The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

DexterMST

DexterMST is an R package acting as a companion to dexter and adding facilities to manage and analyze data from multistage tests (MST). It includes functions for importing and managing test data, assessing and improving the quality of data through basic test and item analysis, and fitting an IRT model, all adapted to the peculiarities of MST designs. DexterMST typically works with project database files saved on disk.

Installation

install.packages('dexterMST')

If you encounter a bug, please post a minimal reproducible example on github. We post news and examples on a blog, it’s also the place for general questions.

Example

Here is an example for a simple two-stage test.

library(dexterMST)
library(dplyr)
# start a project
db = create_mst_project(":memory:")

items = data.frame(item_id=sprintf("item%02i",1:70), item_score=1, delta=sort(runif(70,-1,1)))

design = data.frame(item_id=sprintf("item%02i",1:70),
                    module_id=rep(c('M4','M2','M5','M1','M6','M3', 'M7'),each=10))

routing_rules = routing_rules = mst_rules(
 `124` = M1[0:5] --+ M2[0:10] --+ M4, 
 `125` = M1[0:5] --+ M2[11:15] --+ M5,
 `136` = M1[6:10] --+ M3[6:15] --+ M6,
 `137` = M1[6:10] --+ M3[16:20] --+ M7)


scoring_rules = data.frame(
  item_id = rep(items$item_id,2), 
  item_score= rep(0:1,each=nrow(items)),
  response= rep(0:1,each=nrow(items))) # dummy respons
  

db = create_mst_project(":memory:")
add_scoring_rules_mst(db, scoring_rules)

create_mst_test(db,
                test_design = design,
                routing_rules = routing_rules,
                test_id = 'sim_test',
                routing = "all")

We can now plot the design

# plot test designs for all tests in the project
design_plot(db)

We now simulate data:

theta = rnorm(3000)

dat = sim_mst(items, theta, design, routing_rules,'all')
dat$test_id='sim_test'
dat$response=dat$item_score

add_response_data_mst(db, dat)

# IRT, extended nominal response model
f = fit_enorm_mst(db)

head(f)

# ability estimates per person
rsp_data = get_responses_mst(db)
abl = ability(rsp_data, parms = f)
head(abl)

# ability estimates without item Item01
abl2 = ability(rsp_data, parms = f, item_id != "item01")

# plausible values
pv = plausible_values(rsp_data, parms = f, nPV = 5)
head(pv)

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.