Publications by N Foldnes

Simulations Ordlesing

25.06.2020

Design We have two stop rules (less or more precise) Standard error below 0.4, or reached 20 items Standard error below 0.2, or reached 40 items We have two start rules Assume initial skill is -1 Assume initial skill is -2 These are fully crossed to yield four conditions. Simulation procedure In each condition, we simulate 10 000 test takers...

1395 sym R (7259 sym/54 pcs) 16 img

Ordlesing IRT Final

26.08.2020

#Background for re-analysis Item naming was faulty in previous version. Some items were duplicated, and counted as two different items. The issue was with “Kopi.av.Kopi.av” etcetera Booklets and items A total number of 2054 students participated in this pilot-study, responding to a total of 378 items. The the number of observations per item:...

1057 sym R (271 sym/1 pcs) 6 img 3 tbl

Final ordlesing document

07.09.2020

The final item pool After Oddny/Vibeke removed more than fifty items due to the timing contradiction, we are left with 324 items. The item parameters are as follows. kable(round(itempool[, 1:2], 1))%>% kable_styling(position = "center") a b ord_001_dag_2 1.5 -1.5 ord_003_dag_500 2.3 -0.8 ord_005_tak_2 2.1 -1.9 ord_006_tak_1 1.8 -2....

12725 sym R (2882 sym/20 pcs) 8 img

Document

07.09.2020

The final item pool The SL items were removed, together with ill-fitting items. This resulted in 145 items: a b VM_385_Bakgården_1_kaka 5.0 -3.3 VM_386_Bakgården_2_gutten 1.4 -3.6 VM_388_Bakgården_4_Badebassenget 1.6 -3.6 VM_390_Bakgården_6_Verktøykassa 5.6 -2.1 VM_392_Bakgården_8_Løvetannen 1.5 -2.0 VM_394_Bakgården_10_...

6012 sym R (2730 sym/18 pcs) 7 img

Document

23.09.2020

We use BM for ability estimation and compare 15 vs 25 items. 25 items truethetas <- seq(-2.2,2.2, length.out=n) est.df <- data.frame(truetheta=truethetas) NMAX <- 25 SEMTHR <- .01 # UNATTAINABLE SO LENGTH WILL BE 25 FOR ALL STUDENTS est.df$NMAX <- NMAX; est.df$SE <- SEMTHR; stop <- list(rule = c("precision","length"), thr = c(SEMTHR, NMAX)) re...

165 sym R (1983 sym/9 pcs) 5 img

Holsinger using RLS

28.10.2020

Two models We consider a one-factor model with 4 indicators and the Holzinger 3-factor model. For the one-factor simple model we generate a random sample: library(lavaan) ## This is lavaan 0.6-7 ## lavaan is BETA software! Please report any bugs. #Simple factor model with random data Sim.model <- "F=~x1+x2+x3+x4" Sim.nobs <- 100 set.seed(1) Sim.c...

925 sym R (9946 sym/24 pcs) 3 img

Document

19.11.2020

The population model The vita distribution and the thresholds The vita distribution consists of mostly joe copulas. The first two vine trees: We found some thresholds were the default nt approach seemed to perform poorly. For k=7 For k=10 Bootstrap SEs versus the default NT SEs The simulation design crossed two sample sizes \(n=500,1000\) wi...

656 sym R (1719 sym/4 pcs) 6 img

Document

09.11.2020

Holzinger library(lavaan) ## This is lavaan 0.6-7 ## lavaan is BETA software! Please report any bugs. # Holzinger HS.model <- " visual =~ x1 + x2 + x3;textual =~ x4 + x5 + x6; speed =~ x7 + x8 + x9 " HS.cov <- cov(HolzingerSwineford1939[, paste0("x", 1:9)]) HS.nobs <- nrow(HolzingerSwineford1939) Step size reduction does not lead to solution ...

160 sym R (6883 sym/7 pcs)

Normindex1

28.11.2020

Koden for normindex computeNormIndex ## function (my.data) ## { ## my.data <- data.frame(my.data) ## d <- ncol(my.data) ## indices <- NULL ## for (i2 in 1:(d - 1)) { ## for (i1 in (i2 + 1):d) { ## indices <- rbind(indices, c(i1, i2)) ## } ## } ## Tstat <- nrow(my.data) * computeT(my.data, indic...

466 sym R (1838 sym/6 pcs) 3 img

Longitudinal invariance

22.04.2021

Generate longitudinal data load1 <- (5:8)/10 load2 <- load1# equal loadings set.seed(1) n <- 3000 # xi2 = .5*xi +1 xi <- MASS::mvrnorm(n, c(0,1), Sigma=matrix(c(1,.5, .5, 1),2)) ind1 <- xi[,1 ]%*% matrix(load1, nrow=1)+rnorm(4*n)# unique variance 1 ind2 <- xi[,2]%*% matrix(load2, nrow=1)+rnorm(4*n)# unique variance 1 dat <- cbind(ind1, ind2) da...

234 sym R (28770 sym/19 pcs)