ODEV_VI_MA
Meltem Atasoy
2025-12-07
library(openintro)
library(ggplot2)
library(tidyverse)
library(dplyr)
library(haven)
library(ggpubr)
library(patchwork)
library(corrplot)
library(ggcorrplot)
library(psych)
library(PerformanceAnalytics)
library(GGally)
library(broom)
library(CTT)
library(readxl)
library(readr)
library(lavaan)
library(lavaanPlot)
library(semTools)
library(semPlot)fin_ogrenci<- read_sav("ASGFINR5.sav")
fin_basari <- read_sav("ATGFINR5.sav")
fin_okul <- read_sav("ACGFINR5.sav")
fin_ev <- read_sav("ASHFINR5.sav")
hun_ogrenci <- read_sav("ASGHUNR5.sav")
hun_basari <- read_sav("ATGHUNR5.sav")
hun_okul <- read_sav("ACGHUNR5.sav")
hun_ev <- read_sav("ASHHUNR5.sav")
tur_ogrenci <- read_sav("ASGTURR5.sav")
tur_basari <- read_sav("ATGTURR5.sav")
tur_okul <- read_sav("ACGTURR5.sav")
tur_ev <- read_sav("ASHTURR5.sav")
kaz_ogrenci <- read_sav("ASGKAZA5.sav")
kaz_basari <- read_sav("ATGKAZA5.sav")
kaz_okul <- read_sav("ACGKAZA5.sav")
kaz_ev <- read_sav("ASHKAZA5.sav")
uz_ogrenci <- read_sav("ASGUZBR5.sav")
uz_basari <- read_sav("ATGUZBR5.sav")
uz_okul <- read_sav("ACGUZBR5.sav")
uz_ev <- read_sav("ASHUZBR5.sav")
fin_ev$IDCNTRY <- 246
hun_ev$IDCNTRY <- 348
tur_ev$IDCNTRY <- 792
kaz_ev$IDCNTRY <- 398
uz_ev$IDCNTRY <- 860
full_data_ev <- bind_rows(fin_ev,
hun_ev,
tur_ev,
kaz_ev,
uz_ev)
head(full_data_ev,3)## # A tibble: 3 × 118
## IDCNTRY IDPOP IDGRADER IDGRADE WAVE IDSCHOOL IDCLASS IDSTUD ITLANG_HQ
## <dbl> <dbl+lbl> <dbl+lb> <dbl+l> <dbl+l> <dbl> <dbl> <dbl> <dbl+lbl>
## 1 246 1 [Populat… 2 [Uppe… 4 1 [Spr… 5001 500101 5.00e7 43 [Finn…
## 2 246 1 [Populat… 2 [Uppe… 4 1 [Spr… 5001 500101 5.00e7 NA
## 3 246 1 [Populat… 2 [Uppe… 4 1 [Spr… 5001 500101 5.00e7 43 [Finn…
## # ℹ 109 more variables: LCID_HQ <dbl+lbl>, ASBH01A <dbl+lbl>,
## # ASBH01B <dbl+lbl>, ASBH01C <dbl+lbl>, ASBH01D <dbl+lbl>, ASBH01E <dbl+lbl>,
## # ASBH01F <dbl+lbl>, ASBH01G <dbl+lbl>, ASBH01H <dbl+lbl>, ASBH01I <dbl+lbl>,
## # ASBH01J <dbl+lbl>, ASBH01K <dbl+lbl>, ASBH01L <dbl+lbl>, ASBH01M <dbl+lbl>,
## # ASBH01N <dbl+lbl>, ASBH01O <dbl+lbl>, ASBH01P <dbl+lbl>, ASBH01Q <dbl+lbl>,
## # ASBH01R <dbl+lbl>, ASBH02A <dbl+lbl>, ASBH02B <dbl+lbl>, ASBH03A <dbl+lbl>,
## # ASBH03B <dbl+lbl>, ASBH03C <dbl+lbl>, ASBH03D <dbl+lbl>, …fin_ogrenci$IDCNTRY <- 246
hun_ogrenci$IDCNTRY <- 348
tur_ogrenci$IDCNTRY <- 792
kaz_ogrenci$IDCNTRY <- 398
uz_ogrenci$IDCNTRY <- 860
full_data_ogrenci <- bind_rows(fin_ogrenci,
hun_ogrenci,
tur_ogrenci,
kaz_ogrenci,
uz_ogrenci)
head(full_data_ogrenci,3)## # A tibble: 3 × 155
## IDCNTRY IDPOP IDGRADER IDGRADE WAVE IDSCHOOL IDCLASS IDSTUD ITSEX
## <dbl> <dbl+lbl> <dbl+lb> <dbl+l> <dbl+l> <dbl> <dbl> <dbl> <dbl+l>
## 1 246 1 [Populatio… 2 [Uppe… 4 1 [Spr… 5001 500101 5.00e7 2 [Boy]
## 2 246 1 [Populatio… 2 [Uppe… 4 1 [Spr… 5001 500101 5.00e7 2 [Boy]
## 3 246 1 [Populatio… 2 [Uppe… 4 1 [Spr… 5001 500101 5.00e7 2 [Boy]
## # ℹ 146 more variables: ITADMINI <dbl+lbl>, ITLANG_SA <dbl+lbl>,
## # LCID_SA <dbl+lbl>, ITLANG_SQ <dbl+lbl>, LCID_SQ <dbl+lbl>,
## # IDBOOK <dbl+lbl>, ASBG01 <dbl+lbl>, ASBG03 <dbl+lbl>, ASBG04 <dbl+lbl>,
## # ASBG05A <dbl+lbl>, ASBG05B <dbl+lbl>, ASBG05C <dbl+lbl>, ASBG05D <dbl+lbl>,
## # ASBG05E <dbl+lbl>, ASBG05F <dbl+lbl>, ASBG05G <dbl+lbl>, ASBG05H <dbl+lbl>,
## # ASBG05I <dbl+lbl>, ASBG05J <dbl+lbl>, ASBG05K <dbl+lbl>, ASBG06 <dbl+lbl>,
## # ASBG07A <dbl+lbl>, ASBG07B <dbl+lbl>, ASBG08A <dbl+lbl>, …fin_basari$IDCNTRY <- 246
hun_basari$IDCNTRY <- 348
tur_basari$IDCNTRY <- 792
kaz_basari$IDCNTRY <- 398
uz_basari$IDCNTRY <- 860
full_data_basari <- bind_rows(fin_basari,
hun_basari,
tur_basari,
kaz_basari,
uz_basari)
head(full_data_basari, 3)## # A tibble: 3 × 185
## IDCNTRY IDPOP IDGRADER IDGRADE IDSCHOOL IDTEACH IDLINK IDTEALIN ITLANG_TQ
## <dbl> <dbl+lbl> <dbl+lb> <dbl+l> <dbl> <dbl> <dbl+> <dbl> <dbl+lbl>
## 1 246 1 [Popula… 2 [Uppe… 4 5001 500101 1 50010101 43 [Finn…
## 2 246 1 [Popula… 2 [Uppe… 4 5001 500102 2 50010202 43 [Finn…
## 3 246 1 [Popula… 2 [Uppe… 4 5001 500103 3 50010303 43 [Finn…
## # ℹ 176 more variables: LCID_TQ <dbl+lbl>, isDummy <dbl+lbl>, ATBG01 <dbl+lbl>,
## # ATBG02 <dbl+lbl>, ATBG03 <dbl+lbl>, ATBG04 <dbl+lbl>, ATBG05AA <dbl+lbl>,
## # ATBG05AB <dbl+lbl>, ATBG05AC <dbl+lbl>, ATBG05AD <dbl+lbl>,
## # ATBG05BA <dbl+lbl>, ATBG05BB <dbl+lbl>, ATBG05BC <dbl+lbl>,
## # ATBG05BD <dbl+lbl>, ATBG05BE <dbl+lbl>, ATBG05BF <dbl+lbl>,
## # ATBG05BG <dbl+lbl>, ATBG05BH <dbl+lbl>, ATBG05BI <dbl+lbl>,
## # ATBG05BJ <dbl+lbl>, ATBG05BK <dbl+lbl>, ATBG06 <dbl+lbl>, …fin_okul$IDCNTRY <- 246
hun_okul$IDCNTRY <- 348
tur_okul$IDCNTRY <- 792
kaz_okul$IDCNTRY <- 398
uz_okul$IDCNTRY <- 860
full_data_okul <- bind_rows(fin_okul,
hun_okul,
tur_okul,
kaz_okul,
uz_okul)
head(full_data_okul, 3)## # A tibble: 3 × 101
## IDCNTRY IDPOP IDGRADER IDGRADE IDSCHOOL ITLANG_CQ LCID_CQ ACBG03A ACBG03B
## <dbl> <dbl+l> <dbl+lb> <dbl+l> <dbl> <dbl+lbl> <dbl+lbl> <dbl+l> <dbl+l>
## 1 246 1 [Pop… 2 [Uppe… 4 5001 43 [Finn… 1035 [Fin… 1 [0 t… 2 [11 …
## 2 246 1 [Pop… 2 [Uppe… 4 5002 32 [Swed… 2077 [Swe… 1 [0 t… 4 [Mor…
## 3 246 1 [Pop… 2 [Uppe… 4 5003 43 [Finn… 1035 [Fin… 1 [0 t… 1 [0 t…
## # ℹ 92 more variables: ACBG04 <dbl+lbl>, ACBG05A <dbl+lbl>, ACBG05B <dbl+lbl>,
## # ACBG06A <dbl+lbl>, ACBG06B <dbl+lbl>, ACBG06C <dbl+lbl>, ACBG07A <dbl+lbl>,
## # ACBG07B <dbl+lbl>, ACBG07C <dbl+lbl>, ACBG08 <dbl+lbl>, ACBG09 <dbl+lbl>,
## # ACBG10AA <dbl+lbl>, ACBG10AB <dbl+lbl>, ACBG10AC <dbl+lbl>,
## # ACBG10AD <dbl+lbl>, ACBG10AE <dbl+lbl>, ACBG10AF <dbl+lbl>,
## # ACBG10AG <dbl+lbl>, ACBG10AH <dbl+lbl>, ACBG10AI <dbl+lbl>,
## # ACBG10AJ <dbl+lbl>, ACBG10BA <dbl+lbl>, ACBG10BB <dbl+lbl>, …full_data_ev$IDCNTRY <- as.numeric(full_data_ev$IDCNTRY)
full_data_ev$IDCNTRY <- factor(
full_data_ev$IDCNTRY,
levels = c(246, 348, 792, 398, 860),
labels = c("Finlandiya", "Macaristan", "Türkiye", "Kazakistan", "Özbekistan"))
full_data_okul$IDCNTRY <- as.numeric(full_data_okul$IDCNTRY)
full_data_okul$IDCNTRY <- factor(
full_data_okul$IDCNTRY,
levels = c(246, 348, 792, 398, 860),
labels = c("Finlandiya", "Macaristan", "Türkiye", "Kazakistan", "Özbekistan"))
full_data_ogrenci$IDCNTRY <- as.numeric(full_data_ogrenci$IDCNTRY)
full_data_ogrenci$IDCNTRY <- factor(
full_data_ogrenci$IDCNTRY,
levels = c(246, 348, 792, 398, 860),
labels = c("Finlandiya", "Macaristan", "Türkiye", "Kazakistan", "Özbekistan"))
full_data_basari$IDCNTRY <- as.numeric(full_data_basari$IDCNTRY)
full_data_basari$IDCNTRY <- factor(
full_data_basari$IDCNTRY,
levels = c(246, 348, 792, 398, 860),
labels = c("Finlandiya", "Macaristan", "Türkiye", "Kazakistan", "Özbekistan"))
pirls <- bind_rows(full_data_ogrenci, full_data_basari, full_data_okul, full_data_ev)tutum <- c("ASBR07A", "ASBR07B", "ASBR07C", "ASBR07D", "ASBR07E", "ASBR07F", "ASBR07G", "ASBR07H")
ilgi <- c("ASBR01A", "ASBR01B", "ASBR01C", "ASBR01D", "ASBR01E","ASBR01F", "ASBR01G", "ASBR01H", "ASBR01I")
basari <- c("ASRIBM01", "ASRIBM02", "ASRIBM03", "ASRIBM04", "ASRIBM05")
ev <- c("ASBH01A", "ASBH01B", "ASBH01C", "ASBH01D", "ASBH01E", "ASBH01F", "ASBH01G", "ASBH01H", "ASBH01I", "ASBH01J","ASBH01K", "ASBH01L", "ASBH01M", "ASBH01N", "ASBH01O","ASBH01P", "ASBH01Q", "ASBH01R")
oz <- c("ASBR08A", "ASBR08B", "ASBR08C","ASBR08D", "ASBR08E", "ASBR08F")
tum <- c(tutum, ilgi, basari, ev, oz, "IDCNTRY")
pirls <- pirls %>%
select(all_of(tum))missing_report <- pirls %>%
summarise_all(~ sum(is.na(.))) %>%
t() %>%
as.data.frame()
colnames(missing_report) <- "Missing_Count"
missing_report$Variable <- rownames(missing_report)
missing_report$Missing_Percent <- (missing_report$Missing_Count / nrow(pirls)) * 100
head(missing_report[order(-missing_report$Missing_Percent), ], 20)## Missing_Count Variable Missing_Percent
## ASBH01C 32851 ASBH01C 57.57172
## ASBH01D 32767 ASBH01D 57.42451
## ASBH01G 32706 ASBH01G 57.31761
## ASBH01F 32684 ASBH01F 57.27905
## ASBH01K 32675 ASBH01K 57.26328
## ASBH01R 32669 ASBH01R 57.25276
## ASBH01M 32651 ASBH01M 57.22122
## ASBH01N 32632 ASBH01N 57.18792
## ASBH01L 32621 ASBH01L 57.16864
## ASBH01E 32620 ASBH01E 57.16689
## ASBH01O 32619 ASBH01O 57.16514
## ASBH01B 32615 ASBH01B 57.15813
## ASBH01Q 32602 ASBH01Q 57.13535
## ASBH01H 32592 ASBH01H 57.11782
## ASBH01J 32592 ASBH01J 57.11782
## ASBH01I 32577 ASBH01I 57.09153
## ASBH01P 32564 ASBH01P 57.06875
## ASBH01A 32489 ASBH01A 56.93731
## ASBR08F 30647 ASBR08F 53.70919
## ASBR08D 30588 ASBR08D 53.60579names(pirls)## [1] "ASBR07A" "ASBR07B" "ASBR07C" "ASBR07D" "ASBR07E" "ASBR07F"
## [7] "ASBR07G" "ASBR07H" "ASBR01A" "ASBR01B" "ASBR01C" "ASBR01D"
## [13] "ASBR01E" "ASBR01F" "ASBR01G" "ASBR01H" "ASBR01I" "ASRIBM01"
## [19] "ASRIBM02" "ASRIBM03" "ASRIBM04" "ASRIBM05" "ASBH01A" "ASBH01B"
## [25] "ASBH01C" "ASBH01D" "ASBH01E" "ASBH01F" "ASBH01G" "ASBH01H"
## [31] "ASBH01I" "ASBH01J" "ASBH01K" "ASBH01L" "ASBH01M" "ASBH01N"
## [37] "ASBH01O" "ASBH01P" "ASBH01Q" "ASBH01R" "ASBR08A" "ASBR08B"
## [43] "ASBR08C" "ASBR08D" "ASBR08E" "ASBR08F" "IDCNTRY"full_data_ogrenci <- na.omit(pirls)
names(pirls)## [1] "ASBR07A" "ASBR07B" "ASBR07C" "ASBR07D" "ASBR07E" "ASBR07F"
## [7] "ASBR07G" "ASBR07H" "ASBR01A" "ASBR01B" "ASBR01C" "ASBR01D"
## [13] "ASBR01E" "ASBR01F" "ASBR01G" "ASBR01H" "ASBR01I" "ASRIBM01"
## [19] "ASRIBM02" "ASRIBM03" "ASRIBM04" "ASRIBM05" "ASBH01A" "ASBH01B"
## [25] "ASBH01C" "ASBH01D" "ASBH01E" "ASBH01F" "ASBH01G" "ASBH01H"
## [31] "ASBH01I" "ASBH01J" "ASBH01K" "ASBH01L" "ASBH01M" "ASBH01N"
## [37] "ASBH01O" "ASBH01P" "ASBH01Q" "ASBH01R" "ASBR08A" "ASBR08B"
## [43] "ASBR08C" "ASBR08D" "ASBR08E" "ASBR08F" "IDCNTRY"missing_report <- pirls %>%
summarise_all(~ sum(is.na(.))) %>%
t() %>%
as.data.frame()
colnames(missing_report) <- "Missing_Count"
missing_report$Variable <- rownames(missing_report)
missing_report$Missing_Percent <- (missing_report$Missing_Count / nrow(pirls)) * 100
head(missing_report[order(-missing_report$Missing_Percent), ], 20)## Missing_Count Variable Missing_Percent
## ASBH01C 32851 ASBH01C 57.57172
## ASBH01D 32767 ASBH01D 57.42451
## ASBH01G 32706 ASBH01G 57.31761
## ASBH01F 32684 ASBH01F 57.27905
## ASBH01K 32675 ASBH01K 57.26328
## ASBH01R 32669 ASBH01R 57.25276
## ASBH01M 32651 ASBH01M 57.22122
## ASBH01N 32632 ASBH01N 57.18792
## ASBH01L 32621 ASBH01L 57.16864
## ASBH01E 32620 ASBH01E 57.16689
## ASBH01O 32619 ASBH01O 57.16514
## ASBH01B 32615 ASBH01B 57.15813
## ASBH01Q 32602 ASBH01Q 57.13535
## ASBH01H 32592 ASBH01H 57.11782
## ASBH01J 32592 ASBH01J 57.11782
## ASBH01I 32577 ASBH01I 57.09153
## ASBH01P 32564 ASBH01P 57.06875
## ASBH01A 32489 ASBH01A 56.93731
## ASBR08F 30647 ASBR08F 53.70919
## ASBR08D 30588 ASBR08D 53.60579#Burada bir takım sıkıntılarım vukuu buldu. Öncelikle estonya Pirls 2021'e katılmamış ben estonya yerine kısaltmalarını karıştırıp ispanya verilerini çekmişim ama fark edince çıkattım. na.omit ile veri temizledim sem için en güvenilir yol olduğu için ama bu sefer de hepsi gitti :D bu kısımda eksik verilerle nasıl çalışacağımızı öğrenmediğim için ve bu dönem yetişemeyeceği için bu kadar veri setimi düzenlediğim ve çalışmanın arka planını oturttuğum için yapay zeka desteği ile verilerimi temizlemeye çalıştım bu kısımdan sonraki veri temizleme için yaptığım şeyler bana ait değil pek kısacası...
#FIML (Full Information Maximum Likelihood), eksik verili analizlerde kullanılan modern bir yöntemdir. Geleneksel yöntemlerden (listwise deletion) farklı olarak tüm mevcut veriyi kullanır.
#Lavaan paketi bunu yaptığı için şimdilik bir şey yapmayacağım şeklinde anladım o yüzden analizlerime devam ediyorum. Zaten daha önce Jamovide yem yaparken de lavaan paketini kullanmıştım.
#NOTTTT: Buraları chunk içine yazmayın dediniz ama sonrasında chunkı show nothing yaptığımda bu kısım gözükmeyeceği için pratik olacak o yüzden buraya yazıyorum.The Current Study
Pathways to Reading Achievement: Examining Mediation Effects of Self-Concept and Home Environment
Progress In International Reading Literacy Study (PIRLS)
The current study focuses on the mechanisms through which reading attitude and reading interest influence reading achievement and consists of five hypotheses focused on two research questions.
- RQ: How are home literacy and reading self-concept related to the relationship between reading attitude and reading interest and reading achievement?
H1: Home literacy plays a significant mediating role in the relationship between reading attitude and reading achievement.
H2: Home literacy plays a significant mediating role in the relationship between reading interest and reading achievement.
H3: Reading self-concept plays a significant mediating role in the relationship between reading attitude and reading achievement.
H4: Reading self-concept plays a significant mediating role in the relationship between reading interest and reading achievement.
- RQ: Is there a significant difference in the above relationships when language family is controlled for?
H5: There is a significant difference in the above relationships by language family.
In summary, the hypothetical model is a multimodal model in which home literacy and reading self-concept mediate the effects of reading attitude and reading interest on reading achievement (Figure 1).
Figure 1. Hypothetical model for the
relationship between reading attitude and reading interest and reading
achievement.
Methodogy
Sample
…
Instruments
Reading Attitude : ASBR07A, ASBR07B, ASBR07C, ASBR07D, ASBR07E, ASBR07F, ASBR07G, ASBR07H
Reading Interest : ASBR01A, ASBR01B, ASBR01C, ASBR01D, ASBR01E, ASBR01F, ASBR01G, ASBR01H, ASBR01I
Reading Achievement: The reading achievement scale is described using data coded ASRIBM01, ASRIBM02, ASRIBM03, ASRIBM04, and ASRIBM05. These data are determined by grading students’ scores from 0 to 400 as 1, 400 to 475 as 2, 475 to 550 as 3, 550 to 625 as 4, and 625 and above as 5.
Home Literacy Environment: Scale ASBH01A, ASBH01B, ASBH01C, ASBH01D, ASBH01E, ASBH01F, ASBH01G, ASBH01H, ASBH01I, ASBH01J, ASBH01K, ASBH01L, ASBH01M, ASBH01N, ASBH01O, ASBH01P, ASBH01Q, ASBH01R
Reading Self-Concept: ASBR08A, ASBR08B, ASBR08C, ASBR08D, ASBR08E, ASBR08F
Data analysis
The above publicly available data was loaded into the R programme for statistical analysis. Data analysis was conducted in several stages. Structural Equation Modeling (SEM), a second-generation quantitative data analysis method, was used to test and validate the model. In the first step, reliability values, descriptive statistics, and correlation coefficients between composite scale scores were examined for all variables. In the second stage, confirmatory factor analysis (CFA) was conducted to test the validity of the measurement model. In the final stage, SEM was applied to test the predicted relationships of the model. Prior to the application, the assumption of multiple normality (Mardia’s coefficient) was checked.
Results
Descriptive statistics and correlation analyses
pirls$tutum_puan <- rowMeans(pirls[, tutum], na.rm = TRUE)
pirls$ilgi_puan <- rowMeans(pirls[, ilgi], na.rm = TRUE)
pirls$basari_puan <- rowMeans(pirls[, basari], na.rm = TRUE)
pirls$ev_puan <- rowMeans(pirls[, ev], na.rm = TRUE)
pirls$oz_puan <- rowMeans(pirls[, oz], na.rm = TRUE)
describe(pirls$tutum_puan)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 27137 1.9 0.58 1.75 1.83 0.56 1 4 3 0.97 0.72 0describe(pirls$ilgi_puan)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 27226 1.49 0.51 1.33 1.41 0.49 1 4 3 1.51 2.94 0describe(pirls$basari_puan)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 27415 2.99 1.07 3 3.02 1.19 1 5 4 -0.18 -0.85 0.01describe(pirls$ev_puan)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 25022 1.61 0.37 1.56 1.58 0.33 1 3 2 0.8 0.95 0describe(pirls$oz_puan)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 27045 2.47 0.54 2.5 2.53 0.49 1 4 3 -0.84 0.58 0olcekler <- pirls[, c("tutum_puan", "ilgi_puan", "basari_puan","ev_puan", "oz_puan")]
view(round(describe(olcekler), 3))
p1 <- ggplot(pirls, aes(tutum_puan)) +
geom_density(fill = "skyblue", alpha = 0.5) +
labs(title = "Reading Attitude",
x = "Reading Attitude Score",
y = "Density") +
theme_minimal() +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank(),
plot.title = element_text(size = 10),
axis.title = element_text(size = 8))
p2 <- ggplot(pirls, aes(ilgi_puan)) +
geom_density(fill = "skyblue", alpha = 0.5) +
labs(title = "Reading Interest",
x = "Reading Interest Score",
y = "Density") +
theme_minimal() +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank(),
plot.title = element_text(size = 10),
axis.title = element_text(size = 8))
p3 <- ggplot(pirls, aes(ev_puan)) +
geom_density(fill = "skyblue", alpha = 0.5) +
labs(title = "Home Literacy Environment",
x = "Home Environment Score",
y = "Density") +
theme_minimal() +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank(),
plot.title = element_text(size = 10),
axis.title = element_text(size = 8))
p4 <- ggplot(pirls, aes(oz_puan)) +
geom_density(fill = "skyblue", alpha = 0.5) +
labs(title = "Reading Self-Concept",
x = "Reading Self-Concept Score",
y = "Density") +
theme_minimal() +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank(),
plot.title = element_text(size = 10),
axis.title = element_text(size = 8))
p5 <- ggplot(pirls, aes(basari_puan)) +
geom_density(fill = "skyblue", alpha = 0.5) +
labs(title = "Reading Achievement",
x = "Reading Achievement Score",
y = "Density") +
theme_minimal() +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank(),
plot.title = element_text(size = 10),
axis.title = element_text(size = 8))
(p1 + p2) / (p3 + p4) / (p5 + plot_spacer())
olcekler <- pirls[, c("tutum_puan", "ilgi_puan", "basari_puan","ev_puan", "oz_puan")]
cor(olcekler, use = "pairwise.complete.obs")## tutum_puan ilgi_puan basari_puan ev_puan oz_puan
## tutum_puan 1.0000000 0.5346868860 0.1784155797 NA 0.1602999
## ilgi_puan 0.5346869 1.0000000000 0.0008765158 NA 0.0353600
## basari_puan 0.1784156 0.0008765158 1.0000000000 NA 0.3903747
## ev_puan NA NA NA 1 NA
## oz_puan 0.1602999 0.0353599959 0.3903747125 NA 1.0000000#burada bir takım eksik veriler başıma iş aştı o yüzden ortalama atayarak devam ettim
pirls <- pirls %>%
mutate(
tutum_puan = ifelse(is.na(tutum_puan), mean(tutum_puan, na.rm = TRUE), tutum_puan),
ilgi_puan = ifelse(is.na(ilgi_puan), mean(ilgi_puan, na.rm = TRUE), ilgi_puan),
basari_puan = ifelse(is.na(basari_puan), mean(basari_puan, na.rm = TRUE), basari_puan),
ev_puan = ifelse(is.na(ev_puan), mean(ev_puan, na.rm = TRUE), ev_puan),
oz_puan = ifelse(is.na(oz_puan), mean(oz_puan, na.rm = TRUE), oz_puan)
)
olcekler <- pirls[, c("tutum_puan", "ilgi_puan", "basari_puan","ev_puan", "oz_puan")]
cor <- cor(olcekler, use = "pairwise.complete.obs")
view(cor)| Variables | n | mean | sd | median | trimmed | mad | skew | kurtosis | se |
|---|---|---|---|---|---|---|---|---|---|
| Reading Attitude | 27137 | 1.897 | 0.582 | 1.750 | 1.832 | 0.556 | 0.974 | 0.724 | 0.004 |
| Reading Interest | 27226 | 1.494 | 0.513 | 1.333 | 1.414 | 0.494 | 1.511 | 2.938 | 0.003 |
| Reading Achievement | 27415 | 2.992 | 1.074 | 3.000 | 3.017 | 1.186 | -0.179 | -0.846 | 0.006 |
| Home Literacy Environment | 25022 | 1.606 | 0.373 | 1.556 | 1.581 | 0.329 | 0.802 | 0.955 | 0.002 |
| Reading Self-Concept | 27045 | 2.474 | 0.535 | 2.500 | 2.535 | 0.494 | -0.842 | 0.577 | 0.003 |
| Reading Attitude | Reading Interest | Reading Achievement | Home Literacy Environment | Reading Self-Concept | |
|---|---|---|---|---|---|
| Reading Attitude | 1.000000e+00 | 5.305412e-01 | 1.771641e-01 | -9.407748e-24 | 1.596063e-01 |
| Reading Interest | 5.305412e-01 | 1.000000e+00 | 8.727155e-04 | 7.862450e-24 | 3.495277e-02 |
| Reading Achievement | 1.771641e-01 | 8.727155e-04 | 1.000000e+00 | -3.184852e-24 | 3.868405e-01 |
| Home Literacy Environment | -9.407748e-24 | 7.862450e-24 | -3.184852e-24 | 1.000000e+00 | 2.740915e-24 |
| Reading Self-Concept | 1.596063e-01 | 3.495277e-02 | 3.868405e-01 | 2.740915e-24 | 1.000000e+00 |
CFA of Data Collection Tools
pirls <- pirls[, c(
"ASBR07A","ASBR07B","ASBR07C","ASBR07D","ASBR07E","ASBR07F","ASBR07G","ASBR07H",
"ASBR01A","ASBR01B","ASBR01C","ASBR01D","ASBR01E","ASBR01F","ASBR01G","ASBR01H","ASBR01I",
"ASRIBM01","ASRIBM02","ASRIBM03","ASRIBM04","ASRIBM05",
"ASBH01A","ASBH01B","ASBH01C","ASBH01D","ASBH01E","ASBH01F","ASBH01G","ASBH01H","ASBH01I",
"ASBH01J","ASBH01K","ASBH01L","ASBH01M","ASBH01N","ASBH01O","ASBH01P","ASBH01Q","ASBH01R",
"ASBR08A","ASBR08B","ASBR08C","ASBR08D","ASBR08E","ASBR08F"
)]
pirls<- data.frame(lapply(pirls, function(x) as.numeric(as.character(x))))
model_tutum <- "tutum =~ ASBR07A + ASBR07B + ASBR07C + ASBR07D + ASBR07E + ASBR07F + ASBR07G + ASBR07H"
model_ilgi <- "ilgi =~ ASBR01A + ASBR01B + ASBR01C + ASBR01D + ASBR01E + ASBR01F + ASBR01G + ASBR01H + ASBR01I"
model_basari <-"basari =~ ASRIBM01 + ASRIBM02 + ASRIBM03 + ASRIBM04 + ASRIBM05"
model_ev <- "ev=~ASBH01A + ASBH01B + ASBH01C + ASBH01D + ASBH01E + ASBH01F + ASBH01G + ASBH01H + ASBH01I + ASBH01J+ ASBH01K + ASBH01L+ ASBH01M + ASBH01N + ASBH01O + ASBH01P + ASBH01Q+ ASBH01R"
model_oz <- "oz=~ASBR08A+ASBR08B +ASBR08C+ASBR08D + ASBR08E+ASBR08F"
cfa_tutum <- cfa(model_tutum, data = pirls, missing = "fiml")
summary(cfa_tutum, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)## lavaan 0.6-20 ended normally after 34 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 24
##
## Used Total
## Number of observations 27137 57061
## Number of missing patterns 163
##
## Model Test User Model:
##
## Test statistic 3372.544
## Degrees of freedom 20
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 89143.009
## Degrees of freedom 28
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.962
## Tucker-Lewis Index (TLI) 0.947
##
## Robust Comparative Fit Index (CFI) 0.962
## Robust Tucker-Lewis Index (TLI) 0.947
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -249996.451
## Loglikelihood unrestricted model (H1) -248310.179
##
## Akaike (AIC) 500040.902
## Bayesian (BIC) 500237.910
## Sample-size adjusted Bayesian (SABIC) 500161.639
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.079
## 90 Percent confidence interval - lower 0.076
## 90 Percent confidence interval - upper 0.081
## P-value H_0: RMSEA <= 0.050 0.000
## P-value H_0: RMSEA >= 0.080 0.153
##
## Robust RMSEA 0.080
## 90 Percent confidence interval - lower 0.078
## 90 Percent confidence interval - upper 0.082
## P-value H_0: Robust RMSEA <= 0.050 0.000
## P-value H_0: Robust RMSEA >= 0.080 0.536
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.030
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## tutum =~
## ASBR07A 1.000 0.603 0.588
## ASBR07B 1.199 0.013 93.659 0.000 0.723 0.750
## ASBR07C -0.921 0.013 -69.446 0.000 -0.555 -0.510
## ASBR07D 1.298 0.014 90.972 0.000 0.782 0.723
## ASBR07E 1.261 0.013 97.282 0.000 0.760 0.816
## ASBR07F 1.013 0.011 92.384 0.000 0.611 0.736
## ASBR07G 1.053 0.012 89.589 0.000 0.635 0.706
## ASBR07H 0.958 0.011 86.387 0.000 0.577 0.675
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBR07A 1.891 0.006 302.726 0.000 1.891 1.843
## .ASBR07B 1.735 0.006 295.114 0.000 1.735 1.800
## .ASBR07C 3.102 0.007 464.765 0.000 3.102 2.847
## .ASBR07D 2.040 0.007 308.701 0.000 2.040 1.886
## .ASBR07E 1.710 0.006 300.951 0.000 1.710 1.835
## .ASBR07F 1.564 0.005 308.664 0.000 1.564 1.884
## .ASBR07G 1.643 0.005 299.217 0.000 1.643 1.826
## .ASBR07H 1.520 0.005 290.771 0.000 1.520 1.777
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBR07A 0.689 0.006 108.184 0.000 0.689 0.655
## .ASBR07B 0.407 0.004 96.748 0.000 0.407 0.438
## .ASBR07C 0.878 0.008 109.948 0.000 0.878 0.740
## .ASBR07D 0.557 0.006 99.201 0.000 0.557 0.477
## .ASBR07E 0.290 0.003 85.966 0.000 0.290 0.334
## .ASBR07F 0.316 0.003 97.883 0.000 0.316 0.458
## .ASBR07G 0.407 0.004 100.656 0.000 0.407 0.502
## .ASBR07H 0.399 0.004 102.932 0.000 0.399 0.545
## tutum 0.363 0.007 50.262 0.000 1.000 1.000
##
## R-Square:
## Estimate
## ASBR07A 0.345
## ASBR07B 0.562
## ASBR07C 0.260
## ASBR07D 0.523
## ASBR07E 0.666
## ASBR07F 0.542
## ASBR07G 0.498
## ASBR07H 0.455cfa_ilgi <- cfa(model_ilgi, data = pirls, missing = "fiml")
summary(cfa_ilgi, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)## lavaan 0.6-20 ended normally after 38 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 27
##
## Used Total
## Number of observations 27226 57061
## Number of missing patterns 197
##
## Model Test User Model:
##
## Test statistic 6446.599
## Degrees of freedom 27
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 66410.476
## Degrees of freedom 36
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.903
## Tucker-Lewis Index (TLI) 0.871
##
## Robust Comparative Fit Index (CFI) 0.903
## Robust Tucker-Lewis Index (TLI) 0.870
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -249896.361
## Loglikelihood unrestricted model (H1) -246673.061
##
## Akaike (AIC) 499846.722
## Bayesian (BIC) 500068.444
## Sample-size adjusted Bayesian (SABIC) 499982.638
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.093
## 90 Percent confidence interval - lower 0.092
## 90 Percent confidence interval - upper 0.095
## P-value H_0: RMSEA <= 0.050 0.000
## P-value H_0: RMSEA >= 0.080 1.000
##
## Robust RMSEA 0.095
## 90 Percent confidence interval - lower 0.093
## 90 Percent confidence interval - upper 0.097
## P-value H_0: Robust RMSEA <= 0.050 0.000
## P-value H_0: Robust RMSEA >= 0.080 1.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.045
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ilgi =~
## ASBR01A 1.000 0.463 0.604
## ASBR01B 1.180 0.014 82.140 0.000 0.547 0.616
## ASBR01C 0.892 0.014 62.346 0.000 0.413 0.462
## ASBR01D 0.983 0.013 78.029 0.000 0.456 0.606
## ASBR01E 1.111 0.013 87.220 0.000 0.515 0.679
## ASBR01F 1.142 0.015 78.623 0.000 0.529 0.628
## ASBR01G 0.990 0.013 77.645 0.000 0.459 0.628
## ASBR01H 0.837 0.011 73.072 0.000 0.388 0.580
## ASBR01I 0.888 0.012 75.231 0.000 0.412 0.596
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBR01A 1.517 0.005 325.656 0.000 1.517 1.978
## .ASBR01B 1.657 0.005 306.595 0.000 1.657 1.868
## .ASBR01C 1.640 0.005 299.744 0.000 1.640 1.832
## .ASBR01D 1.483 0.005 322.874 0.000 1.483 1.971
## .ASBR01E 1.477 0.005 319.632 0.000 1.477 1.950
## .ASBR01F 1.594 0.005 310.586 0.000 1.594 1.893
## .ASBR01G 1.419 0.004 318.426 0.000 1.419 1.943
## .ASBR01H 1.320 0.004 323.348 0.000 1.320 1.973
## .ASBR01I 1.331 0.004 315.671 0.000 1.331 1.925
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBR01A 0.373 0.004 101.505 0.000 0.373 0.635
## .ASBR01B 0.488 0.005 100.841 0.000 0.488 0.620
## .ASBR01C 0.630 0.006 109.411 0.000 0.630 0.787
## .ASBR01D 0.359 0.004 102.331 0.000 0.359 0.633
## .ASBR01E 0.309 0.003 95.191 0.000 0.309 0.539
## .ASBR01F 0.430 0.004 100.257 0.000 0.430 0.605
## .ASBR01G 0.323 0.003 99.642 0.000 0.323 0.605
## .ASBR01H 0.297 0.003 103.395 0.000 0.297 0.664
## .ASBR01I 0.308 0.003 102.626 0.000 0.308 0.645
## ilgi 0.215 0.004 49.821 0.000 1.000 1.000
##
## R-Square:
## Estimate
## ASBR01A 0.365
## ASBR01B 0.380
## ASBR01C 0.213
## ASBR01D 0.367
## ASBR01E 0.461
## ASBR01F 0.395
## ASBR01G 0.395
## ASBR01H 0.336
## ASBR01I 0.355cfa_basari <- cfa(model_basari, data = pirls, missing = "fiml")
summary(cfa_basari, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)## lavaan 0.6-20 ended normally after 30 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 15
##
## Used Total
## Number of observations 27415 57061
## Number of missing patterns 1
##
## Model Test User Model:
##
## Test statistic 3.369
## Degrees of freedom 5
## P-value (Chi-square) 0.643
##
## Model Test Baseline Model:
##
## Test statistic 173932.621
## Degrees of freedom 10
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -125589.166
## Loglikelihood unrestricted model (H1) -125587.482
##
## Akaike (AIC) 251208.332
## Bayesian (BIC) 251331.615
## Sample-size adjusted Bayesian (SABIC) 251283.945
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.007
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.007
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## basari =~
## ASRIBM01 1.000 1.057 0.928
## ASRIBM02 0.997 0.004 281.077 0.000 1.054 0.926
## ASRIBM03 0.999 0.004 281.554 0.000 1.056 0.926
## ASRIBM04 1.004 0.004 282.967 0.000 1.062 0.928
## ASRIBM05 1.002 0.004 281.871 0.000 1.059 0.927
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASRIBM01 3.008 0.007 437.189 0.000 3.008 2.640
## .ASRIBM02 2.997 0.007 436.152 0.000 2.997 2.634
## .ASRIBM03 2.980 0.007 432.906 0.000 2.980 2.615
## .ASRIBM04 2.986 0.007 432.074 0.000 2.986 2.610
## .ASRIBM05 2.988 0.007 433.050 0.000 2.988 2.615
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASRIBM01 0.181 0.002 92.769 0.000 0.181 0.140
## .ASRIBM02 0.185 0.002 93.404 0.000 0.185 0.143
## .ASRIBM03 0.184 0.002 93.211 0.000 0.184 0.142
## .ASRIBM04 0.183 0.002 92.718 0.000 0.183 0.139
## .ASRIBM05 0.185 0.002 93.116 0.000 0.185 0.141
## basari 1.117 0.011 101.124 0.000 1.000 1.000
##
## R-Square:
## Estimate
## ASRIBM01 0.860
## ASRIBM02 0.857
## ASRIBM03 0.858
## ASRIBM04 0.861
## ASRIBM05 0.859cfa_ev <- cfa(model_ev, data = pirls, missing = "fiml")
summary(cfa_ev, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)## lavaan 0.6-20 ended normally after 59 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 54
##
## Used Total
## Number of observations 25022 57061
## Number of missing patterns 630
##
## Model Test User Model:
##
## Test statistic 28250.077
## Degrees of freedom 135
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 128696.512
## Degrees of freedom 153
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.781
## Tucker-Lewis Index (TLI) 0.752
##
## Robust Comparative Fit Index (CFI) 0.781
## Robust Tucker-Lewis Index (TLI) 0.752
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -381706.811
## Loglikelihood unrestricted model (H1) -367581.773
##
## Akaike (AIC) 763521.623
## Bayesian (BIC) 763960.508
## Sample-size adjusted Bayesian (SABIC) 763788.898
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.091
## 90 Percent confidence interval - lower 0.090
## 90 Percent confidence interval - upper 0.092
## P-value H_0: RMSEA <= 0.050 0.000
## P-value H_0: RMSEA >= 0.080 1.000
##
## Robust RMSEA 0.093
## 90 Percent confidence interval - lower 0.092
## 90 Percent confidence interval - upper 0.094
## P-value H_0: Robust RMSEA <= 0.050 0.000
## P-value H_0: Robust RMSEA >= 0.080 1.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.061
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## ev =~
## ASBH01A 1.000 0.266 0.446
## ASBH01B 1.167 0.021 56.429 0.000 0.311 0.514
## ASBH01C 0.928 0.020 46.055 0.000 0.247 0.375
## ASBH01D 1.607 0.027 60.315 0.000 0.428 0.609
## ASBH01E 0.797 0.016 48.538 0.000 0.212 0.399
## ASBH01F 1.279 0.022 57.926 0.000 0.340 0.537
## ASBH01G 1.585 0.026 61.106 0.000 0.422 0.622
## ASBH01H 1.470 0.025 59.649 0.000 0.391 0.582
## ASBH01I 1.400 0.024 58.380 0.000 0.373 0.551
## ASBH01J 1.567 0.027 58.694 0.000 0.417 0.580
## ASBH01K 1.707 0.028 61.294 0.000 0.454 0.641
## ASBH01L 1.318 0.022 61.154 0.000 0.351 0.612
## ASBH01M 1.247 0.022 57.297 0.000 0.332 0.533
## ASBH01N 1.010 0.020 49.727 0.000 0.269 0.418
## ASBH01O 1.067 0.021 50.766 0.000 0.284 0.430
## ASBH01P 1.521 0.025 60.617 0.000 0.405 0.616
## ASBH01Q 1.412 0.023 60.176 0.000 0.376 0.603
## ASBH01R 1.372 0.025 55.737 0.000 0.365 0.515
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBH01A 1.460 0.004 383.989 0.000 1.460 2.447
## .ASBH01B 1.550 0.004 402.016 0.000 1.550 2.566
## .ASBH01C 1.633 0.004 386.172 0.000 1.633 2.478
## .ASBH01D 1.778 0.004 396.060 0.000 1.778 2.532
## .ASBH01E 1.320 0.003 388.457 0.000 1.320 2.482
## .ASBH01F 1.638 0.004 404.669 0.000 1.638 2.586
## .ASBH01G 1.705 0.004 393.680 0.000 1.705 2.514
## .ASBH01H 1.610 0.004 375.785 0.000 1.610 2.397
## .ASBH01I 1.669 0.004 387.045 0.000 1.669 2.468
## .ASBH01J 1.740 0.005 379.239 0.000 1.740 2.419
## .ASBH01K 1.778 0.005 393.276 0.000 1.778 2.510
## .ASBH01L 1.399 0.004 382.943 0.000 1.399 2.443
## .ASBH01M 1.497 0.004 376.618 0.000 1.497 2.405
## .ASBH01N 1.450 0.004 352.355 0.000 1.450 2.251
## .ASBH01O 1.571 0.004 372.570 0.000 1.571 2.380
## .ASBH01P 1.574 0.004 375.903 0.000 1.574 2.396
## .ASBH01Q 1.545 0.004 388.419 0.000 1.545 2.477
## .ASBH01R 2.045 0.005 451.193 0.000 2.045 2.883
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBH01A 0.285 0.003 106.896 0.000 0.285 0.801
## .ASBH01B 0.268 0.003 105.074 0.000 0.268 0.736
## .ASBH01C 0.373 0.003 107.555 0.000 0.373 0.860
## .ASBH01D 0.310 0.003 101.144 0.000 0.310 0.629
## .ASBH01E 0.238 0.002 107.583 0.000 0.238 0.841
## .ASBH01F 0.286 0.003 104.282 0.000 0.286 0.711
## .ASBH01G 0.282 0.003 100.974 0.000 0.282 0.613
## .ASBH01H 0.298 0.003 102.167 0.000 0.298 0.661
## .ASBH01I 0.319 0.003 104.016 0.000 0.319 0.696
## .ASBH01J 0.344 0.003 102.807 0.000 0.344 0.664
## .ASBH01K 0.295 0.003 99.458 0.000 0.295 0.589
## .ASBH01L 0.205 0.002 101.643 0.000 0.205 0.625
## .ASBH01M 0.277 0.003 104.214 0.000 0.277 0.715
## .ASBH01N 0.343 0.003 107.113 0.000 0.343 0.826
## .ASBH01O 0.355 0.003 107.025 0.000 0.355 0.815
## .ASBH01P 0.268 0.003 100.479 0.000 0.268 0.621
## .ASBH01Q 0.248 0.002 101.954 0.000 0.248 0.637
## .ASBH01R 0.370 0.004 105.154 0.000 0.370 0.735
## ev 0.071 0.002 34.601 0.000 1.000 1.000
##
## R-Square:
## Estimate
## ASBH01A 0.199
## ASBH01B 0.264
## ASBH01C 0.140
## ASBH01D 0.371
## ASBH01E 0.159
## ASBH01F 0.289
## ASBH01G 0.387
## ASBH01H 0.339
## ASBH01I 0.304
## ASBH01J 0.336
## ASBH01K 0.411
## ASBH01L 0.375
## ASBH01M 0.285
## ASBH01N 0.174
## ASBH01O 0.185
## ASBH01P 0.379
## ASBH01Q 0.363
## ASBH01R 0.265cfa_oz <- cfa(model_oz, data = pirls, missing = "fiml")
summary(cfa_oz, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)## lavaan 0.6-20 ended normally after 55 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 18
##
## Used Total
## Number of observations 27045 57061
## Number of missing patterns 56
##
## Model Test User Model:
##
## Test statistic 7194.962
## Degrees of freedom 9
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 38221.567
## Degrees of freedom 15
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.812
## Tucker-Lewis Index (TLI) 0.687
##
## Robust Comparative Fit Index (CFI) 0.812
## Robust Tucker-Lewis Index (TLI) 0.687
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -195779.095
## Loglikelihood unrestricted model (H1) -192181.614
##
## Akaike (AIC) 391594.190
## Bayesian (BIC) 391741.885
## Sample-size adjusted Bayesian (SABIC) 391684.681
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.172
## 90 Percent confidence interval - lower 0.168
## 90 Percent confidence interval - upper 0.175
## P-value H_0: RMSEA <= 0.050 0.000
## P-value H_0: RMSEA >= 0.080 1.000
##
## Robust RMSEA 0.175
## 90 Percent confidence interval - lower 0.171
## 90 Percent confidence interval - upper 0.178
## P-value H_0: Robust RMSEA <= 0.050 0.000
## P-value H_0: Robust RMSEA >= 0.080 1.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.083
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## oz =~
## ASBR08A 1.000 0.189 0.290
## ASBR08B 1.239 0.034 36.726 0.000 0.235 0.360
## ASBR08C -2.767 0.073 -37.693 0.000 -0.524 -0.468
## ASBR08D -4.415 0.106 -41.671 0.000 -0.836 -0.781
## ASBR08E -4.240 0.102 -41.614 0.000 -0.803 -0.782
## ASBR08F -3.613 0.088 -40.851 0.000 -0.684 -0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBR08A 1.381 0.004 347.245 0.000 1.381 2.118
## .ASBR08B 1.375 0.004 344.719 0.000 1.375 2.111
## .ASBR08C 2.501 0.007 364.574 0.000 2.501 2.234
## .ASBR08D 3.140 0.007 478.725 0.000 3.140 2.933
## .ASBR08E 3.289 0.006 523.150 0.000 3.289 3.203
## .ASBR08F 3.225 0.007 478.356 0.000 3.225 2.936
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBR08A 0.389 0.003 112.864 0.000 0.389 0.916
## .ASBR08B 0.369 0.003 110.627 0.000 0.369 0.870
## .ASBR08C 0.979 0.009 107.348 0.000 0.979 0.781
## .ASBR08D 0.448 0.006 68.864 0.000 0.448 0.390
## .ASBR08E 0.409 0.006 68.895 0.000 0.409 0.388
## .ASBR08F 0.739 0.008 96.717 0.000 0.739 0.612
## oz 0.036 0.002 21.461 0.000 1.000 1.000
##
## R-Square:
## Estimate
## ASBR08A 0.084
## ASBR08B 0.130
## ASBR08C 0.219
## ASBR08D 0.610
## ASBR08E 0.612
## ASBR08F 0.388fit_table <- bind_rows(glance(cfa_tutum) %>% mutate(Scale = "Reading Attitude"),
glance(cfa_ilgi) %>% mutate(Scale = "Reading Interest"),
glance(cfa_basari) %>% mutate(Scale = "Reading Achievement"),
glance(cfa_ev) %>% mutate(Scale = "Home Literacy Environment"),
glance(cfa_oz) %>% mutate(Scale = "Reading Self-Concept")
)
view(fit_table)| Variables | AGFI | AIC | BIC | CFI | chisq | RMSEA | rmsea.conf.high | SRMR | TLI |
|---|---|---|---|---|---|---|---|---|---|
| Reading Attitude | 0.9902840 | 500040.9 | 500237.9 | 0.9623796 | 3372.543739 | 0.07859435 | 0.080841864 | 0.029507049 | 0.9473314 |
| Reading Interest | 0.9594887 | 499846.7 | 500068.4 | 0.9032821 | 6446.598930 | 0.09345018 | 0.095377832 | 0.045161181 | 0.8710428 |
| Reading Achievement | 0.9999522 | 251208.3 | 251331.6 | 1.0000000 | 3.369365 | 0.00000000 | 0.006809242 | 0.000350572 | 1.0000188 |
| Home Literacy Environment | 0.9386178 | 763521.6 | 763960.5 | 0.7812797 | 28250.077218 | 0.09123086 | 0.092128486 | 0.061405420 | 0.7521170 |
| Reading Self-Concept | 0.9812449 | 391594.2 | 391741.9 | 0.8119181 | 7194.962061 | 0.17182158 | 0.175168426 | 0.083498308 | 0.6865302 |
Figure 2. The mediation model with the names of
paths.
D: Direct, M: Mediation, I: Indirect
Multiple Correlation Coefficient and Coefficient of Determination
model1 <- lm(basari_puan ~ tutum_puan,data=olcekler)
sqrt(glance(model1)[,1])## # A tibble: 1 × 1
## r.squared
## <dbl>
## 1 0.177model2 <- lm(basari_puan ~ ilgi_puan,data=olcekler)
sqrt(glance(model2)[,1])## # A tibble: 1 × 1
## r.squared
## <dbl>
## 1 0.000873model <- lm(basari_puan ~tutum_puan + ilgi_puan ,data=olcekler)
glance(model)[,1]## # A tibble: 1 × 1
## r.squared
## <dbl>
## 1 0.0435model <- 'basari_puan ~ tutum_puan + ilgi_puan'
fit1 <- sem(model, data = olcekler)
labels <- list(
tutum_puan = "Reading Attitude",
ilgi_puan = "Reading Interest",
basari_puan = "Reading Achievement")
lavaanPlot(model = fit1,
coefs = TRUE,
stand = TRUE,
sig = 0.05,
labels = labels,
graph_options = list(rankdir = "LR"))tekdegisken_tutum <- lm(basari_puan ~ tutum_puan, data = olcekler)
glance(tekdegisken_tutum)## # A tibble: 1 × 12
## r.squared adj.r.squared sigma statistic p.value df logLik AIC BIC
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.0314 0.0314 0.733 1849. 0 1 -63241. 126488. 126515.
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>tekdegisken_ilgi <- lm(basari_puan ~ ilgi_puan, data = olcekler)
glance(tekdegisken_ilgi)## # A tibble: 1 × 12
## r.squared adj.r.squared sigma statistic p.value df logLik AIC BIC
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.000000762 -0.0000168 0.745 0.0435 0.835 1 -64151. 128308. 1.28e5
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>pirls$ReadingAttitude <- rowMeans(pirls[, tutum], na.rm = TRUE)
pirls$ReadingInterest <- rowMeans(pirls[, ilgi], na.rm = TRUE)
pirls$ReadingAchievement <- rowMeans(pirls[, basari], na.rm = TRUE)
pirls$HomeLiteracyEnvironment <- rowMeans(pirls[, ev], na.rm = TRUE)
pirls$ReadingSelfConcept <- rowMeans(pirls[, oz], na.rm = TRUE)
#ortalama ile de denemeye kalktım da ondan sütun ekledim nolur nolmaz sonra kullanırım diye
tumdegisken <- lm(basari_puan ~ tutum_puan + ilgi_puan, data = olcekler)
glance(tumdegisken)## # A tibble: 1 × 12
## r.squared adj.r.squared sigma statistic p.value df logLik AIC BIC
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.0435 0.0434 0.728 1296. 0 2 -62883. 125775. 125810.
## # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int>tidy(anova(tumdegisken,tekdegisken_tutum, tekdegisken_ilgi))## # A tibble: 3 × 7
## term df.residual rss df sumsq statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 basari_puan ~ tutum_puan … 57058 30275. NA NA NA NA
## 2 basari_puan ~ tutum_puan 57059 30657. -1 -382. 720. 1.36e-157
## 3 basari_puan ~ ilgi_puan 57059 31650. 0 -993. NA NAfull_sem_model <- '
Attitude =~ ASBR07A + ASBR07B + ASBR07C + ASBR07D +
ASBR07E + ASBR07F + ASBR07G + ASBR07H
Interest =~ ASBR01A + ASBR01B + ASBR01C + ASBR01D + ASBR01E +
ASBR01F + ASBR01G + ASBR01H + ASBR01I
Achievement =~ ASRIBM01 + ASRIBM02 + ASRIBM03 + ASRIBM04 + ASRIBM05
HomeEnv =~ ASBH01A + ASBH01B + ASBH01C + ASBH01D + ASBH01E +
ASBH01F + ASBH01G + ASBH01H + ASBH01I + ASBH01J +
ASBH01K + ASBH01L + ASBH01M + ASBH01N + ASBH01O +
ASBH01P + ASBH01Q + ASBH01R
SelfConcept =~ ASBR08A + ASBR08B + ASBR08C +
ASBR08D + ASBR08E + ASBR08F
HomeEnv ~ M1*Attitude + M3*Interest
SelfConcept ~ M2*Attitude + M4*Interest
Achievement ~ I1*HomeEnv + I2*SelfConcept + D1*Attitude + D2*Interest
indirect_att_home := M1 * I1
indirect_att_self := M2 * I2
total_indirect_att := (M1 * I1) + (M2 * I2)
indirect_int_home := M3 * I1
indirect_int_self := M4 * I2
total_indirect_int := (M3 * I1) + (M4 * I2)
total_attitude := D1 + total_indirect_att
total_interest := D2 + total_indirect_int
'
for(var in tutum) {
pirls[[var]] <- ifelse(is.na(pirls[[var]]),
mean(pirls[[var]], na.rm = TRUE),
pirls[[var]])
}
for(var in ilgi) {
pirls[[var]] <- ifelse(is.na(pirls[[var]]),
mean(pirls[[var]], na.rm = TRUE),
pirls[[var]])
}
for(var in basari) {
pirls[[var]] <- ifelse(is.na(pirls[[var]]),
mean(pirls[[var]], na.rm = TRUE),
pirls[[var]])
}
for(var in ev) {
pirls[[var]] <- ifelse(is.na(pirls[[var]]),
mean(pirls[[var]], na.rm = TRUE),
pirls[[var]])
}
for(var in oz) {
pirls[[var]] <- ifelse(is.na(pirls[[var]]),
mean(pirls[[var]], na.rm = TRUE),
pirls[[var]])
}
fit_full <- sem(full_sem_model, data = pirls, std.lv = TRUE)
summary(fit_full, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)## lavaan 0.6-20 ended normally after 90 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 101
##
## Number of observations 57061
##
## Model Test User Model:
##
## Test statistic 140145.371
## Degrees of freedom 980
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 1140883.240
## Degrees of freedom 1035
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.878
## Tucker-Lewis Index (TLI) 0.871
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1589202.294
## Loglikelihood unrestricted model (H1) -1519129.609
##
## Akaike (AIC) 3178606.588
## Bayesian (BIC) 3179510.728
## Sample-size adjusted Bayesian (SABIC) 3179189.748
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.050
## 90 Percent confidence interval - lower 0.050
## 90 Percent confidence interval - upper 0.050
## P-value H_0: RMSEA <= 0.050 0.801
## P-value H_0: RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.056
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Attitude =~
## ASBR07A 0.419 0.003 149.086 0.000 0.419 0.594
## ASBR07B 0.491 0.002 200.203 0.000 0.491 0.745
## ASBR07C -0.376 0.003 -122.996 0.000 -0.376 -0.506
## ASBR07D 0.524 0.003 187.918 0.000 0.524 0.711
## ASBR07E 0.513 0.002 223.778 0.000 0.513 0.804
## ASBR07F 0.421 0.002 199.276 0.000 0.421 0.742
## ASBR07G 0.433 0.002 185.290 0.000 0.433 0.704
## ASBR07H 0.389 0.002 172.297 0.000 0.389 0.666
## Interest =~
## ASBR01A 0.347 0.002 164.921 0.000 0.347 0.658
## ASBR01B 0.387 0.002 158.358 0.000 0.387 0.637
## ASBR01C 0.269 0.003 102.508 0.000 0.269 0.440
## ASBR01D 0.303 0.002 143.515 0.000 0.303 0.588
## ASBR01E 0.359 0.002 176.534 0.000 0.359 0.693
## ASBR01F 0.349 0.002 148.514 0.000 0.349 0.605
## ASBR01G 0.296 0.002 144.689 0.000 0.296 0.592
## ASBR01H 0.247 0.002 129.388 0.000 0.247 0.540
## ASBR01I 0.267 0.002 136.202 0.000 0.267 0.563
## Achievement =~
## ASRIBM01 0.628 0.002 268.139 0.000 0.732 0.927
## ASRIBM02 0.626 0.002 267.423 0.000 0.730 0.926
## ASRIBM03 0.627 0.002 267.597 0.000 0.732 0.926
## ASRIBM04 0.630 0.002 268.212 0.000 0.736 0.928
## ASRIBM05 0.629 0.002 267.769 0.000 0.734 0.927
## HomeEnv =~
## ASBH01A 0.174 0.002 105.193 0.000 0.174 0.443
## ASBH01B 0.202 0.002 123.429 0.000 0.202 0.510
## ASBH01C 0.160 0.002 86.698 0.000 0.160 0.372
## ASBH01D 0.277 0.002 151.389 0.000 0.277 0.605
## ASBH01E 0.138 0.001 92.975 0.000 0.138 0.396
## ASBH01F 0.221 0.002 130.239 0.000 0.221 0.534
## ASBH01G 0.274 0.002 155.343 0.000 0.274 0.618
## ASBH01H 0.255 0.002 143.658 0.000 0.255 0.580
## ASBH01I 0.243 0.002 134.396 0.000 0.243 0.548
## ASBH01J 0.272 0.002 143.004 0.000 0.272 0.578
## ASBH01K 0.295 0.002 161.889 0.000 0.295 0.638
## ASBH01L 0.228 0.001 152.771 0.000 0.228 0.609
## ASBH01M 0.216 0.002 129.335 0.000 0.216 0.531
## ASBH01N 0.175 0.002 97.912 0.000 0.175 0.415
## ASBH01O 0.185 0.002 101.226 0.000 0.185 0.428
## ASBH01P 0.264 0.002 153.906 0.000 0.264 0.613
## ASBH01Q 0.245 0.002 149.927 0.000 0.245 0.600
## ASBH01R 0.237 0.002 123.794 0.000 0.237 0.511
## SelfConcept =~
## ASBR08A 0.137 0.002 69.298 0.000 0.140 0.313
## ASBR08B 0.167 0.002 85.900 0.000 0.171 0.384
## ASBR08C -0.339 0.003 -103.196 0.000 -0.347 -0.454
## ASBR08D -0.542 0.003 -189.840 0.000 -0.554 -0.760
## ASBR08E -0.526 0.003 -192.324 0.000 -0.537 -0.768
## ASBR08F -0.461 0.003 -151.244 0.000 -0.471 -0.631
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## HomeEnv ~
## Attitude (M1) 0.000 0.007 0.000 1.000 0.000 0.000
## Interest (M3) -0.000 0.007 -0.000 1.000 -0.000 -0.000
## SelfConcept ~
## Attitude (M2) 0.160 0.007 21.656 0.000 0.156 0.156
## Interest (M4) 0.063 0.008 8.378 0.000 0.062 0.062
## Achievement ~
## HomeEnv (I1) 0.000 0.005 0.000 1.000 0.000 0.000
## SelfCncpt (I2) -0.581 0.006 -99.628 0.000 -0.509 -0.509
## Attitude (D1) 0.297 0.007 40.947 0.000 0.254 0.254
## Interest (D2) -0.066 0.007 -9.208 0.000 -0.057 -0.057
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Attitude ~~
## Interest 0.659 0.003 214.643 0.000 0.659 0.659
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBR07A 0.321 0.002 158.191 0.000 0.321 0.647
## .ASBR07B 0.194 0.001 144.332 0.000 0.194 0.446
## .ASBR07C 0.411 0.003 162.181 0.000 0.411 0.744
## .ASBR07D 0.268 0.002 148.726 0.000 0.268 0.494
## .ASBR07E 0.144 0.001 132.686 0.000 0.144 0.353
## .ASBR07F 0.144 0.001 144.696 0.000 0.144 0.449
## .ASBR07G 0.191 0.001 149.556 0.000 0.191 0.505
## .ASBR07H 0.189 0.001 153.197 0.000 0.189 0.556
## .ASBR01A 0.158 0.001 146.418 0.000 0.158 0.568
## .ASBR01B 0.220 0.001 148.770 0.000 0.220 0.594
## .ASBR01C 0.302 0.002 161.849 0.000 0.302 0.806
## .ASBR01D 0.173 0.001 153.312 0.000 0.173 0.654
## .ASBR01E 0.139 0.001 141.621 0.000 0.139 0.520
## .ASBR01F 0.211 0.001 151.891 0.000 0.211 0.634
## .ASBR01G 0.162 0.001 152.988 0.000 0.162 0.649
## .ASBR01H 0.149 0.001 156.821 0.000 0.149 0.709
## .ASBR01I 0.153 0.001 155.216 0.000 0.153 0.683
## .ASRIBM01 0.087 0.001 134.175 0.000 0.087 0.140
## .ASRIBM02 0.089 0.001 135.056 0.000 0.089 0.143
## .ASRIBM03 0.089 0.001 134.845 0.000 0.089 0.142
## .ASRIBM04 0.088 0.001 134.082 0.000 0.088 0.139
## .ASRIBM05 0.089 0.001 134.635 0.000 0.089 0.141
## .ASBH01A 0.123 0.001 163.467 0.000 0.123 0.804
## .ASBH01B 0.116 0.001 161.075 0.000 0.116 0.740
## .ASBH01C 0.159 0.001 165.345 0.000 0.159 0.862
## .ASBH01D 0.133 0.001 156.039 0.000 0.133 0.634
## .ASBH01E 0.102 0.001 164.763 0.000 0.102 0.843
## .ASBH01F 0.123 0.001 160.019 0.000 0.123 0.715
## .ASBH01G 0.121 0.001 155.157 0.000 0.121 0.619
## .ASBH01H 0.129 0.001 157.628 0.000 0.129 0.664
## .ASBH01I 0.137 0.001 159.324 0.000 0.137 0.699
## .ASBH01J 0.148 0.001 157.755 0.000 0.148 0.666
## .ASBH01K 0.127 0.001 153.585 0.000 0.127 0.593
## .ASBH01L 0.088 0.001 155.736 0.000 0.088 0.629
## .ASBH01M 0.119 0.001 160.165 0.000 0.119 0.718
## .ASBH01N 0.147 0.001 164.266 0.000 0.147 0.827
## .ASBH01O 0.152 0.001 163.913 0.000 0.152 0.817
## .ASBH01P 0.116 0.001 155.483 0.000 0.116 0.624
## .ASBH01Q 0.107 0.001 156.352 0.000 0.107 0.640
## .ASBH01R 0.159 0.001 161.021 0.000 0.159 0.738
## .ASBR08A 0.180 0.001 164.681 0.000 0.180 0.902
## .ASBR08B 0.169 0.001 162.196 0.000 0.169 0.853
## .ASBR08C 0.464 0.003 158.787 0.000 0.464 0.794
## .ASBR08D 0.224 0.002 112.896 0.000 0.224 0.423
## .ASBR08E 0.201 0.002 110.121 0.000 0.201 0.410
## .ASBR08F 0.336 0.002 142.556 0.000 0.336 0.602
## Attitude 1.000 1.000 1.000
## Interest 1.000 1.000 1.000
## .Achievement 1.000 0.734 0.734
## .HomeEnv 1.000 1.000 1.000
## .SelfConcept 1.000 0.959 0.959
##
## R-Square:
## Estimate
## ASBR07A 0.353
## ASBR07B 0.554
## ASBR07C 0.256
## ASBR07D 0.506
## ASBR07E 0.647
## ASBR07F 0.551
## ASBR07G 0.495
## ASBR07H 0.444
## ASBR01A 0.432
## ASBR01B 0.406
## ASBR01C 0.194
## ASBR01D 0.346
## ASBR01E 0.480
## ASBR01F 0.366
## ASBR01G 0.351
## ASBR01H 0.291
## ASBR01I 0.317
## ASRIBM01 0.860
## ASRIBM02 0.857
## ASRIBM03 0.858
## ASRIBM04 0.861
## ASRIBM05 0.859
## ASBH01A 0.196
## ASBH01B 0.260
## ASBH01C 0.138
## ASBH01D 0.366
## ASBH01E 0.157
## ASBH01F 0.285
## ASBH01G 0.381
## ASBH01H 0.336
## ASBH01I 0.301
## ASBH01J 0.334
## ASBH01K 0.407
## ASBH01L 0.371
## ASBH01M 0.282
## ASBH01N 0.173
## ASBH01O 0.183
## ASBH01P 0.376
## ASBH01Q 0.360
## ASBH01R 0.262
## ASBR08A 0.098
## ASBR08B 0.147
## ASBR08C 0.206
## ASBR08D 0.577
## ASBR08E 0.590
## ASBR08F 0.398
## Achievement 0.266
## HomeEnv 0.000
## SelfConcept 0.041
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect_tt_hm 0.000 0.000 0.000
## indirct_tt_slf -0.093 0.004 -21.059 0.000 -0.080 -0.080
## total_ndrct_tt -0.093 0.004 -21.059 0.000 -0.080 -0.080
## indirect_nt_hm -0.000 -0.000 -0.000
## indirct_nt_slf -0.037 0.004 -8.378 0.000 -0.031 -0.031
## total_ndrct_nt -0.037 0.004 -8.378 0.000 -0.031 -0.031
## total_attitude 0.204 0.008 26.186 0.000 0.174 0.174
## total_interest -0.103 0.008 -12.983 0.000 -0.088 -0.088fit_full <- sem(full_sem_model, data = pirls, std.lv = TRUE)
summary(fit_full, fit.measures = TRUE, standardized = TRUE, rsquare = TRUE)## lavaan 0.6-20 ended normally after 90 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 101
##
## Number of observations 57061
##
## Model Test User Model:
##
## Test statistic 140145.371
## Degrees of freedom 980
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 1140883.240
## Degrees of freedom 1035
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.878
## Tucker-Lewis Index (TLI) 0.871
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1589202.294
## Loglikelihood unrestricted model (H1) -1519129.609
##
## Akaike (AIC) 3178606.588
## Bayesian (BIC) 3179510.728
## Sample-size adjusted Bayesian (SABIC) 3179189.748
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.050
## 90 Percent confidence interval - lower 0.050
## 90 Percent confidence interval - upper 0.050
## P-value H_0: RMSEA <= 0.050 0.801
## P-value H_0: RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.056
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Attitude =~
## ASBR07A 0.419 0.003 149.086 0.000 0.419 0.594
## ASBR07B 0.491 0.002 200.203 0.000 0.491 0.745
## ASBR07C -0.376 0.003 -122.996 0.000 -0.376 -0.506
## ASBR07D 0.524 0.003 187.918 0.000 0.524 0.711
## ASBR07E 0.513 0.002 223.778 0.000 0.513 0.804
## ASBR07F 0.421 0.002 199.276 0.000 0.421 0.742
## ASBR07G 0.433 0.002 185.290 0.000 0.433 0.704
## ASBR07H 0.389 0.002 172.297 0.000 0.389 0.666
## Interest =~
## ASBR01A 0.347 0.002 164.921 0.000 0.347 0.658
## ASBR01B 0.387 0.002 158.358 0.000 0.387 0.637
## ASBR01C 0.269 0.003 102.508 0.000 0.269 0.440
## ASBR01D 0.303 0.002 143.515 0.000 0.303 0.588
## ASBR01E 0.359 0.002 176.534 0.000 0.359 0.693
## ASBR01F 0.349 0.002 148.514 0.000 0.349 0.605
## ASBR01G 0.296 0.002 144.689 0.000 0.296 0.592
## ASBR01H 0.247 0.002 129.388 0.000 0.247 0.540
## ASBR01I 0.267 0.002 136.202 0.000 0.267 0.563
## Achievement =~
## ASRIBM01 0.628 0.002 268.139 0.000 0.732 0.927
## ASRIBM02 0.626 0.002 267.423 0.000 0.730 0.926
## ASRIBM03 0.627 0.002 267.597 0.000 0.732 0.926
## ASRIBM04 0.630 0.002 268.212 0.000 0.736 0.928
## ASRIBM05 0.629 0.002 267.769 0.000 0.734 0.927
## HomeEnv =~
## ASBH01A 0.174 0.002 105.193 0.000 0.174 0.443
## ASBH01B 0.202 0.002 123.429 0.000 0.202 0.510
## ASBH01C 0.160 0.002 86.698 0.000 0.160 0.372
## ASBH01D 0.277 0.002 151.389 0.000 0.277 0.605
## ASBH01E 0.138 0.001 92.975 0.000 0.138 0.396
## ASBH01F 0.221 0.002 130.239 0.000 0.221 0.534
## ASBH01G 0.274 0.002 155.343 0.000 0.274 0.618
## ASBH01H 0.255 0.002 143.658 0.000 0.255 0.580
## ASBH01I 0.243 0.002 134.396 0.000 0.243 0.548
## ASBH01J 0.272 0.002 143.004 0.000 0.272 0.578
## ASBH01K 0.295 0.002 161.889 0.000 0.295 0.638
## ASBH01L 0.228 0.001 152.771 0.000 0.228 0.609
## ASBH01M 0.216 0.002 129.335 0.000 0.216 0.531
## ASBH01N 0.175 0.002 97.912 0.000 0.175 0.415
## ASBH01O 0.185 0.002 101.226 0.000 0.185 0.428
## ASBH01P 0.264 0.002 153.906 0.000 0.264 0.613
## ASBH01Q 0.245 0.002 149.927 0.000 0.245 0.600
## ASBH01R 0.237 0.002 123.794 0.000 0.237 0.511
## SelfConcept =~
## ASBR08A 0.137 0.002 69.298 0.000 0.140 0.313
## ASBR08B 0.167 0.002 85.900 0.000 0.171 0.384
## ASBR08C -0.339 0.003 -103.196 0.000 -0.347 -0.454
## ASBR08D -0.542 0.003 -189.840 0.000 -0.554 -0.760
## ASBR08E -0.526 0.003 -192.324 0.000 -0.537 -0.768
## ASBR08F -0.461 0.003 -151.244 0.000 -0.471 -0.631
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## HomeEnv ~
## Attitude (M1) 0.000 0.007 0.000 1.000 0.000 0.000
## Interest (M3) -0.000 0.007 -0.000 1.000 -0.000 -0.000
## SelfConcept ~
## Attitude (M2) 0.160 0.007 21.656 0.000 0.156 0.156
## Interest (M4) 0.063 0.008 8.378 0.000 0.062 0.062
## Achievement ~
## HomeEnv (I1) 0.000 0.005 0.000 1.000 0.000 0.000
## SelfCncpt (I2) -0.581 0.006 -99.628 0.000 -0.509 -0.509
## Attitude (D1) 0.297 0.007 40.947 0.000 0.254 0.254
## Interest (D2) -0.066 0.007 -9.208 0.000 -0.057 -0.057
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Attitude ~~
## Interest 0.659 0.003 214.643 0.000 0.659 0.659
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .ASBR07A 0.321 0.002 158.191 0.000 0.321 0.647
## .ASBR07B 0.194 0.001 144.332 0.000 0.194 0.446
## .ASBR07C 0.411 0.003 162.181 0.000 0.411 0.744
## .ASBR07D 0.268 0.002 148.726 0.000 0.268 0.494
## .ASBR07E 0.144 0.001 132.686 0.000 0.144 0.353
## .ASBR07F 0.144 0.001 144.696 0.000 0.144 0.449
## .ASBR07G 0.191 0.001 149.556 0.000 0.191 0.505
## .ASBR07H 0.189 0.001 153.197 0.000 0.189 0.556
## .ASBR01A 0.158 0.001 146.418 0.000 0.158 0.568
## .ASBR01B 0.220 0.001 148.770 0.000 0.220 0.594
## .ASBR01C 0.302 0.002 161.849 0.000 0.302 0.806
## .ASBR01D 0.173 0.001 153.312 0.000 0.173 0.654
## .ASBR01E 0.139 0.001 141.621 0.000 0.139 0.520
## .ASBR01F 0.211 0.001 151.891 0.000 0.211 0.634
## .ASBR01G 0.162 0.001 152.988 0.000 0.162 0.649
## .ASBR01H 0.149 0.001 156.821 0.000 0.149 0.709
## .ASBR01I 0.153 0.001 155.216 0.000 0.153 0.683
## .ASRIBM01 0.087 0.001 134.175 0.000 0.087 0.140
## .ASRIBM02 0.089 0.001 135.056 0.000 0.089 0.143
## .ASRIBM03 0.089 0.001 134.845 0.000 0.089 0.142
## .ASRIBM04 0.088 0.001 134.082 0.000 0.088 0.139
## .ASRIBM05 0.089 0.001 134.635 0.000 0.089 0.141
## .ASBH01A 0.123 0.001 163.467 0.000 0.123 0.804
## .ASBH01B 0.116 0.001 161.075 0.000 0.116 0.740
## .ASBH01C 0.159 0.001 165.345 0.000 0.159 0.862
## .ASBH01D 0.133 0.001 156.039 0.000 0.133 0.634
## .ASBH01E 0.102 0.001 164.763 0.000 0.102 0.843
## .ASBH01F 0.123 0.001 160.019 0.000 0.123 0.715
## .ASBH01G 0.121 0.001 155.157 0.000 0.121 0.619
## .ASBH01H 0.129 0.001 157.628 0.000 0.129 0.664
## .ASBH01I 0.137 0.001 159.324 0.000 0.137 0.699
## .ASBH01J 0.148 0.001 157.755 0.000 0.148 0.666
## .ASBH01K 0.127 0.001 153.585 0.000 0.127 0.593
## .ASBH01L 0.088 0.001 155.736 0.000 0.088 0.629
## .ASBH01M 0.119 0.001 160.165 0.000 0.119 0.718
## .ASBH01N 0.147 0.001 164.266 0.000 0.147 0.827
## .ASBH01O 0.152 0.001 163.913 0.000 0.152 0.817
## .ASBH01P 0.116 0.001 155.483 0.000 0.116 0.624
## .ASBH01Q 0.107 0.001 156.352 0.000 0.107 0.640
## .ASBH01R 0.159 0.001 161.021 0.000 0.159 0.738
## .ASBR08A 0.180 0.001 164.681 0.000 0.180 0.902
## .ASBR08B 0.169 0.001 162.196 0.000 0.169 0.853
## .ASBR08C 0.464 0.003 158.787 0.000 0.464 0.794
## .ASBR08D 0.224 0.002 112.896 0.000 0.224 0.423
## .ASBR08E 0.201 0.002 110.121 0.000 0.201 0.410
## .ASBR08F 0.336 0.002 142.556 0.000 0.336 0.602
## Attitude 1.000 1.000 1.000
## Interest 1.000 1.000 1.000
## .Achievement 1.000 0.734 0.734
## .HomeEnv 1.000 1.000 1.000
## .SelfConcept 1.000 0.959 0.959
##
## R-Square:
## Estimate
## ASBR07A 0.353
## ASBR07B 0.554
## ASBR07C 0.256
## ASBR07D 0.506
## ASBR07E 0.647
## ASBR07F 0.551
## ASBR07G 0.495
## ASBR07H 0.444
## ASBR01A 0.432
## ASBR01B 0.406
## ASBR01C 0.194
## ASBR01D 0.346
## ASBR01E 0.480
## ASBR01F 0.366
## ASBR01G 0.351
## ASBR01H 0.291
## ASBR01I 0.317
## ASRIBM01 0.860
## ASRIBM02 0.857
## ASRIBM03 0.858
## ASRIBM04 0.861
## ASRIBM05 0.859
## ASBH01A 0.196
## ASBH01B 0.260
## ASBH01C 0.138
## ASBH01D 0.366
## ASBH01E 0.157
## ASBH01F 0.285
## ASBH01G 0.381
## ASBH01H 0.336
## ASBH01I 0.301
## ASBH01J 0.334
## ASBH01K 0.407
## ASBH01L 0.371
## ASBH01M 0.282
## ASBH01N 0.173
## ASBH01O 0.183
## ASBH01P 0.376
## ASBH01Q 0.360
## ASBH01R 0.262
## ASBR08A 0.098
## ASBR08B 0.147
## ASBR08C 0.206
## ASBR08D 0.577
## ASBR08E 0.590
## ASBR08F 0.398
## Achievement 0.266
## HomeEnv 0.000
## SelfConcept 0.041
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect_tt_hm 0.000 0.000 0.000
## indirct_tt_slf -0.093 0.004 -21.059 0.000 -0.080 -0.080
## total_ndrct_tt -0.093 0.004 -21.059 0.000 -0.080 -0.080
## indirect_nt_hm -0.000 -0.000 -0.000
## indirct_nt_slf -0.037 0.004 -8.378 0.000 -0.031 -0.031
## total_ndrct_nt -0.037 0.004 -8.378 0.000 -0.031 -0.031
## total_attitude 0.204 0.008 26.186 0.000 0.174 0.174
## total_interest -0.103 0.008 -12.983 0.000 -0.088 -0.088fitMeasures(fit_full, c("chisq", "df", "pvalue", "cfi", "tli",
"rmsea", "rmsea.ci.lower", "rmsea.ci.upper",
"srmr", "nfi", "ifi", "rfi"))## chisq df pvalue cfi tli
## 140145.371 980.000 0.000 0.878 0.871
## rmsea rmsea.ci.lower rmsea.ci.upper srmr nfi
## 0.050 0.050 0.050 0.056 0.877
## ifi rfi
## 0.878 0.870Model Fit Indices
uyum <- fitMeasures(fit_full, c("chisq", "df", "pvalue", "cfi", "tli",
"rmsea", "rmsea.ci.lower", "rmsea.ci.upper",
"srmr", "nfi", "ifi", "rfi"))
uyum_tablo <- data.frame(
Index = c("χ²", "df", "p-value", "CFI", "TLI", "RMSEA",
"RMSEA Lower", "RMSEA Upper", "SRMR", "NFI", "IFI", "RFI"),
Value = round(uyum, 3),
Criteria = c("", "", ">0.05", "≥0.90", "≥0.90", "≤0.08",
"", "", "≤0.08", "≥0.90", "≥0.90", "≥0.90"),
Result = c("", "", ifelse(uyum[3] > 0.05, "✓", "✗"),
ifelse(uyum[4] >= 0.90, "✓", "Acceptable"),
ifelse(uyum[5] >= 0.90, "✓", "Acceptable"),
ifelse(uyum[6] <= 0.08, "✓", "✗"),
"", "",
ifelse(uyum[8] <= 0.08, "✓", "✗"),
ifelse(uyum[9] >= 0.90, "✓", "Acceptable"),
ifelse(uyum[10] >= 0.90, "✓", "Acceptable"),
ifelse(uyum[11] >= 0.90, "✓", "Acceptable"))
)
View(uyum_tablo)
write.csv(uyum_tablo, "1_model_uyum.csv", row.names = FALSE)| Index | Value | Criteria | Result | |
|---|---|---|---|---|
| chisq | χ² | 140145.371 | ||
| df | df | 980.000 | ||
| pvalue | p-value | 0.000 | >0.05 | ✗ |
| cfi | CFI | 0.878 | ≥0.90 | Acceptable |
| tli | TLI | 0.871 | ≥0.90 | Acceptable |
| rmsea | RMSEA | 0.050 | ≤0.08 | ✓ |
| rmsea.ci.lower | RMSEA Lower | 0.050 | ||
| rmsea.ci.upper | RMSEA Upper | 0.050 | ||
| srmr | SRMR | 0.056 | ≤0.08 | ✓ |
| nfi | NFI | 0.877 | ≥0.90 | Acceptable |
| ifi | IFI | 0.878 | ≥0.90 | Acceptable |
| rfi | RFI | 0.870 | ≥0.90 | Acceptable |
The structural equation model demonstrated acceptable to good fit indices. The RMSEA value of 0.050 (90% CI [0.050, 0.050]) and SRMR value of 0.056 both fell within acceptable ranges (≤0.08), indicating good model fit. However, the comparative fit indices (CFI = 0.878, TLI = 0.871, NFI = 0.877, IFI = 0.878, RFI = 0.870) were slightly below the ideal threshold of 0.90, though still within the acceptable range (>0.85). The significant chi-square test (χ² = 140145.371, df = 980, p < 0.001) was expected given the large sample size (N = 57,061). Overall, the model demonstrated adequate fit to the data, justifying further examination of the structural paths.
Structural Model Coefficients (Regression Paths)
yapisal <- parameterEstimates(fit_full, standardized = TRUE) %>%
filter(op == "~") %>%
select(lhs, rhs, est, se, z = z, pvalue, std.all) %>%
mutate(
sig = case_when(
pvalue < 0.001 ~ "***",
pvalue < 0.01 ~ "**",
pvalue < 0.05 ~ "*",
TRUE ~ "ns"))
View(yapisal)
write.csv(yapisal, "2_structural_paths.csv", row.names = FALSE)| lhs | rhs | est | se | z | pvalue | std.all | sig |
|---|---|---|---|---|---|---|---|
| HomeEnv | Attitude | 1.648105e-25 | 0.006935399 | 2.376366e-23 | 1 | 1.648105e-25 | ns |
| HomeEnv | Interest | -1.946887e-25 | 0.007110071 | -2.738210e-23 | 1 | -1.946887e-25 | ns |
| SelfConcept | Attitude | 1.597476e-01 | 0.007376711 | 2.165567e+01 | 0 | 1.564381e-01 | *** |
| SelfConcept | Interest | 6.300088e-02 | 0.007519747 | 8.378058e+00 | 0 | 6.169565e-02 | *** |
| Achievement | HomeEnv | 3.431988e-26 | 0.004723839 | 7.265251e-24 | 1 | 2.940463e-26 | ns |
| Achievement | SelfConcept | -5.812168e-01 | 0.005833896 | -9.962756e+01 | 0 | -5.085109e-01 | *** |
| Achievement | Attitude | 2.965158e-01 | 0.007241424 | 4.094717e+01 | 0 | 2.540493e-01 | *** |
| Achievement | Interest | -6.608165e-02 | 0.007176928 | -9.207512e+00 | 0 | -5.661753e-02 | *** |
The structural model revealed significant paths through Reading Self-Concept but not through Home Literacy Environment. Reading Attitude (β = 0.156, p < 0.001) and Reading Interest (β = 0.062, p < 0.001) both significantly predicted Reading Self-Concept as a mediator variable. However, neither Reading Attitude (β = 0.000, p = 1.000) nor Reading Interest (β = 0.000, p = 1.000) predicted Home Literacy Environment, and Home Environment showed no significant effect on Reading Achievement (β = 0.000, p = 1.000), indicating that Home Literacy Environment did not function as a mediator in this model. Regarding direct effects on Reading Achievement, Reading Attitude demonstrated a significant positive effect (β = 0.254, p < 0.001), while Reading Self-Concept showed an unexpected significant negative effect (β = -0.509, p < 0.001). Reading Interest also exhibited a small but significant negative direct effect on Achievement (β = -0.057, p < 0.001). These findings suggest that Reading Self-Concept partially mediates the relationship between reading attitudes/interest and achievement, though the negative direction warrants further investigation.
Indirect Effects
dolayli <- parameterEstimates(fit_full, standardized = TRUE) %>%
filter(op == ":=") %>%
select(label, est, se, z, pvalue, std.all) %>%
mutate(
sig = case_when(
pvalue < 0.001 ~ "***",
pvalue < 0.01 ~ "**",
pvalue < 0.05 ~ "*",
TRUE ~ "ns"))
View(dolayli)
write.csv(dolayli, "3_indirect_effects.csv", row.names = FALSE)| label | est | se | z | pvalue | std.all | sig |
|---|---|---|---|---|---|---|
| indirect_att_home | 5.656275e-51 | 0.000000000 | NA | NA | 4.846191e-51 | ns |
| indirect_att_self | -9.284801e-02 | 0.004408858 | -21.059423 | 0 | -7.955045e-02 | *** |
| total_indirect_att | -9.284801e-02 | 0.004408858 | -21.059423 | 0 | -7.955045e-02 | *** |
| indirect_int_home | -6.681691e-51 | 0.000000000 | NA | NA | -5.724749e-51 | ns |
| indirect_int_self | -3.661717e-02 | 0.004370747 | -8.377782 | 0 | -3.137291e-02 | *** |
| total_indirect_int | -3.661717e-02 | 0.004370747 | -8.377782 | 0 | -3.137291e-02 | *** |
| total_attitude | 2.036678e-01 | 0.007777831 | 26.185686 | 0 | 1.744988e-01 | *** |
| total_interest | -1.026988e-01 | 0.007910529 | -12.982547 | 0 | -8.799044e-02 | *** |
The mediation analysis revealed that Reading Self-Concept served as a significant mediator, while Home Literacy Environment did not. For Reading Attitude, the indirect effect through Self-Concept was significant but negative (β = -0.080, p < 0.001), resulting in a total indirect effect of -0.080. Similarly, Reading Interest showed a significant negative indirect effect through Self-Concept (β = -0.031, p < 0.001). In contrast, both indirect paths through Home Literacy Environment were non-significant (β = 0.000, p > 0.05). The total effects showed that Reading Attitude maintained a positive overall influence on Achievement (β = 0.174, p < 0.001), combining its positive direct effect (0.254) with the negative indirect effect (-0.080). However, Reading Interest demonstrated a negative total effect on Achievement (β = -0.088, p < 0.001), suggesting a suppression effect. These findings indicate partial mediation through Reading Self-Concept, though the negative direction of the indirect effects contradicts theoretical expectations and warrants further investigation into the nature of this relationship.
R² (Explained Variance)
r2_values <- inspect(fit_full, "r2")
r2_tablo <- data.frame(
Variable = names(r2_values),
R_Square = round(r2_values, 3),
Percentage = paste0(round(r2_values * 100, 1), "%"))
View(r2_tablo)
write.csv(r2_tablo, "4_r_square.csv", row.names = FALSE)| Variable | Variable’ | R_Square | Percentage |
|---|---|---|---|
| ASBR07A | ASBR07A | 0.353 | 35.3% |
| ASBR07B | ASBR07B | 0.554 | 55.4% |
| ASBR07C | ASBR07C | 0.256 | 25.6% |
| ASBR07D | ASBR07D | 0.506 | 50.6% |
| ASBR07E | ASBR07E | 0.647 | 64.7% |
| ASBR07F | ASBR07F | 0.551 | 55.1% |
| ASBR07G | ASBR07G | 0.495 | 49.5% |
| ASBR07H | ASBR07H | 0.444 | 44.4% |
| ASBR01A | ASBR01A | 0.432 | 43.2% |
| ASBR01B | ASBR01B | 0.406 | 40.6% |
| ASBR01C | ASBR01C | 0.194 | 19.4% |
| ASBR01D | ASBR01D | 0.346 | 34.6% |
| ASBR01E | ASBR01E | 0.480 | 48% |
| ASBR01F | ASBR01F | 0.366 | 36.6% |
| ASBR01G | ASBR01G | 0.351 | 35.1% |
| ASBR01H | ASBR01H | 0.291 | 29.1% |
| ASBR01I | ASBR01I | 0.317 | 31.7% |
| ASRIBM01 | ASRIBM01 | 0.860 | 86% |
| ASRIBM02 | ASRIBM02 | 0.857 | 85.7% |
| ASRIBM03 | ASRIBM03 | 0.858 | 85.8% |
| ASRIBM04 | ASRIBM04 | 0.861 | 86.1% |
| ASRIBM05 | ASRIBM05 | 0.859 | 85.9% |
| ASBH01A | ASBH01A | 0.196 | 19.6% |
| ASBH01B | ASBH01B | 0.260 | 26% |
| ASBH01C | ASBH01C | 0.138 | 13.8% |
| ASBH01D | ASBH01D | 0.366 | 36.6% |
| ASBH01E | ASBH01E | 0.157 | 15.7% |
| ASBH01F | ASBH01F | 0.285 | 28.5% |
| ASBH01G | ASBH01G | 0.381 | 38.1% |
| ASBH01H | ASBH01H | 0.336 | 33.6% |
| ASBH01I | ASBH01I | 0.301 | 30.1% |
| ASBH01J | ASBH01J | 0.334 | 33.4% |
| ASBH01K | ASBH01K | 0.407 | 40.7% |
| ASBH01L | ASBH01L | 0.371 | 37.1% |
| ASBH01M | ASBH01M | 0.282 | 28.2% |
| ASBH01N | ASBH01N | 0.173 | 17.3% |
| ASBH01O | ASBH01O | 0.183 | 18.3% |
| ASBH01P | ASBH01P | 0.376 | 37.6% |
| ASBH01Q | ASBH01Q | 0.360 | 36% |
| ASBH01R | ASBH01R | 0.262 | 26.2% |
| ASBR08A | ASBR08A | 0.098 | 9.8% |
| ASBR08B | ASBR08B | 0.147 | 14.7% |
| ASBR08C | ASBR08C | 0.206 | 20.6% |
| ASBR08D | ASBR08D | 0.577 | 57.7% |
| ASBR08E | ASBR08E | 0.590 | 59% |
| ASBR08F | ASBR08F | 0.398 | 39.8% |
| Achievement | Achievement | 0.266 | 26.6% |
| HomeEnv | HomeEnv | 0.000 | 0% |
| SelfConcept | SelfConcept | 0.041 | 4.1% |
The R² values indicate the proportion of variance in endogenous variables explained by their predictors. Reading Achievement showed moderate variance explained (R² = 0.266, 26.6%), suggesting that Reading Attitude, Reading Interest, Home Literacy Environment, and Reading Self-Concept collectively accounted for approximately one-quarter of the variance in reading achievement scores. Reading Self-Concept demonstrated low but significant variance explained (R² = 0.041, 4.1%), indicating that Reading Attitude and Interest explained only a small portion of self-concept variance. Most notably, Home Literacy Environment showed no variance explained (R² = 0.000, 0.0%) by Reading Attitude and Interest, confirming that these variables did not predict home environment in this model. This finding aligns with the non-significant paths to Home Literacy Environment observed in the structural model, explaining why it failed to function as a mediator.
Path
#R da çizemedim de çizdiremedim de pes ettim canvadan yapacağımNOTE: In the PIRLS 2021 data structure, student (ASG), school (ACG), and achievement (ATG) files for some countries are presented in two different versions: A5 and R5. This is related to the use of two different survey and test forms in the data collection process in these countries. In countries with large sample sizes, such as Finland, Estonia, and Hungary, some of the items administered to students were administered on Form A (A5), while others were administered on Form R (R5). This practice is a result of the rotated booklet design approach used to reduce student response load, balance test time, and obtain more comprehensive data. Because R5 files generally contain all items and full sample information, using R5 versions in analyses is considered more compatible with international reporting standards.
Öğrenme Günlüğü: Eksik veriler başıma iş aştı.
Modelim de zaten çok kötü oldu. o yüzden dil ailesini dahil edecek
zamanım da kalmadı. bu halityle paylaşıyorum. notlarımı da yazamadım.
öğrenme günlüğü için şunu diyebilirim ama regresyon notları ile hepsini
kurcalamış oldum. Korelasyon analizleri yaparken Pearson ve Spearman
korelasyonlarını hesaplamayı ve korelasyon matrisleri oluşturmayı
öğrendim. corrplot paketi sayesinde korelasyonları
grafiklerle görselleştirdim ve bu görselleri daha anlaşılır hale
getirmeyi başardım. Bu süreç bana, sayılarla çalışmanın sadece hesaplama
değil aynı zamanda yorumlama gerektirdiğini fark ettirdi. Regresyon
analizlerinde basit ve çoklu regresyon modelleri kurmayı öğrendim.
Bağımsız değişkenleri modele eklemeyi, sonuçları yorumlamayı
ve R² değerlerinin ne anlama geldiğini daha iyi
kavradım. Ayrıca modellerin varsayımlarını test etmeyi, artıklar
üzerinden grafikler oluşturmayı ve çoklu bağlantı problemlerini
incelemeyi deneyimledim. Yapısal eşitlik modellemesi ve doğrulayıcı
faktör analiziyle tanışmam, benim için bu sürecin en öğretici
kısımlarından biri oldu. lavaan paketini kullanarak model
kurmayı, model uyum indekslerini okumayı ve maddelerin faktör yüklerini
incelemeyi öğrendim. Lavaan paketini kullanan jamovi ile yem daha önce
yapmnıştım ona göre tbiii ki çok karmaşık geldi ama daha deneyerek
çözeceğim.