Comments (11)
Bockův (nominal response) model do sekce IRT models.
from shinyitemanalysis.
Muj stary kod (20.2.15):
Nominal response model (NRM)
and Nested logit model (2PLNRM, 3PLNRM)
neelegantni prepocet
for (i in 1:680)
dataNRM<-rbind(dataNRM,as.numeric(data[i,varsA]))
keyNRM <- c(4,2,1,4,2,3,3,3,4,1,1,4,1,1,3,1,3,3,3,4)
modely
mod1 <- mirt(dataNRM, 1, 'nominal')
mod2 <- mirt(dataNRM, 1, '2PLNRM', key=keyNRM)
mod3 <- mirt(dataNRM, 1, '3PLNRM', key=keyNRM)
from shinyitemanalysis.
Můj nový kód. Vypadá to, že 2PLNRM
je to, co hledáme
library(difNLR)
library(mirt)
data("GMATtest", "GMATkey")
data <- GMATtest[, 1:20]
head(data)
data <- sapply(1:ncol(data), function(i) as.numeric(data[, i]))
head(data)
colnames(data) <- paste("Item", 1:ncol(data))
key <- as.numeric(as.factor(GMATkey))
# NOMINAL MODEL
fitNOM <- mirt(data, 1, "nominal")
coef(fitNOM)
itemplot(fitNOM, 3)
# 2PLNRM
fit2PLNRM <- mirt(data, 1, "2PLNRM", key = key)
coef(fit2PLNRM)
itemplot(fit2PLNRM, 3)
from shinyitemanalysis.
Tady je další kód, kdy ostatní položky jsou odhadovány pomocí 2PL
modelu:
library(difNLR)
library(mirt)
data("GMATtest", "GMATkey")
key <- as.numeric(as.factor(GMATkey))
data <- sapply(1:20, function(i) as.numeric(GMATtest[, i]))
colnames(data) <- paste("Item", 1:ncol(data))
scoredGMAT <- key2binary(data, key)
# 2PL IRT model for scored data
mod0 <- mirt(scoredGMAT, 1)
# nominal model for item 1 for unscored data
i <- 1
itemtype <- rep("2PL", ncol(data))
itemtype[i] <- "nominal"
df <- scoredGMAT
df[, i] <- data[, 1]
head(df)
mod1 <- mirt(df, 1, itemtype = itemtype)
# plots of characteristic curves for item 1
itemplot(mod0, 1)
itemplot(mod1, 1)
A tady je ještě porovnání factor scores:
fs0 <- fscores(mod0)
fs1 <- fscores(mod1)
summary(data.frame(fs0, fs1))
plot(fs0 ~ fs1)
A tady pokud odhadnu všechny položky jako nominal
mod1 <- mirt(data, 1, itemtype = "nominal")
# plots of characteristic curves for item 1
itemplot(mod0, 1)
itemplot(mod1, 1)
fs0 <- fscores(mod0)
fs1 <- fscores(mod1)
plot(fs0 ~ fs1)
from shinyitemanalysis.
Díky za update! Zatím úplně nerozumím, proč se ta interpretace theta takto změní, když se fituje nominal pro všechny položky... Připadá mi to jako bug v mirtu(?) Budu se těšit na update.
from shinyitemanalysis.
Přidáno s omezením
from shinyitemanalysis.
Jeste nam sem pridam odkaz na diskusi k tomuto tematu, at ji tu mame: http://stackoverflow.com/questions/41671318/mirt-odd-results-for-nominal-model/41753852#41753852
from shinyitemanalysis.
Vypada to skvele, parada!
Jeste myslim, ze tady by uz stalo za to udelat zalozku Item, a vyobrazovat ICC pro polozky postupne. Nebo jen pridat pod graf ICC graf se sliderem, kde se budou vyobrazovat ICC polozek postupne.
from shinyitemanalysis.
Lze jiz prohlizet a testovat na https://shiny.cs.cas.cz/ShinyItemAnalysis/
from shinyitemanalysis.
Záložky pro IRT (nebo jen Bockův model) bych asi nechala až do další verze. Předpokládám, že se budeme pokoušet řešit DDF pomocí Bockova modelu a bude jednodušší to implementovat najednou.
from shinyitemanalysis.
Dobrá, ponechme tedy prozatím, jak je, grafy pro položky (záložku Items) pořešíme v příští verzi.
Zatím prosím Jakuba o zprovoznění stahování obrázků i v této záložce (IRT models with mirt/Bock's nominal model).
from shinyitemanalysis.
Related Issues (20)
- Hexbin in footer HOT 2
- HTML generation on CS.CAS.CZ server HOT 2
- Section headings not well visible when using smartphone HOT 2
- PDF generation on cemp.shinyapps.io/ShinyItemAnalysis HOT 1
- Page acceess count on shinyapps.io HOT 2
- Analyses of ordinal data HOT 1
- Loading group vector with missing values HOT 2
- Errored occured when using "startShinyItemAnalysis()" on Windows 10 HOT 6
- Error after excuting startShinyItemAnalysis() HOT 5
- After updating R to 4-0-4 recent version, ShinyItemAnalysis does not work HOT 3
- Upload data loading! HOT 5
- Total Scores and data HOT 3
- Data is read incorrectly HOT 5
- Disconnecting while trying to read in data HOT 3
- disconnections HOT 2
- Plot legend is duplicated in black HOT 2
- No issue, just an idea HOT 1
- Error on Table of estimated parameters on IRT HOT 1
- uncertain dependency on Matrix package HOT 1
- Webpage fails to load HOT 7
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from shinyitemanalysis.