pacman::p_load(openxlsx)
dta <- read.xlsx(xlsxFile ="ANA_V2(遺漏值改1)(有加權).xlsx", sheet = 'ANA')資料結構
dta$sleep_grp<-cut(dta$T_Sleep, c(0, 7, 9, 10), c("poor", "moderate", "good"))
dta$sleep_grp1<-cut(dta$T_Sleep, c(0, 7, 9, 10), c("1", "2", "3"))
dta$sleep1_1<-cut(dta$T_Sleep, c(0, 7, 9, 10), c("1", "2", "3"))
dta$sleep2_1<-cut(dta$T_Sleep, c(0, 7, 9, 10), c("1", "2", "3"))
dta$sleep3_1<-cut(dta$T_Sleep, c(0, 7, 9, 10), c("1", "2", "3"))
dta$sleep4_1<-cut(dta$T_Sleep, c(0, 7, 9, 10), c("1", "2", "3"))
dta$sleep5_1<-cut(dta$T_Sleep, c(0, 7, 9, 10), c("1", "2", "3"))將睡眠進行分組 0~7poor ，8~9moderate， 10 good。 參考以下文章 Dalmases, M., Benítez, I. D., Mas, A., Garcia-Codina, O., Medina-Bustos, A., Escarrabill, J., … & de Batlle, J. (2018). Assessing sleep health in a European population: results of the Catalan Health Survey 2015. PloS one, 13(4), e0194495.
head(dta)pacman::p_load(ggplot2,Hmisc, MASS, reshape2,vcd)將五題睡眠進行”poor”, “moderate”, “good”分組後，在性別、年齡、健康識能、KAP上資料分布皆相同。
Sleep1 您對您的睡眠狀況滿意嗎?
pacman::p_load(gtsummary)
#sleep2_1, sleep3_1, sleep4_1, sleep5_1
sleep1<- dta %>%
select(SEX, AGE,ATOTAL,K_SUM,A_SUM,P_SUM, LIVING,LIVING1_1,LIVING1_11, LIVING1_12,sleep1_1) %>%
tbl_summary(by = sleep1_1, label = list(SEX ~ "Sex", AGE ~ "Age", ATOTAL ~ "Health awareness",K_SUM ~ "Knoeledge ", A_SUM ~ "Attitude", P_SUM ~ "Practice")) %>%
add_p()%>%
add_stat_label() %>%
bold_labels() %>%
modify_header(list(label ~ "**Variable**", all_stat_cols() ~ "**{level}**")) %>%
modify_spanning_header(all_stat_cols() ~ "**Group**") %>%
as_gt() %>%
gt::tab_header(
title = gt::md("**Table 1. Sleep Satisfaction **"))## 1 observations missing `sleep1_1` have been removed. To include these observations, use `forcats::fct_explicit_na()` on `sleep1_1` column before passing to `tbl_summary()`.## There was an error in 'add_p()/add_difference()' for variable 'LIVING1_11', p-value omitted:
## Error in stats::fisher.test(c(1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, : FEXACT 錯誤碼 6. LDKEY=618 對此問題而言太小，
## (ii := key2[itp=699] = 1812637, ldstp=18540)
## 嘗試增加工作空間的大小並盡可能 'mult'sleep1| **Table 1. Sleep Satisfaction ** | ||||
|---|---|---|---|---|
| Variable | Group | p-value1 | ||
| 1 | 2 | 3 | ||
| Sex, n (%) | 195 (47%) | 82 (47%) | 28 (47%) | >0.9 |
| Age, Median (IQR) | 47 (24, 57) | 42 (24, 56) | 50 (25, 62) | 0.3 |
| Health awareness, Median (IQR) | 94 (80, 110) | 95 (77, 110) | 96 (80, 109) | >0.9 |
| Knoeledge , Median (IQR) | 7.39 (5.72, 8.44) | 7.39 (6.13, 8.45) | 6.97 (5.77, 7.62) | 0.2 |
| Attitude, Median (IQR) | 24.4 (21.4, 27.0) | 24.4 (21.0, 27.8) | 23.7 (20.1, 27.0) | 0.6 |
| Practice, Median (IQR) | 38 (33, 43) | 38 (33, 43) | 38 (32, 41) | 0.6 |
| LIVING, n (%) | 346 (84%) | 152 (87%) | 55 (92%) | 0.3 |
| LIVING1_1, n (%) | 0.4 | |||
| 0 | 277 (67%) | 115 (66%) | 41 (68%) | |
| 1 | 69 (17%) | 37 (21%) | 14 (23%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_11, n (%) | ||||
| 0 | 23 (5.6%) | 10 (5.7%) | 4 (6.7%) | |
| 1 | 323 (79%) | 142 (81%) | 51 (85%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_12, n (%) | 0.6 | |||
| 0 | 230 (56%) | 103 (59%) | 36 (60%) | |
| 1 | 116 (28%) | 49 (28%) | 19 (32%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
|
1
Pearson's Chi-squared test; Kruskal-Wallis rank sum test
|
||||
Sleep2 您可以整天保持清醒而沒有打瞌睡嗎?
sleep2<- dta %>%
select(SEX, AGE,ATOTAL,K_SUM,A_SUM,P_SUM, LIVING,LIVING1_1,LIVING1_11, LIVING1_12,sleep2_1) %>%
tbl_summary(by = sleep2_1, label = list(SEX ~ "Sex", AGE ~ "Age", ATOTAL ~ "Health awareness",K_SUM ~ "Knoeledge ", A_SUM ~ "Attitude", P_SUM ~ "Practice")) %>%
add_p()%>%
add_stat_label() %>%
bold_labels() %>%
modify_header(list(label ~ "**Variable**", all_stat_cols() ~ "**{level}**")) %>%
modify_spanning_header(all_stat_cols() ~ "**Group**") %>%
as_gt() %>%
gt::tab_header(
title = gt::md("**Table 2. Sleep Alertness**"))## 1 observations missing `sleep2_1` have been removed. To include these observations, use `forcats::fct_explicit_na()` on `sleep2_1` column before passing to `tbl_summary()`.## There was an error in 'add_p()/add_difference()' for variable 'LIVING1_11', p-value omitted:
## Error in stats::fisher.test(c(1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, : FEXACT 錯誤碼 6. LDKEY=618 對此問題而言太小，
## (ii := key2[itp=699] = 1812637, ldstp=18540)
## 嘗試增加工作空間的大小並盡可能 'mult'sleep2| Table 2. Sleep Alertness | ||||
|---|---|---|---|---|
| Variable | Group | p-value1 | ||
| 1 | 2 | 3 | ||
| Sex, n (%) | 195 (47%) | 82 (47%) | 28 (47%) | >0.9 |
| Age, Median (IQR) | 47 (24, 57) | 42 (24, 56) | 50 (25, 62) | 0.3 |
| Health awareness, Median (IQR) | 94 (80, 110) | 95 (77, 110) | 96 (80, 109) | >0.9 |
| Knoeledge , Median (IQR) | 7.39 (5.72, 8.44) | 7.39 (6.13, 8.45) | 6.97 (5.77, 7.62) | 0.2 |
| Attitude, Median (IQR) | 24.4 (21.4, 27.0) | 24.4 (21.0, 27.8) | 23.7 (20.1, 27.0) | 0.6 |
| Practice, Median (IQR) | 38 (33, 43) | 38 (33, 43) | 38 (32, 41) | 0.6 |
| LIVING, n (%) | 346 (84%) | 152 (87%) | 55 (92%) | 0.3 |
| LIVING1_1, n (%) | 0.4 | |||
| 0 | 277 (67%) | 115 (66%) | 41 (68%) | |
| 1 | 69 (17%) | 37 (21%) | 14 (23%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_11, n (%) | ||||
| 0 | 23 (5.6%) | 10 (5.7%) | 4 (6.7%) | |
| 1 | 323 (79%) | 142 (81%) | 51 (85%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_12, n (%) | 0.6 | |||
| 0 | 230 (56%) | 103 (59%) | 36 (60%) | |
| 1 | 116 (28%) | 49 (28%) | 19 (32%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
|
1
Pearson's Chi-squared test; Kruskal-Wallis rank sum test
|
||||
Sleep3 您在凌晨2點~4點間睡著了(或是試圖入睡)嗎?
sleep3<- dta %>%
select(SEX, AGE,ATOTAL,K_SUM,A_SUM,P_SUM, LIVING,LIVING1_1,LIVING1_11, LIVING1_12,sleep3_1) %>%
tbl_summary(by = sleep3_1, label = list(SEX ~ "Sex", AGE ~ "Age", ATOTAL ~ "Health awareness",K_SUM ~ "Knoeledge ", A_SUM ~ "Attitude", P_SUM ~ "Practice")) %>%
add_p()%>%
add_stat_label() %>%
bold_labels() %>%
modify_header(list(label ~ "**Variable**", all_stat_cols() ~ "**{level}**")) %>%
modify_spanning_header(all_stat_cols() ~ "**Group**") %>%
as_gt() %>%
gt::tab_header(
title = gt::md("**Table 3. Sleep Timing **"))## 1 observations missing `sleep3_1` have been removed. To include these observations, use `forcats::fct_explicit_na()` on `sleep3_1` column before passing to `tbl_summary()`.## There was an error in 'add_p()/add_difference()' for variable 'LIVING1_11', p-value omitted:
## Error in stats::fisher.test(c(1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, : FEXACT 錯誤碼 6. LDKEY=618 對此問題而言太小，
## (ii := key2[itp=699] = 1812637, ldstp=18540)
## 嘗試增加工作空間的大小並盡可能 'mult'sleep3| **Table 3. Sleep Timing ** | ||||
|---|---|---|---|---|
| Variable | Group | p-value1 | ||
| 1 | 2 | 3 | ||
| Sex, n (%) | 195 (47%) | 82 (47%) | 28 (47%) | >0.9 |
| Age, Median (IQR) | 47 (24, 57) | 42 (24, 56) | 50 (25, 62) | 0.3 |
| Health awareness, Median (IQR) | 94 (80, 110) | 95 (77, 110) | 96 (80, 109) | >0.9 |
| Knoeledge , Median (IQR) | 7.39 (5.72, 8.44) | 7.39 (6.13, 8.45) | 6.97 (5.77, 7.62) | 0.2 |
| Attitude, Median (IQR) | 24.4 (21.4, 27.0) | 24.4 (21.0, 27.8) | 23.7 (20.1, 27.0) | 0.6 |
| Practice, Median (IQR) | 38 (33, 43) | 38 (33, 43) | 38 (32, 41) | 0.6 |
| LIVING, n (%) | 346 (84%) | 152 (87%) | 55 (92%) | 0.3 |
| LIVING1_1, n (%) | 0.4 | |||
| 0 | 277 (67%) | 115 (66%) | 41 (68%) | |
| 1 | 69 (17%) | 37 (21%) | 14 (23%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_11, n (%) | ||||
| 0 | 23 (5.6%) | 10 (5.7%) | 4 (6.7%) | |
| 1 | 323 (79%) | 142 (81%) | 51 (85%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_12, n (%) | 0.6 | |||
| 0 | 230 (56%) | 103 (59%) | 36 (60%) | |
| 1 | 116 (28%) | 49 (28%) | 19 (32%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
|
1
Pearson's Chi-squared test; Kruskal-Wallis rank sum test
|
||||
Sleep4 您夜晚醒著的時間少於30分鐘嗎?(這包括進入睡眠的時間與從睡眠中醒來的時間)
sleep4<- dta %>%
select(SEX, AGE,ATOTAL,K_SUM,A_SUM,P_SUM, LIVING,LIVING1_1,LIVING1_11, LIVING1_12,sleep4_1) %>%
tbl_summary(by = sleep4_1, label = list(SEX ~ "Sex", AGE ~ "Age", ATOTAL ~ "Health awareness",K_SUM ~ "Knoeledge ", A_SUM ~ "Attitude", P_SUM ~ "Practice")) %>%
add_p()%>%
add_stat_label() %>%
bold_labels() %>%
modify_header(list(label ~ "**Variable**", all_stat_cols() ~ "**{level}**")) %>%
modify_spanning_header(all_stat_cols() ~ "**Group**") %>%
as_gt() %>%
gt::tab_header(
title = gt::md("**Table 4. Sleep Efficiency **"))## 1 observations missing `sleep4_1` have been removed. To include these observations, use `forcats::fct_explicit_na()` on `sleep4_1` column before passing to `tbl_summary()`.## There was an error in 'add_p()/add_difference()' for variable 'LIVING1_11', p-value omitted:
## Error in stats::fisher.test(c(1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, : FEXACT 錯誤碼 6. LDKEY=618 對此問題而言太小，
## (ii := key2[itp=699] = 1812637, ldstp=18540)
## 嘗試增加工作空間的大小並盡可能 'mult'sleep4| **Table 4. Sleep Efficiency ** | ||||
|---|---|---|---|---|
| Variable | Group | p-value1 | ||
| 1 | 2 | 3 | ||
| Sex, n (%) | 195 (47%) | 82 (47%) | 28 (47%) | >0.9 |
| Age, Median (IQR) | 47 (24, 57) | 42 (24, 56) | 50 (25, 62) | 0.3 |
| Health awareness, Median (IQR) | 94 (80, 110) | 95 (77, 110) | 96 (80, 109) | >0.9 |
| Knoeledge , Median (IQR) | 7.39 (5.72, 8.44) | 7.39 (6.13, 8.45) | 6.97 (5.77, 7.62) | 0.2 |
| Attitude, Median (IQR) | 24.4 (21.4, 27.0) | 24.4 (21.0, 27.8) | 23.7 (20.1, 27.0) | 0.6 |
| Practice, Median (IQR) | 38 (33, 43) | 38 (33, 43) | 38 (32, 41) | 0.6 |
| LIVING, n (%) | 346 (84%) | 152 (87%) | 55 (92%) | 0.3 |
| LIVING1_1, n (%) | 0.4 | |||
| 0 | 277 (67%) | 115 (66%) | 41 (68%) | |
| 1 | 69 (17%) | 37 (21%) | 14 (23%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_11, n (%) | ||||
| 0 | 23 (5.6%) | 10 (5.7%) | 4 (6.7%) | |
| 1 | 323 (79%) | 142 (81%) | 51 (85%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_12, n (%) | 0.6 | |||
| 0 | 230 (56%) | 103 (59%) | 36 (60%) | |
| 1 | 116 (28%) | 49 (28%) | 19 (32%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
|
1
Pearson's Chi-squared test; Kruskal-Wallis rank sum test
|
||||
Sleep5 您每天的睡眠時間介於6-8小時之間嗎?
sleep5<- dta %>%
select(SEX, AGE,ATOTAL,K_SUM,A_SUM,P_SUM, LIVING,LIVING1_1,LIVING1_11, LIVING1_12,sleep5_1) %>%
tbl_summary(by = sleep5_1, label = list(SEX ~ "Sex", AGE ~ "Age", ATOTAL ~ "Health awareness",K_SUM ~ "Knoeledge ", A_SUM ~ "Attitude", P_SUM ~ "Practice")) %>%
add_p()%>%
add_stat_label() %>%
bold_labels() %>%
modify_header(list(label ~ "**Variable**", all_stat_cols() ~ "**{level}**")) %>%
modify_spanning_header(all_stat_cols() ~ "**Group**") %>%
as_gt() %>%
gt::tab_header(
title = gt::md("**Table 5. Sleep Duration **"))## 1 observations missing `sleep5_1` have been removed. To include these observations, use `forcats::fct_explicit_na()` on `sleep5_1` column before passing to `tbl_summary()`.## There was an error in 'add_p()/add_difference()' for variable 'LIVING1_11', p-value omitted:
## Error in stats::fisher.test(c(1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, : FEXACT 錯誤碼 6. LDKEY=618 對此問題而言太小，
## (ii := key2[itp=699] = 1812637, ldstp=18540)
## 嘗試增加工作空間的大小並盡可能 'mult'sleep5| **Table 5. Sleep Duration ** | ||||
|---|---|---|---|---|
| Variable | Group | p-value1 | ||
| 1 | 2 | 3 | ||
| Sex, n (%) | 195 (47%) | 82 (47%) | 28 (47%) | >0.9 |
| Age, Median (IQR) | 47 (24, 57) | 42 (24, 56) | 50 (25, 62) | 0.3 |
| Health awareness, Median (IQR) | 94 (80, 110) | 95 (77, 110) | 96 (80, 109) | >0.9 |
| Knoeledge , Median (IQR) | 7.39 (5.72, 8.44) | 7.39 (6.13, 8.45) | 6.97 (5.77, 7.62) | 0.2 |
| Attitude, Median (IQR) | 24.4 (21.4, 27.0) | 24.4 (21.0, 27.8) | 23.7 (20.1, 27.0) | 0.6 |
| Practice, Median (IQR) | 38 (33, 43) | 38 (33, 43) | 38 (32, 41) | 0.6 |
| LIVING, n (%) | 346 (84%) | 152 (87%) | 55 (92%) | 0.3 |
| LIVING1_1, n (%) | 0.4 | |||
| 0 | 277 (67%) | 115 (66%) | 41 (68%) | |
| 1 | 69 (17%) | 37 (21%) | 14 (23%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_11, n (%) | ||||
| 0 | 23 (5.6%) | 10 (5.7%) | 4 (6.7%) | |
| 1 | 323 (79%) | 142 (81%) | 51 (85%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
| LIVING1_12, n (%) | 0.6 | |||
| 0 | 230 (56%) | 103 (59%) | 36 (60%) | |
| 1 | 116 (28%) | 49 (28%) | 19 (32%) | |
| 2 | 65 (16%) | 23 (13%) | 5 (8.3%) | |
|
1
Pearson's Chi-squared test; Kruskal-Wallis rank sum test
|
||||
五題的回歸皆無顯著。
pacman::p_load(ordinal,ggeffects, effects,tidyverse)
cbPalette <- c("#999999", "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7")Sleep1 您對您的睡眠狀況滿意嗎?
ols1 = clm(sleep1_1~SEX+ AGE+EDU+ ATOTAL+ K_SUM+ A_SUM+ P_SUM+ LIVING+LIVING1_1+ LIVING1_11+ LIVING1_12 ,data = dta, link = "logit")## Warning: Using formula(x) is deprecated when x is a character vector of length > 1.
## Consider formula(paste(x, collapse = " ")) instead.summary(ols1)## formula:
## sleep1_1 ~ SEX + AGE + EDU + ATOTAL + K_SUM + A_SUM + P_SUM + LIVING + LIVING1_1 + LIVING1_11 + LIVING1_12
## data: dta
##
## link threshold nobs logLik AIC niter max.grad cond.H
## logit flexible 646 -549.28 1124.56 5(0) 1.67e-10 6.4e+06
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## SEX 0.015322 0.169067 0.091 0.9278
## AGE 0.008941 0.005612 1.593 0.1111
## EDU 0.284502 0.114174 2.492 0.0127 *
## ATOTAL 0.008184 0.004543 1.802 0.0716 .
## K_SUM -0.008298 0.052983 -0.157 0.8755
## A_SUM -0.019978 0.025110 -0.796 0.4262
## P_SUM -0.018890 0.014547 -1.299 0.1941
## LIVING 0.516275 0.692544 0.745 0.4560
## LIVING1_1 0.290993 0.213012 1.366 0.1719
## LIVING1_11 -0.218531 0.388839 -0.562 0.5741
## LIVING1_12 -0.087645 0.205582 -0.426 0.6699
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 1.276 1.129 1.130
## 2|3 3.022 1.136 2.659
## (因為不存在，1 個觀察量被刪除了)exp(coef(ols1))## 1|2 2|3 SEX AGE EDU ATOTAL K_SUM
## 3.5805148 20.5366803 1.0154402 1.0089807 1.3290997 1.0082178 0.9917364
## A_SUM P_SUM LIVING LIVING1_1 LIVING1_11 LIVING1_12
## 0.9802201 0.9812876 1.6757729 1.3377552 0.8036986 0.9160861Sleep2 您可以整天保持清醒而沒有打瞌睡嗎?
ols1 = clm(sleep2_1~SEX+ AGE+EDU+ ATOTAL+ K_SUM+ A_SUM+ P_SUM+ LIVING+LIVING1_1+ LIVING1_11+ LIVING1_12 ,data = dta, link = "logit")## Warning: Using formula(x) is deprecated when x is a character vector of length > 1.
## Consider formula(paste(x, collapse = " ")) instead.summary(ols1)## formula:
## sleep2_1 ~ SEX + AGE + EDU + ATOTAL + K_SUM + A_SUM + P_SUM + LIVING + LIVING1_1 + LIVING1_11 + LIVING1_12
## data: dta
##
## link threshold nobs logLik AIC niter max.grad cond.H
## logit flexible 646 -549.28 1124.56 5(0) 1.67e-10 6.4e+06
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## SEX 0.015322 0.169067 0.091 0.9278
## AGE 0.008941 0.005612 1.593 0.1111
## EDU 0.284502 0.114174 2.492 0.0127 *
## ATOTAL 0.008184 0.004543 1.802 0.0716 .
## K_SUM -0.008298 0.052983 -0.157 0.8755
## A_SUM -0.019978 0.025110 -0.796 0.4262
## P_SUM -0.018890 0.014547 -1.299 0.1941
## LIVING 0.516275 0.692544 0.745 0.4560
## LIVING1_1 0.290993 0.213012 1.366 0.1719
## LIVING1_11 -0.218531 0.388839 -0.562 0.5741
## LIVING1_12 -0.087645 0.205582 -0.426 0.6699
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 1.276 1.129 1.130
## 2|3 3.022 1.136 2.659
## (因為不存在，1 個觀察量被刪除了)Sleep3 您在凌晨2點~4點間睡著了(或是試圖入睡)嗎?
ols1 = clm(sleep3_1~SEX+ AGE+EDU+ ATOTAL+ K_SUM+ A_SUM+ P_SUM+ LIVING+LIVING1_1+ LIVING1_11+ LIVING1_12 ,data = dta, link = "logit")## Warning: Using formula(x) is deprecated when x is a character vector of length > 1.
## Consider formula(paste(x, collapse = " ")) instead.summary(ols1)## formula:
## sleep3_1 ~ SEX + AGE + EDU + ATOTAL + K_SUM + A_SUM + P_SUM + LIVING + LIVING1_1 + LIVING1_11 + LIVING1_12
## data: dta
##
## link threshold nobs logLik AIC niter max.grad cond.H
## logit flexible 646 -549.28 1124.56 5(0) 1.67e-10 6.4e+06
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## SEX 0.015322 0.169067 0.091 0.9278
## AGE 0.008941 0.005612 1.593 0.1111
## EDU 0.284502 0.114174 2.492 0.0127 *
## ATOTAL 0.008184 0.004543 1.802 0.0716 .
## K_SUM -0.008298 0.052983 -0.157 0.8755
## A_SUM -0.019978 0.025110 -0.796 0.4262
## P_SUM -0.018890 0.014547 -1.299 0.1941
## LIVING 0.516275 0.692544 0.745 0.4560
## LIVING1_1 0.290993 0.213012 1.366 0.1719
## LIVING1_11 -0.218531 0.388839 -0.562 0.5741
## LIVING1_12 -0.087645 0.205582 -0.426 0.6699
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 1.276 1.129 1.130
## 2|3 3.022 1.136 2.659
## (因為不存在，1 個觀察量被刪除了)Sleep4 您夜晚醒著的時間少於30分鐘嗎?(這包括進入睡眠的時間與從睡眠中醒來的時間)
ols1 = clm(sleep4_1~SEX+ AGE+EDU+ ATOTAL+ K_SUM+ A_SUM+ P_SUM+ LIVING+LIVING1_1+ LIVING1_11+ LIVING1_12 ,data = dta, link = "logit")## Warning: Using formula(x) is deprecated when x is a character vector of length > 1.
## Consider formula(paste(x, collapse = " ")) instead.summary(ols1)## formula:
## sleep4_1 ~ SEX + AGE + EDU + ATOTAL + K_SUM + A_SUM + P_SUM + LIVING + LIVING1_1 + LIVING1_11 + LIVING1_12
## data: dta
##
## link threshold nobs logLik AIC niter max.grad cond.H
## logit flexible 646 -549.28 1124.56 5(0) 1.67e-10 6.4e+06
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## SEX 0.015322 0.169067 0.091 0.9278
## AGE 0.008941 0.005612 1.593 0.1111
## EDU 0.284502 0.114174 2.492 0.0127 *
## ATOTAL 0.008184 0.004543 1.802 0.0716 .
## K_SUM -0.008298 0.052983 -0.157 0.8755
## A_SUM -0.019978 0.025110 -0.796 0.4262
## P_SUM -0.018890 0.014547 -1.299 0.1941
## LIVING 0.516275 0.692544 0.745 0.4560
## LIVING1_1 0.290993 0.213012 1.366 0.1719
## LIVING1_11 -0.218531 0.388839 -0.562 0.5741
## LIVING1_12 -0.087645 0.205582 -0.426 0.6699
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 1.276 1.129 1.130
## 2|3 3.022 1.136 2.659
## (因為不存在，1 個觀察量被刪除了)Sleep5 您每天的睡眠時間介於6-8小時之間嗎?
ols1 = clm(sleep5_1~SEX+ AGE+ EDU+ ATOTAL+ K_SUM+ A_SUM+ P_SUM+ LIVING+LIVING1_1+ LIVING1_11+ LIVING1_12 ,data = dta, link = "logit")## Warning: Using formula(x) is deprecated when x is a character vector of length > 1.
## Consider formula(paste(x, collapse = " ")) instead.summary(ols1)## formula:
## sleep5_1 ~ SEX + AGE + EDU + ATOTAL + K_SUM + A_SUM + P_SUM + LIVING + LIVING1_1 + LIVING1_11 + LIVING1_12
## data: dta
##
## link threshold nobs logLik AIC niter max.grad cond.H
## logit flexible 646 -549.28 1124.56 5(0) 1.67e-10 6.4e+06
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## SEX 0.015322 0.169067 0.091 0.9278
## AGE 0.008941 0.005612 1.593 0.1111
## EDU 0.284502 0.114174 2.492 0.0127 *
## ATOTAL 0.008184 0.004543 1.802 0.0716 .
## K_SUM -0.008298 0.052983 -0.157 0.8755
## A_SUM -0.019978 0.025110 -0.796 0.4262
## P_SUM -0.018890 0.014547 -1.299 0.1941
## LIVING 0.516275 0.692544 0.745 0.4560
## LIVING1_1 0.290993 0.213012 1.366 0.1719
## LIVING1_11 -0.218531 0.388839 -0.562 0.5741
## LIVING1_12 -0.087645 0.205582 -0.426 0.6699
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 1.276 1.129 1.130
## 2|3 3.022 1.136 2.659
## (因為不存在，1 個觀察量被刪除了)以睡眠總分來看，也得到同樣結果。
ols1 = clm(sleep_grp1~SEX+ AGE+ EDU+ ATOTAL+ K_SUM+ A_SUM+ P_SUM+ LIVING+LIVING1_1+ LIVING1_11+ LIVING1_12 ,data = dta, link = "logit")## Warning: Using formula(x) is deprecated when x is a character vector of length > 1.
## Consider formula(paste(x, collapse = " ")) instead.summary(ols1)## formula:
## sleep_grp1 ~ SEX + AGE + EDU + ATOTAL + K_SUM + A_SUM + P_SUM + LIVING + LIVING1_1 + LIVING1_11 + LIVING1_12
## data: dta
##
## link threshold nobs logLik AIC niter max.grad cond.H
## logit flexible 646 -549.28 1124.56 5(0) 1.67e-10 6.4e+06
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## SEX 0.015322 0.169067 0.091 0.9278
## AGE 0.008941 0.005612 1.593 0.1111
## EDU 0.284502 0.114174 2.492 0.0127 *
## ATOTAL 0.008184 0.004543 1.802 0.0716 .
## K_SUM -0.008298 0.052983 -0.157 0.8755
## A_SUM -0.019978 0.025110 -0.796 0.4262
## P_SUM -0.018890 0.014547 -1.299 0.1941
## LIVING 0.516275 0.692544 0.745 0.4560
## LIVING1_1 0.290993 0.213012 1.366 0.1719
## LIVING1_11 -0.218531 0.388839 -0.562 0.5741
## LIVING1_12 -0.087645 0.205582 -0.426 0.6699
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 1.276 1.129 1.130
## 2|3 3.022 1.136 2.659
## (因為不存在，1 個觀察量被刪除了)若將居住狀況移除，5題中只有教育顯著，以下僅秀出sleep5的情況。
ols1 = clm(sleep5_1~SEX+ AGE+ EDU+ ATOTAL+ K_SUM+ A_SUM+ P_SUM ,data = dta, link = "logit")
summary(ols1)## formula: sleep5_1 ~ SEX + AGE + EDU + ATOTAL + K_SUM + A_SUM + P_SUM
## data: dta
##
## link threshold nobs logLik AIC niter max.grad cond.H
## logit flexible 646 -551.51 1121.02 5(0) 1.77e-10 1.1e+06
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## SEX -0.021555 0.167514 -0.129 0.8976
## AGE 0.010056 0.005355 1.878 0.0604 .
## EDU 0.284783 0.113384 2.512 0.0120 *
## ATOTAL 0.007718 0.004515 1.709 0.0874 .
## K_SUM -0.004639 0.052676 -0.088 0.9298
## A_SUM -0.020160 0.024927 -0.809 0.4186
## P_SUM -0.017491 0.014379 -1.216 0.2238
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 1.0436 0.5026 2.076
## 2|3 2.7834 0.5167 5.387
## (因為不存在，1 個觀察量被刪除了)