42
Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference October 2012

Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Embed Size (px)

Citation preview

Page 1: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Modeling Student Growth Using Multilevel Mixture Item Response Theory

Hong Jiao

Robert Lissitz

University of Maryland

Presentation at the 2012 MARCES Conference

October 2012

Page 2: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Yong Luo, Chao Xie, and Ming Li for feedback

Thanks to

Page 3: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Value-added modeling• Multilevel IRT models • Mixture IRT models• Direct modeling of students’ growth

parameters in multilevel mixture IRT models• Simulation for direct modeling of growth in

IRT models• Future explorations

Outline of presentation

Page 4: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• VAM intends to estimate the effect of educational inputs on student outcomes or student achievement as measured by standardized tests. (McCaffrey et al. 2003)

• Accurate estimation of students’ achievement is very important as high stakes decisions are associated with the use of such scores.

• All value-added models estimate the growth associated with schools and/or teachers

• To measure growth, some models control for students’ prior achievement (FL commissioned paper by AIR)

Value-added modeling

Page 5: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• How prior achievements are accounted for

• How value-added scores of school and teacher effects are estimated

• Assumptions about the sustainability of school and teacher effects

• Value-added models can be grouped into two major classes (AIR): Typical learning path models Covariate adjustment models

Complexity of the VAM

Page 6: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Each student is assumed to have a typical learning path

• Schools and teachers can alter this learning path relative to the state mean, a conditional average

• No direct control of prior achievement• With more data points, a student’s propensity

to achieve can be estimated with more accuracy

• With each passing year, a student’s typical learning path can be estimated with increased precision over time

• Different learning path models assume differently about how teachers and schools can impact a student’s propensity to achieve

Typical learning path models-longitudinal mixed-effects mdoels

Page 7: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Sander’s Tennessee value added assessment system (TVAAS) model, teacher effects are assumed to have a permanent impact on students

• McCaffrey and Lockwood (2008) relaxed this assumption and let the data dictate the extent to which teacher effects decay over time

• Kane et al. (2008) found that teacher effects appear to dissipate over the course of about two years in an experiment in Los Angeles

Different learning path models

Page 8: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Direct control of prior student scores, prior test scores are included as predictors in the model

• Teacher effects can be treated as either fixed or random

• To obtain unbiased estimates, covariate adjustment models must account for measurement error introduced by the inclusion of model predictors-students’ prior achievement

Covariate adjustment models

Page 9: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Two frequently used methods for accounting for measurement error in regression analysis include Direct modeling of error such as in

structural equation models or errors-in-variables regression

Instrumental variable approach using one or more variables that are assumed to influence the current year score, but not prior year scores to statistically purge the measurement error from the prior year scores

Covariate adjustment models

Page 10: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Students are not randomly assigned to districts, schools, and classes

• Parent selection of schools and teachers, teacher selection of schools, subjects, and sections, principal discretion in assigning certain students to certain teachers

• These selection factors cause significant biases

• Unbiased estimates of teacher value-added controls the factors that influence both selection of students into particular classes and current year test scores

Statistical controls for contextual factors

Page 11: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Many value-added models assume only students’ prior test score is relevant to students’ posttest score

• Other models incorporate controls for additional variables that might influence selection and outcomes

Statistical controls for contextual factors

Page 12: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Empirical evidence is mixed on the extent to which student characteristics other than score histories remain correlated with test scores after controlling for prior test scores

• Some studies found that controlling for student-level characteristics makes little if any significant difference in model estimates (Ballou, Sanders, and Wright, 2004; McCaffrey et al. 2004) This is consistent with the view that durable student

characteristics associated with race, income, and other characteristics are already reflected in prior test scores, such that controlling for the prior test scores controls for any relevant impact of the factors proxied by the measured characteristics

Statistical controls for contextual factors

Page 13: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• In contrast, when student factors are aggregated to school or classroom levels, they sometimes reveal a significant residual effect (Raudenbush, 2004; Ballou, Sanders, & Wright, 2004). School or classroom characteristics may explain additional variance in students’ posttest scores independently beyond students’ individual characteristics accounted for by their prior test scores

• True teacher effectiveness really does vary with student characteristics and correlated variation of estimated teacher value-added is not the consequence of uncontrolled selection bias but rather a reflection of these true differences in teacher effectiveness.

Statistical controls for contextual factors

Page 14: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Typical learning path models require an assumption about the durability of the impact of teachers on a student’s learning path. Sanders’ Tennessee value-added assessment

system assume that teacher effects have a permanent impact on students

McCaffrey & Lockwood (2008) let the data dictate the extent to which teacher effects decay over time

Kane et al. (2008) found that teacher effects appeared to dissipate over the course of about two years in an experiment in LA.

Durability of teacher effects

Page 15: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Covariate models do not make assumption about the durability of teacher effects as they explicitly establish expectations based on prior achievement by including prior test scores as a covariate, rather than the abstract ‘propensity to achieve’ estimated in learning path models

Durability of teacher effects

Page 16: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Colorado growth model (Betebenner, 2008) uses entirely normative in-state percentile ranks• Not rely on a potentially flawed vertical

scale• But only provide normative criteria• Students’ growth is examined relative to

their peers rather than absolute growth in their own learning.

Unit of measurement for student achievement

Page 17: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Majority used interval measures of students; scaled test score

• Student percentile ranks within the student’s grade was also used as the dependent variable in some models

Dependent variable in growth modeling

Page 18: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Selection effects include parent selection of schools and teachers; teacher selection of schools, subjects, and sections; and principal discretion in assigning certain students to certain teachers

• Selection effects can be mitigated when the model includes factors that are not accounted for by pretest scores, and are associated with posttest scores after controlling for pretest scores.

Correction of biased estimates of teacher effects in VAM

Page 19: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Testing is infrequent-once a year• Tests sample all topics related to

achievement• The scale for measuring achievement is not

predetermined by the nature of achievement but is chosen by the test developer.

• Changes to the timing of tests, the weight given to alternative topics, or the scaling of the test could change our conclusions about the relative achievement or growth in achievement across classes of students.

Issues arising from the use of achievement test scores as an outcome measure

Page 20: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Linking errors could be conflated with teacher effects

• Equal interval property of the scale across grades was questionable.

• Ceiling effects at higher grades may lead to smaller learning gains than grades in the middle scale.

• Measurement errors cause estimated treatment effects confounded with group means of prior achievement (Lockwood, 2012)

Potential problems in value-added models

Page 21: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Covariate Adjusted Models (McCaffrey, et al. 2003)

tTttStmSt b )1(*

the student’s score at time t

a student-specific mean

the student’s score at time t-1

the teacher effect

the error term assumed to be normally distributed and independent of

Page 22: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Gain Score Models (McCaffrey et al. 2003)

tTttmtSSt )1(

the student’s score at time t

a student-specific mean

the student’s score at time t-1

the teacher effect

the error term assumed to be normally distributed and independent of

The gain score model can be viewed as a special case of the covariate adjusted model, where b, the coefficient of prior achievement, is equal to 1.

Page 23: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Teacher Effect Estimate in VAM (Luo, Jiao, & Van Wie,2012)

• Two-step process: In most value-added modeling, student

achievement scores are estimated before entering the model for estimating teacher or school effect.

Students’ achievement scores are estimated based on a certain item response theory (IRT) model first, most often a unidimensional IRT model.

Page 24: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Issues with Two-Step Process (Luo, Jiao, & Van Wie, 2012)

• Standard IRT models are used in operation to measure students’ achievement scores.

• Non-random assignment of students into schools and classes cause local person dependence due to the nesting structure (Reckase, 2009, Jiao et al. 2012).

• Measurement precision might be affected• Parameter estimates may be biased due to the

reduced effective sample size (Cochrane, 1977; Cyr & Davies, 2005; Kish, 1965).

• Ultimately, the accuracy in estimating teacher and school effect may also be affected.

Page 25: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

• Standardized test scores• Intrinsic measurement errors in the test

scores• Possible solution is to use multilevel item

response theory (IRT) models Simultaneous modeling of students’

achievement, teacher effects, and school effects using item response data as the input data and the latent ability is simultaneously estimated with other model parameters such as item parameters and teacher and school random-effects.(van Wie, Luo, & Jiao, 2012; Luo, Jiao, & van Wie, 2012)

Outcome variables in VAM

Page 26: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Four level model in the traditional Rasch model format (Van Wie, Luo, & Jiao, 2012)

26

)](exp[1

1

iSTjjmsi b

p

Page 27: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Four level model in the traditional 3PL IRT model format (Luo, Jiao, & Van Wie, 2012)

27

)](exp[1

1

iSTj

iijmsi b

ccp

Page 28: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Multilevel IRT Framework

• Model parameter estimation of the 4-level IRT models: item parameters, student ability, teacher effect, and school effect.Rasch: HLM7, Proc Glimmix, MCMC2pl: MCMC3pl: MCMC

Page 29: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Teacher Effect and School Effect Computation

• In the two-step process, teacher effect is computed as the average of the scores of the nested students, and school effect is computed as the average of the teacher effects within the school. This is analogous to the status model.

• In the 4-level IRT model, the student ability, the teacher effect and the school effect were simultaneously estimated.

Page 30: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Findings

• Except for RMSE in teacher effect parameter estimation, the 4-level 3pl IRT model performs significantly better than the 2-level 3pl IRT model.

• Especially noticeable is the considerable improvement of teacher effect parameter estimation.

Page 31: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Improvement of Teacher Effect Estimates

• The improvement is especially noticeable when teacher effects and school effects are medium.

• The improvement decreases with the decrease of teacher effects and school effects.

Page 32: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Further improvement

• As the change score is ultimately used in evaluating teacher and school effects in several value-added models, we explored direct estimation of change score by including prior achievement scores in the IRT modeling.

• An IRT model formulation for growth score is presented and model parameter estimation is explored.

• A multilevel formulation is presented.

• A mixture IRT version including growth score is presented and model parameter estimation is discussed.

Page 33: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Possible models

• Rasch model with direct modeling of growth parameter

)))(exp(1(

1),1(

ijjjjiji b

,bxP

• Multilevel Rasch model with direct modeling of growth parameter

)](exp[1

1

iSTjjjmsi b

p

Page 34: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Possible models

• Multilevel Rasch mixture model with direct modeling of growth parameter with no latent classes at teacher and school levels

)](exp[1

1

icSTjcjcjmsic b

p

)](exp[1

1

icScTcjcjcjmsic b

p

• Multilevel Rasch mixture model with direct modeling of growth parameter with latent classes at teacher and school levels

Page 35: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Simulation Study

• 30 items and 1000 examinees simulated

)1,0(~ Nb )1,0(~ N

)5.0,0(~ N

)))(exp(1(

1),1(

ijjjjiji b

,bxP

Page 36: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Model Parameter Estimation

Using the Markov Chain Monte Carlo (MCMC) method implemented in OpenBUGS 3.0.7

)2,0(~ Nj

,

.

)10,0(~ dnormbi

)(~ jiji pBernoullix

Priors:

)))(exp(1(

1),1(

ijjjjiji b

,bxP

scoretestprioraparameterknownaisj

Page 37: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

MCMC runs

two chains used

Initial values were generated by the program

Page 38: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Convergence Check

Multiple criteria for convergence check

The required number of iterations for equilibrium varied for different models

The number of burn-in iterations: 40,000 iterations

The model parameter inferences were made based on the 10,000 monitoring iterations for each chain with a total of 20,000 samples.

Page 39: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Growth parameter estimates

Descriptive Statistics

N Minimum Maximum Mean Std. Deviation

dtheta 1000 -1.426000 1.818000 -.00315860 .485358632

dtheta_true 1000 -1.346726 1.459898 -.01686716 .488377290

dif_theta 1000 -1.513055 2.036097 .00835295 .543427499

Valid N (listwise) 1000

Page 40: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Correlations: growth parameter estimates

Correlations

dtheta_true dif_theta

dtheta_true

Pearson Correlation 1 .616**

Sig. (2-tailed) .000

N 1000 1000

dif_theta

Pearson Correlation .616** 1

Sig. (2-tailed) .000

N 1000 1000

**. Correlation is significant at the 0.01 level (2-tailed).

Correlations

dtheta dtheta_true

dtheta

Pearson Correlation 1 .745**

Sig. (2-tailed) .000

N 1000 1000

dtheta_true

Pearson Correlation .745** 1

Sig. (2-tailed) .000

N 1000 1000

**. Correlation is significant at the 0.01 level (2-tailed).

Page 41: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Future Research

• Multilevel IRT model for direct estimation of the growth change scores.

• A Mixture multilevel IRT model for direct estimation of the growth change scores

• A constrained version of the model is possible by setting the growth change scores to non-negative values.

• Extensions to other IRT models such as 2PL, 3PL-c, 3PL-d, and 4P IRT models and the mixture version of the models.

• Replications and simulate more study conditions.

• Model fit indexes to select among competing models should be investigated under more extensive study conditions.

Page 42: Modeling Student Growth Using Multilevel Mixture Item Response Theory Hong Jiao Robert Lissitz University of Maryland Presentation at the 2012 MARCES Conference

Thank you!