et al., 2011)

Description

TIMSS 2007 (Grade 4) dataset with 25 mathematics (dichotomized) items used in Lee, Park and Taylan (2011), Park and Lee (2014) and Park, Xing and Lee (2018). The dataset includes a sample of 698 Austrian students.

Usage

data(data.timss07.G4.lee)
data(data.timss07.G4.py)
data(data.timss07.G4.Qdomains)

Arguments

Format

The dataset data.timss07.G4.lee is a list containing dichotomous item responses (data; information on booklet and gender included), the Q-matrix (q.matrix) and descriptions of the skills (skillinfo) used in Lee et al. (2011).

The format is:

List of 3
$ data :'data.frame':
..$ idstud : int [1:698] 10110 10111 20105 20106 30203 30204 40106 40107 60111 60112 ...
..$ idbook : int [1:698] 4 5 4 5 4 5 4 5 4 5 ...
..$ girl : int [1:698] 0 0 1 1 0 1 0 1 1 1 ...
..$ M041052 : num [1:698] 1 NA 1 NA 0 NA 1 NA 1 NA ...
..$ M041056 : num [1:698] 1 NA 0 NA 0 NA 0 NA 1 NA ...
..$ M041069 : num [1:698] 0 NA 0 NA 0 NA 0 NA 1 NA ...
..$ M041076 : num [1:698] 1 NA 0 NA 1 NA 1 NA 0 NA ...
..$ M041281 : num [1:698] 1 NA 0 NA 1 NA 1 NA 0 NA ...
..$ M041164 : num [1:698] 1 NA 1 NA 0 NA 1 NA 1 NA ...
..$ M041146 : num [1:698] 0 NA 0 NA 1 NA 1 NA 0 NA ...
..$ M041152 : num [1:698] 1 NA 1 NA 1 NA 0 NA 1 NA ...
..$ M041258A: num [1:698] 0 NA 1 NA 1 NA 0 NA 1 NA ...
..$ M041258B: num [1:698] 1 NA 0 NA 1 NA 0 NA 1 NA ...
..$ M041131 : num [1:698] 0 NA 0 NA 1 NA 1 NA 1 NA ...
..$ M041275 : num [1:698] 1 NA 0 NA 0 NA 1 NA 1 NA ...
..$ M041186 : num [1:698] 1 NA 0 NA 1 NA 1 NA 0 NA ...
..$ M041336 : num [1:698] 1 NA 1 NA 0 NA 1 NA 0 NA ...
..$ M031303 : num [1:698] 1 1 0 1 0 1 1 1 0 0 ...
..$ M031309 : num [1:698] 1 0 1 1 1 1 1 1 0 0 ...
..$ M031245 : num [1:698] 0 0 0 0 0 0 0 0 0 0 ...
..$ M031242A: num [1:698] 1 1 0 1 1 1 1 1 0 0 ...
..$ M031242B: num [1:698] 0 1 0 1 1 1 1 1 1 0 ...
..$ M031242C: num [1:698] 1 1 0 1 1 1 1 1 1 0 ...
..$ M031247 : num [1:698] 0 0 0 0 0 0 0 0 0 0 ...
..$ M031219 : num [1:698] 1 1 1 0 1 1 1 1 1 0 ...
..$ M031173 : num [1:698] 1 1 0 0 0 1 1 1 1 0 ...
..$ M031085 : num [1:698] 1 0 0 1 1 1 0 0 0 1 ...
..$ M031172 : num [1:698] 1 0 0 1 1 1 1 1 1 0 ...
$ q.matrix : int [1:25, 1:15] 1 0 0 0 0 0 0 1 0 0 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : chr [1:25] "M041052" "M041056" "M041069" "M041076" ...
.. ..$ : chr [1:15] "NWN01" "NWN02" "NWN03" "NWN04" ...
$ skillinfo:'data.frame':
..$ skillindex : int [1:15] 1 2 3 4 5 6 7 8 9 10 ...
..$ skill : Factor w/ 15 levels "DOR15","DRI13",..: 12 13 14 15 8 9 10 11 4 6 ...
..$ content : Factor w/ 3 levels "D","G","N": 3 3 3 3 3 3 3 3 2 2 ...
..$ content_label : Factor w/ 3 levels "Data Display",..: 3 3 3 3 3 3 3 3 2 2 ...
..$ subcontent : Factor w/ 9 levels "FD","LA","LM",..: 9 9 9 9 1 1 4 6 2 8 ...
..$ subcontent_label: Factor w/ 9 levels "Fractions and Decimals",..: 9 9 9 9 1 1 4 6 2 8 ...
The dataset data.timss07.G4.py uses the same items as data.timss07.G4.lee but employs a simplified Q-matrix with 7 skills. This Q-matrix was used in Park and Lee (2014) and Park et al. (2018).

List of 3
$ q.matrix:'data.frame': 25 obs. of 7 variables:
..$ N1: num [1:25] 1 0 1 1 1 0 0 1 0 0 ...
..$ N2: num [1:25] 0 1 1 1 0 0 0 0 0 0 ...
..$ N3: num [1:25] 0 0 0 0 1 0 0 0 0 0 ...
..$ G4: num [1:25] 0 0 0 0 0 0 1 0 0 1 ...
..$ G5: num [1:25] 0 0 0 0 0 1 1 1 1 1 ...
..$ G6: num [1:25] 0 0 0 0 0 1 1 0 0 0 ...
..$ D7: num [1:25] 0 0 0 0 0 0 0 0 0 0 ...
$ domains : Named chr [1:3] "Number" "Geometric Shapes and Measures" "Data Display"
..- attr(*, "names")=chr [1:3] "N" "G" "D"
$ skills : Named chr [1:7] "Whole Numbers" ...
..- attr(*, "names")=chr [1:7] "N1" "N2" "N3" "G4" ...
The Q-matrix data.timss07.G4.Qdomains is a simplification of data.timss07.G4.py$q.matrix to 3 domains and involves a simple structure of skills.

num [1:25, 1:3] 1 1 1 1 1 0 0 1 0 0 ...
- attr(*, "dimnames")=List of 2
..$ : chr [1:25] "M041052" "M041056" "M041069" "M041076" ...
..$ : chr [1:3] "N" "G" "D"

References

Lee, Y. S., Park, Y. S., & Taylan, D. (2011). A cognitive diagnostic modeling of attribute mastery in Massachusetts, Minnesota, and the US national sample using the TIMSS 2007. International Journal of Testing, 11, 144-177.

Park, Y. S., & Lee, Y. S. (2014). An extension of the DINA model using covariates: Examining factors affecting response probability and latent classification. Applied Psychological Measurement, 38(5), 376-390.

Park, Y. S., Xing, K., & Lee, Y. S. (2018). Explanatory cognitive diagnostic models: Incorporating latent and observed predictors. Applied Psychological Measurement, 42(5), 376-392.

Yamaguchi, K., & Okada, K. (2018). Comparison among cognitive diagnostic models for the TIMSS 2007 fourth grade mathematics assessment. PloS ONE, 13(2), e0188691.

Examples

Run this code

if (FALSE) {
#############################################################################
# EXAMPLE 1: DINA model Lee et al. (2011) - 15 skills
#############################################################################

data(data.timss07.G4.lee, package="CDM")
dat <- data.timss07.G4.lee$data
q.matrix <- data.timss07.G4.lee$q.matrix
# extract items
items <- grep( "M0", colnames(dat), value=TRUE )

#*** Model 1: estimate DINA model
mod1 <- CDM::din( dat[,items], q.matrix )
summary(mod1)

#############################################################################
# EXAMPLE 2: DINA models Park and Lee (2014) - 7 skills and 3 skills
#############################################################################

data(data.timss07.G4.lee, package="CDM")
data(data.timss07.G4.py, package="CDM")
data(data.timss07.G4.Qdomains, package="CDM")

dat <- data.timss07.G4.lee$data
q.matrix <- data.timss07.G4.py$q.matrix
items <- rownames(q.matrix)

#*** Model 1: estimate DINA model
mod1 <- CDM::din( dat[,items], q.matrix )
summary(mod1)

#*** Model 2: estimate DINA model with Q-matrix defined by domains
Q <- data.timss07.G4.Qdomains
mod2 <- CDM::din( dat[,items], q.matrix=Q )
summary(mod2)
}