statapath <- "/usr/local/stata15/stata" # <- Ubuntu path to stata
#statapath <- "D:/software/STATA/Stata-64.exe" # <- Windows STATA path modify if needed
knitr::opts_chunk$set(engine.path = list(
stata = statapath
))
library(naniar)
library(epiDisplay)
library(readr)
library(plyr)
library(dplyr)
library(tidyverse)
library(haven)
library(survey)
# install packages if neededCW2CB2 <- read_table2("~/Documents/LSHTMproject/results/50NDNS_CW2CB2.txt",
col_names = FALSE)# change the path to your own path
names(CW2CB2) <- c("H0", "H1", "H2", "H3", "H4", "H5", "H6", "H7",
"H8", "H9", "H10", "H11", "H12", "H13", "H14",
"H15", "H16", "H17", "H18", "H19", "H20", "H21",
"H22", "H23", "ID_DAY", "AGE", "SEX", "CPROB1",
"CPROB2", "CPROB3", "CPROB4",
# "CPROB5",
# "CPROB6",
"CB", "CW", "MLCJOINT", "ID")
CW2CB2_reg <- CW2CB2[!duplicated(CW2CB2$ID), ]
CW2CB2_reg <- CW2CB2_reg %>%
select(ID, AGE, SEX, CB) # extract only the CB variable (Between individual classes == 1 or 2)
tab1(CW2CB2_reg$CB, graph = FALSE)## CW2CB2_reg$CB :
## Frequency Percent Cum. percent
## 1 4147 67.4 67.4
## 2 2008 32.6 100.0
## Total 6155 100.0 100.0CW3CB2 <- read_table2("~/Documents/LSHTMproject/results/50NDNS_CW3CB2.txt",
col_names = FALSE)# change the path to your own path
names(CW3CB2) <- c("H0", "H1", "H2", "H3", "H4", "H5", "H6", "H7",
"H8", "H9", "H10", "H11", "H12", "H13", "H14",
"H15", "H16", "H17", "H18", "H19", "H20", "H21",
"H22", "H23", "ID_DAY", "AGE", "SEX", "CPROB1",
"CPROB2", "CPROB3", "CPROB4", "CPROB5", "CPROB6",
"CB", "CW", "MLCJOINT", "ID")
CW3CB2_reg <- CW3CB2[!duplicated(CW3CB2$ID), ]
CW3CB2_reg <- CW3CB2_reg %>%
select(ID, AGE, SEX, CB) # extract only the CB variable (Between individual classes == 1 or 2)
tab1(CW3CB2_reg$CB, graph = FALSE)## CW3CB2_reg$CB :
## Frequency Percent Cum. percent
## 1 3743 60.8 60.8
## 2 2412 39.2 100.0
## Total 6155 100.0 100.0CARB_50_LGCA_2CLASS <- read_table2("~/Documents/LSHTMproject/results/LCGA/CARB_50_LGCA_2CLASS.txt",
col_names = FALSE)# change the path to your own path
names(CARB_50_LGCA_2CLASS) <- c("H0_X", "H1_X", "H2_X", "H3_X", "H4_X", "H5_X", "H6_X", "H7_X",
"H8_X", "H9_X", "H10_X", "H11_X", "H12_X", "H13_X", "H14_X", "H15_X", "H16_X", "H17_X",
"H18_X", "H19_X", "H20_X", "H21_X", "H22_X", "H23_X", "H0_Y", "H1_Y", "H2_Y", "H3_Y",
"H4_Y", "H5_Y", "H6_Y", "H7_Y", "H8_Y", "H9_Y", "H10_Y", "H11_Y", "H12_Y", "H13_Y",
"H14_Y", "H15_Y", "H16_Y", "H17_Y", "H18_Y", "H19_Y", "H20_Y", "H21_Y",
"H22_Y", "H23_Y", "H0_X_X", "H1_X_X", "H2_X_X", "H3_X_X", "H4_X_X", "H5_X_X",
"H6_X_X", "H7_X_X", "H8_X_X", "H9_X_X", "H10_X_X", "H11_X_X", "H12_X_X", "H13_X_X",
"H14_X_X", "H15_X_X", "H16_X_X", "H17_X_X", "H18_X_X", "H19_X_X", "H20_X_X", "H21_X_X",
"H22_X_X", "H23_X_X", "H0_Y_Y", "H1_Y_Y", "H2_Y_Y", "H3_Y_Y", "H4_Y_Y", "H5_Y_Y",
"H6_Y_Y", "H7_Y_Y", "H8_Y_Y", "H9_Y_Y", "H10_Y_Y", "H11_Y_Y", "H12_Y_Y", "H13_Y_Y",
"H14_Y_Y", "H15_Y_Y", "H16_Y_Y", "H17_Y_Y", "H18_Y_Y", "H19_Y_Y", "H20_Y_Y", "H21_Y_Y",
"H22_Y_Y", "H23_Y_Y", "ID", "CPROB1", "CPROB2",
#"CPROB3", #"CPROB4",
"C")
CARB_50_LGCA_2CLASS[CARB_50_LGCA_2CLASS == "*"] <- NA
LCGA_2class <- CARB_50_LGCA_2CLASS %>%
select(ID, C) # extract only the C variable (classes == 1 or 2)
tab1(LCGA_2class$C, graph = FALSE)## LCGA_2class$C :
## Frequency Percent Cum. percent
## 1 4283 69.6 69.6
## 2 1872 30.4 100.0
## Total 6155 100.0 100.0CARB_50_LGCA_3CLASS <- read_table2("~/Documents/LSHTMproject/results/LCGA/CARB_50_LGCA_3CLASS.DAT",
col_names = FALSE)# change the path to your own path
names(CARB_50_LGCA_3CLASS) <- c("H0_X", "H1_X", "H2_X", "H3_X", "H4_X", "H5_X", "H6_X", "H7_X",
"H8_X", "H9_X", "H10_X", "H11_X", "H12_X", "H13_X", "H14_X", "H15_X", "H16_X", "H17_X",
"H18_X", "H19_X", "H20_X", "H21_X", "H22_X", "H23_X", "H0_Y", "H1_Y", "H2_Y", "H3_Y",
"H4_Y", "H5_Y", "H6_Y", "H7_Y", "H8_Y", "H9_Y", "H10_Y", "H11_Y", "H12_Y", "H13_Y",
"H14_Y", "H15_Y", "H16_Y", "H17_Y", "H18_Y", "H19_Y", "H20_Y", "H21_Y",
"H22_Y", "H23_Y", "H0_X_X", "H1_X_X", "H2_X_X", "H3_X_X", "H4_X_X", "H5_X_X",
"H6_X_X", "H7_X_X", "H8_X_X", "H9_X_X", "H10_X_X", "H11_X_X", "H12_X_X", "H13_X_X",
"H14_X_X", "H15_X_X", "H16_X_X", "H17_X_X", "H18_X_X", "H19_X_X", "H20_X_X", "H21_X_X",
"H22_X_X", "H23_X_X", "H0_Y_Y", "H1_Y_Y", "H2_Y_Y", "H3_Y_Y", "H4_Y_Y", "H5_Y_Y",
"H6_Y_Y", "H7_Y_Y", "H8_Y_Y", "H9_Y_Y", "H10_Y_Y", "H11_Y_Y", "H12_Y_Y", "H13_Y_Y",
"H14_Y_Y", "H15_Y_Y", "H16_Y_Y", "H17_Y_Y", "H18_Y_Y", "H19_Y_Y", "H20_Y_Y", "H21_Y_Y",
"H22_Y_Y", "H23_Y_Y", "ID", "CPROB1", "CPROB2",
"CPROB3", "C")
CARB_50_LGCA_3CLASS[CARB_50_LGCA_3CLASS == "*"] <- NA
LCGA_3class <- CARB_50_LGCA_3CLASS %>%
select(ID, C) # extract only the C variable (classes == 1 or 2)
tab1(LCGA_3class$C, graph = FALSE)## LCGA_3class$C :
## Frequency Percent Cum. percent
## 1 1783 29.0 29.0
## 2 376 6.1 35.1
## 3 3996 64.9 100.0
## Total 6155 100.0 100.0# change the following path according to your own data folders
blood78 <- read_dta("~/Downloads/UKDA-6533-stata11_se/stata11_se/ndns_rp_yr7-8a_indiv.dta")
blood56 <- read_dta("~/Downloads/UKDA-6533-stata11_se/stata11_se/ndns_rp_yr5-6a_indiv.dta")
blood14 <- read_dta("~/Downloads/UKDA-6533-stata11_se/stata11_se/ndns_rp_yr1-4a_indiv_uk.dta")
names(blood78)[names(blood78)=="seriali"] <- "ID"
names(blood56)[names(blood56)=="seriali"] <- "ID"
names(blood14)[names(blood14)=="seriali"] <- "ID"
BMI78 <- blood78 %>%
select(ID, Sex, age, bmival, wstval, Diabetes, bpmedc2, bpmedd2, hyper140_2, hibp140_2,
Glucose, A1C, cigsta3, dnoft3, dnnow, wti_Y78, wtn_Y78, wtb_Y78, cluster1, cluster2, cluster3,
cluster4, cluster5, area, gor) %>%
rename(wti = wti_Y78, wtn = wtn_Y78, wtb = wtb_Y78, drink = dnoft3) %>%
mutate(Years = "7-8") %>%
replace_with_na(replace = list(bmival = -1,
wstval = -1,
bpmedd2 = -1,
bpmedc2 = -1,
hyper140_2 = -7,
# hyper140_2 = -1,
hibp140_2 = -7,
# hibp140_2 = -1,
Glucose = -1,
A1C = -1,
dnnow = -1,
drink = -1,
cigsta3 = -1)) %>%
replace_with_na(replace = list(hyper140_2 = -1, hibp140_2 = -1,
drink = -8)) %>%
replace_with_na(replace = list(drink = -9,
cigsta3 = -8))
BMI56 <- blood56 %>%
select(ID, Sex, age, area, bmival, wstval, Diabetes, bpmedc2, bpmedd2, hyper140_2, hibp140_2,
Glucose, A1C, cigsta3, dnoft3, dnnow, wti_Y56, wtn_Y56, wtb_Y56, cluster1, cluster2, cluster3,
cluster4, cluster5, area, gor) %>%
mutate(Years = "5-6") %>%
rename(wti = wti_Y56, wtn = wtn_Y56, wtb = wtb_Y56, drink = dnoft3) %>%
replace_with_na(replace = list(bmival = -1,
wstval = -1,
bpmedd2 = -1,
bpmedc2 = -1,
hyper140_2 = -7,
# hyper140_2 = -1,
hibp140_2 = -7,
# hibp140_2 = -1,
Glucose = -1,
A1C = -1,
dnnow = -1,
drink = -1,
cigsta3 = -1)) %>%
replace_with_na(replace = list(hyper140_2 = -1, hibp140_2 = -1,
drink = -8)) %>%
replace_with_na(replace = list(drink = -9,
cigsta3 = -8))
BMI14 <- blood14 %>%
select(ID, Sex, age, bmival, wstval, Diabetes, bpmedc, bpmedd, hyper140, hibp140,
Glucose, A1C, cigsta3, dnoft3, dnnow, wti_CY1234, wtn_CY1234, wtb_CY1234, cluster, area, gor) %>%
rename(hyper140_2 = hyper140, hibp140_2 = hibp140, bpmedd2 = bpmedd,
bpmedc2 = bpmedc, cluster1 = cluster,
wti = wti_CY1234, wtn = wtn_CY1234, wtb = wtb_CY1234, drink = dnoft3) %>%
mutate(cluster2 = NA, cluster3 = NA, cluster4 = NA, cluster5 = NA, Years = "1-4") %>%
replace_with_na(replace = list(bmival = -1,
wstval = -1,
bpmedd2 = -1,
bpmedc2 = -1,
hyper140_2 = -7,
# hyper140_2 = -1,
hibp140_2 = -7,
# hibp140_2 = -1,
Glucose = -1,
A1C = -1,
dnnow = -1,
drink = -1,
cigsta3 = -1)) %>%
replace_with_na(replace = list(hyper140_2 = -1, hibp140_2 = -1,
drink = -8)) %>%
replace_with_na(replace = list(drink = -9,
cigsta3 = -8))
BMI <- bind_rows(BMI14, BMI56, BMI78)
CW2CB2_regss <- CW2CB2_reg %>%
left_join(BMI, by = "ID") ## dataset for 2by2 multilevel latent classes
CW3CB2_regss <- CW3CB2_reg %>%
left_join(BMI, by = "ID") ## dataset for 3by2 multilevel latent classes
LCGA_2class <- LCGA_2class %>%
left_join(BMI, by = "ID") ## dataset for 2 classes LCGA
LCGA_3class <- LCGA_3class %>%
left_join(BMI, by = "ID") ## dataset for 3 classes LCGA
rm(blood14, blood56, blood78, BMI14, BMI56, BMI78, #BMI,
CW2CB2, CW2CB2_reg, CW3CB2, CW3CB2_reg, CARB_50_LGCA_2CLASS, CARB_50_LGCA_3CLASS)# individual weighting
a <- sum(CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wti)
b <- sum(CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wti)
c <- sum(CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wti)
CW2CB2_regss$wti1to8 <- CW2CB2_regss$wti
CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wti1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wti*(a+b+c)*(1/2)/a
CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wti1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wti*(a+b+c)*(1/4)/b
CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wti1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wti*(a+b+c)*(1/4)/c
mean(CW2CB2_regss$wti1to8)## [1] 1.209817CW2CB2_regss$wti1to8 <- CW2CB2_regss$wti1to8/1.209816814
summ(CW2CB2_regss$wti1to8, graph = FALSE)## obs. mean median s.d. min. max.
## 6155 1 0.892 0.897 0 5.893sum(CW2CB2_regss$wti1to8, graph = FALSE) #Check if the weighting sum up to the sample size we have## [1] 6155# Nurse weights
a <- sum(CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wtn)
b <- sum(CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wtn)
c <- sum(CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wtn)
CW2CB2_regss$wtn1to8 <- CW2CB2_regss$wtn
CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wtn1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wtn*(a+b+c)*(1/2)/a
CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wtn1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wtn*(a+b+c)*(1/4)/b
CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wtn1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wtn*(a+b+c)*(1/4)/c
mean(CW2CB2_regss$wtn1to8)## [1] 0.9070036CW2CB2_regss$wtn1to8 <- CW2CB2_regss$wtn1to8/0.907003577
summ(CW2CB2_regss$wtn1to8, graph = FALSE)## obs. mean median s.d. min. max.
## 6155 1 0.588 1.203 0 8.516sum(CW2CB2_regss$wtn1to8, graph = FALSE) #Check if the weighting sum up to the sample size we have## [1] 6155# Blood weights
a <- sum(CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wtb)
b <- sum(CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wtb)
c <- sum(CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wtb)
CW2CB2_regss$wtb1to8 <- CW2CB2_regss$wtb
CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wtb1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "1-4",]$wtb*(a+b+c)*(1/2)/a
CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wtb1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "5-6",]$wtb*(a+b+c)*(1/4)/b
CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wtb1to8 <- CW2CB2_regss[CW2CB2_regss$Years == "7-8",]$wtb*(a+b+c)*(1/4)/c
mean(CW2CB2_regss$wtb1to8)## [1] 0.4817445CW2CB2_regss$wtb1to8 <- CW2CB2_regss$wtb1to8/0.4817444505
summ(CW2CB2_regss$wtb1to8, graph = FALSE)## obs. mean median s.d. min. max.
## 6155 1 0 1.618 0 14.577sum(CW2CB2_regss$wtb1to8, graph = FALSE) #Check if the weighting sum up to the sample size we have## [1] 6155weightings <- CW2CB2_regss %>% select(ID, wti1to8, wtn1to8, wtb1to8)
# add the weightings to the other datasets
CW3CB2_regss <- CW3CB2_regss %>%
left_join(weightings, by = "ID")
LCGA_2class <- LCGA_2class %>%
left_join(weightings, by = "ID")
LCGA_3class <- LCGA_3class %>%
left_join(weightings, by = "ID") # specifying a survey design
CW2CB2_regss$dnnow <- as.factor(CW2CB2_regss$dnnow)
CW2CB2_regss$cigsta3 <- as.factor(CW2CB2_regss$cigsta3)
cw2cb2 <- svydesign(id = ~area, strat = ~gor, weights=~wti1to8, data = CW2CB2_regss, nest = TRUE)
summary(svyglm(bmival ~ CB, design = cw2cb2))
summary(svyglm(bmival ~ CB + AGE + SEX + cigsta3 + dnnow, design = cw2cb2))## Call:
## svyglm(formula = bmival ~ CB, design = cw2cb2)
##
## Survey design:
## svydesign(id = ~area, strat = ~gor, weights = ~wti1to8, data = CW2CB2_regss,
## nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 26.6815 0.2917 91.468 < 2e-16 ***
## CB 0.5474 0.2026 2.702 0.00699 **
## ---
## Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
##
## (Dispersion parameter for gaussian family taken to be 28.88983)
##
## Number of Fisher Scoring iterations: 2
##
##
## Call:
## svyglm(formula = bmival ~ CB + AGE + SEX + cigsta3 + dnnow, design = cw2cb2)
##
## Survey design:
## svydesign(id = ~area, strat = ~gor, weights = ~wti1to8, data = CW2CB2_regss,
## nest = TRUE)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 24.53607 0.49745 49.324 < 2e-16 ***
## CB 0.44258 0.20174 2.194 0.0285 *
## AGE 0.04177 0.00582 7.176 1.33e-12 ***
## SEX -0.21736 0.18620 -1.167 0.2433
## cigsta32 1.18384 0.29947 3.953 8.22e-05 ***
## cigsta33 0.48760 0.24885 1.959 0.0503 .
## dnnow2 0.42970 0.24531 1.752 0.0801 .
## ---
## Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
##
## (Dispersion parameter for gaussian family taken to be 27.97746)
##
## Number of Fisher Scoring iterations: 2After adjusting for age, sex, smoking, and drinking, subjects in latent class 2 were averagely with 0.748599 kg/m2 higher BMI compared with subjects in latent class 1.
##
## . use "/home/wangcc-me/Downloads/UKDA-6533-stata11_se/stata11_se/CW2CB2_regss.d
## > ta", clear
##
## .
## . label define smoking 1 "current" 2 "ex-smoker" 3 "Never"
##
## . label values cigsta3 smoking
##
## . label define drinking 1 "no" 2 "yes"
##
## . label values dnnow drinking
##
## . label define gender 1 "Men" 2 "Women"
##
## . label values Sex gender
##
## .
## .
## . svyset area [pweight = wti1to8], strata(gor)
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## .
## . svydescribe wti
##
## Survey: Describing stage 1 sampling units
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## #Obs with #Obs with #Obs per included Unit
## #Units #Units complete missing ----------------------------
## Stratum included omitted data data min mean max
## -------- -------- -------- -------- -------- -------- -------- --------
## 1 42 0 215 0 2 5.1 8
## 2 111 0 480 0 1 4.3 9
## 3 83 0 340 0 1 4.1 7
## 4 71 0 327 0 1 4.6 8
## 5 84 0 403 0 1 4.8 8
## 6 89 0 424 0 2 4.8 9
## 7 111 0 380 0 1 3.4 8
## 8 130 0 575 0 1 4.4 8
## 9 82 0 348 0 2 4.2 8
## 10 184 0 846 0 1 4.6 9
## 11 255 0 1,033 0 1 4.1 9
## 12 172 0 784 0 1 4.6 9
## -------- -------- -------- -------- -------- -------- -------- --------
## 12 1,414 0 6,155 0 1 4.4 9
## ------------------
## 6,155
##
## . svy: mean bmival
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.41424 .1007122 27.21667 27.6118
## --------------------------------------------------------------
##
## .
## . // two-way table
## .
## . svy: tabulate Sex CB, row se ci format(%7.3f)
## (running tabulate on estimation sample)
##
## Number of strata = 12 Number of obs = 6,155
## Number of PSUs = 1,414 Population size = 6,155
## Design df = 1,402
##
## -------------------------------------------------------
## | CB
## Sex | 1 2 Total
## ----------+--------------------------------------------
## Men | 0.647 0.353 1.000
## | (0.013) (0.013)
## | [0.622,0.672] [0.328,0.378]
## |
## Women | 0.680 0.320 1.000
## | (0.011) (0.011)
## | [0.659,0.700] [0.300,0.341]
## |
## Total | 0.664 0.336 1.000
## | (0.008) (0.008)
## | [0.648,0.681] [0.319,0.352]
## -------------------------------------------------------
## Key: row proportion
## (linearized standard error of row proportion)
## [95% confidence interval for row proportion]
##
## Pearson:
## Uncorrected chi2(1) = 7.3933
## Design-based F(1, 1402) = 3.9332 P = 0.0475
##
## .
## . // comparing means
## . svy: mean bmi, over(CB)
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
##
## 1: CB = 1
## 2: CB = 2
##
## --------------------------------------------------------------
## | Linearized
## Over | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival |
## 1 | 27.22889 .1233456 26.98693 27.47085
## 2 | 27.77631 .1655422 27.45157 28.10105
## --------------------------------------------------------------
##
## .
## . svy: regress bmival i.CB
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
## F( 1, 1396) = 7.30
## Prob > F = 0.0070
## R-squared = 0.0023
##
## ------------------------------------------------------------------------------
## | Linearized
## bmival | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .5474219 .2025698 2.70 0.007 .1500479 .9447959
## _cons | 27.22889 .1233456 220.75 0.000 26.98693 27.47085
## ------------------------------------------------------------------------------
##
## . svy: regress bmival i.CB age i.Sex i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 5,759
## Number of PSUs = 1,408 Population size = 5,678.1909
## Design df = 1,396
## F( 6, 1391) = 16.82
## Prob > F = 0.0000
## R-squared = 0.0339
##
## ------------------------------------------------------------------------------
## | Linearized
## bmival | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .4426651 .2017238 2.19 0.028 .0469506 .8383796
## age | .0417652 .00582 7.18 0.000 .0303484 .0531821
## |
## Sex |
## Women | -.2173063 .1861902 -1.17 0.243 -.5825491 .1479364
## |
## cigsta3 |
## ex-smoker | 1.183842 .2994778 3.95 0.000 .596367 1.771317
## Never | .4876578 .2488466 1.96 0.050 -.0004958 .9758115
## |
## dnnow |
## yes | .4296711 .2453108 1.75 0.080 -.0515465 .9108887
## _cons | 24.76124 .3497594 70.80 0.000 24.07513 25.44735
## ------------------------------------------------------------------------------
##
## .
## . svy: regress wstval i.CB#i.Sex age i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 4,864
## Number of PSUs = 1,370 Population size = 4,522.9738
## Design df = 1,358
## F( 7, 1352) = 105.53
## Prob > F = 0.0000
## R-squared = 0.2049
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## CB#Sex |
## 1#Women | -9.548281 .5987538 -15.95 0.000 -10.72286 -8.373698
## 2#Men | 1.101516 .8381474 1.31 0.189 -.5426876 2.74572
## 2#Women | -9.654859 .7472127 -12.92 0.000 -11.12068 -8.189043
## |
## age | .2321863 .0158729 14.63 0.000 .2010482 .2633243
## |
## cigsta3 |
## ex-smoker | 1.770304 .8655538 2.05 0.041 .0723361 3.468271
## Never | -1.013585 .7438516 -1.36 0.173 -2.472808 .4456378
## |
## dnnow |
## yes | 2.118908 .6652328 3.19 0.001 .8139127 3.423904
## _cons | 86.30946 1.019941 84.62 0.000 84.30863 88.31029
## ------------------------------------------------------------------------------
##
## .
## . svy: regress wst i.CB age i.cigsta3 i.dnnow if Sex == 1
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 2,004
## Number of PSUs = 1,055 Population size = 2,210.0429
## Design df = 1,043
## F( 5, 1039) = 35.14
## Prob > F = 0.0000
## R-squared = 0.1472
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | 1.007916 .8319585 1.21 0.226 -.624587 2.640419
## age | .2729095 .0246606 11.07 0.000 .2245195 .3212996
## |
## cigsta3 |
## ex-smoker | 2.220963 1.246324 1.78 0.075 -.2246258 4.666551
## Never | -.2888131 1.089376 -0.27 0.791 -2.426431 1.848805
## |
## dnnow |
## yes | 1.321979 1.015162 1.30 0.193 -.6700136 3.313973
## _cons | 84.01739 1.525234 55.08 0.000 81.02451 87.01027
## ------------------------------------------------------------------------------
##
## . svy: regress wst i.CB age i.cigsta3 i.dnnow if Sex == 2
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 2,860
## Number of PSUs = 1,230 Population size = 2,312.9309
## Design df = 1,218
## F( 5, 1214) = 25.13
## Prob > F = 0.0000
## R-squared = 0.0817
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .0698594 .7441777 0.09 0.925 -1.390153 1.529872
## age | .1972089 .0197849 9.97 0.000 .1583927 .2360251
## |
## cigsta3 |
## ex-smoker | .8837992 1.164231 0.76 0.448 -1.400322 3.16792
## Never | -1.825048 1.008156 -1.81 0.070 -3.802964 .1528668
## |
## dnnow |
## yes | 2.801683 .8710974 3.22 0.001 1.092665 4.5107
## _cons | 78.97532 1.246172 63.37 0.000 76.53044 81.4202
## ------------------------------------------------------------------------------##
## . use "/home/wangcc-me/Downloads/UKDA-6533-stata11_se/stata11_se/CW3CB2_regss.d
## > ta", clear
##
## .
## . label define smoking 1 "current" 2 "ex-smoker" 3 "Never"
##
## . label values cigsta3 smoking
##
## . label define drinking 1 "no" 2 "yes"
##
## . label values dnnow drinking
##
## . label define gender 1 "Men" 2 "Women"
##
## . label values Sex gender
##
## .
## .
## . svyset area [pweight = wti1to8], strata(gor)
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## . svydescribe wti
##
## Survey: Describing stage 1 sampling units
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## #Obs with #Obs with #Obs per included Unit
## #Units #Units complete missing ----------------------------
## Stratum included omitted data data min mean max
## -------- -------- -------- -------- -------- -------- -------- --------
## 1 42 0 215 0 2 5.1 8
## 2 111 0 480 0 1 4.3 9
## 3 83 0 340 0 1 4.1 7
## 4 71 0 327 0 1 4.6 8
## 5 84 0 403 0 1 4.8 8
## 6 89 0 424 0 2 4.8 9
## 7 111 0 380 0 1 3.4 8
## 8 130 0 575 0 1 4.4 8
## 9 82 0 348 0 2 4.2 8
## 10 184 0 846 0 1 4.6 9
## 11 255 0 1,033 0 1 4.1 9
## 12 172 0 784 0 1 4.6 9
## -------- -------- -------- -------- -------- -------- -------- --------
## 12 1,414 0 6,155 0 1 4.4 9
## ------------------
## 6,155
##
## . svy: mean bmival
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.41424 .1007122 27.21667 27.6118
## --------------------------------------------------------------
##
## . svy: mean bmival if CB == 1
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 3,493
## Number of PSUs = 1,330 Population size = 3,353.6321
## Design df = 1,318
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.23762 .1280732 26.98637 27.48887
## --------------------------------------------------------------
##
## . svy: mean bmival if CB == 2
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 2,269
## Number of PSUs = 1,149 Population size = 2,329.4141
## Design df = 1,137
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.66851 .1592101 27.35613 27.98089
## --------------------------------------------------------------
##
## .
## . svy: regress bmival i.CB
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
## F( 1, 1396) = 4.49
## Prob > F = 0.0343
## R-squared = 0.0016
##
## ------------------------------------------------------------------------------
## | Linearized
## bmival | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .4308947 .2033444 2.12 0.034 .0320012 .8297882
## _cons | 27.23762 .1281177 212.60 0.000 26.98629 27.48894
## ------------------------------------------------------------------------------
##
## . svy: regress bmival i.CB age i.Sex i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 5,759
## Number of PSUs = 1,408 Population size = 5,678.1909
## Design df = 1,396
## F( 6, 1391) = 16.00
## Prob > F = 0.0000
## R-squared = 0.0332
##
## ------------------------------------------------------------------------------
## | Linearized
## bmival | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .303214 .1983815 1.53 0.127 -.0859439 .6923719
## age | .0419207 .0057981 7.23 0.000 .0305467 .0532948
## |
## Sex |
## Women | -.220035 .186015 -1.18 0.237 -.5849341 .144864
## |
## cigsta3 |
## ex-smoker | 1.177303 .3000094 3.92 0.000 .5887854 1.765821
## Never | .4646605 .2490891 1.87 0.062 -.0239687 .9532898
## |
## dnnow |
## yes | .4170172 .2441024 1.71 0.088 -.0618298 .8958643
## _cons | 24.79733 .3541021 70.03 0.000 24.1027 25.49196
## ------------------------------------------------------------------------------##
## .
## . use "/home/wangcc-me/Downloads/UKDA-6533-stata11_se/stata11_se/LCGA_2class.dt
## > a", clear
##
## .
## . label define smoking 1 "current" 2 "ex-smoker" 3 "Never"
##
## . label values cigsta3 smoking
##
## . label define drinking 1 "no" 2 "yes"
##
## . label values dnnow drinking
##
## . label define gender 1 "Men" 2 "Women"
##
## . label values Sex gender
##
## .
## .
## .
## . svyset area [pweight = wti1to8], strata(gor)
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## . svydescribe wti
##
## Survey: Describing stage 1 sampling units
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## #Obs with #Obs with #Obs per included Unit
## #Units #Units complete missing ----------------------------
## Stratum included omitted data data min mean max
## -------- -------- -------- -------- -------- -------- -------- --------
## 1 42 0 215 0 2 5.1 8
## 2 111 0 480 0 1 4.3 9
## 3 83 0 340 0 1 4.1 7
## 4 71 0 327 0 1 4.6 8
## 5 84 0 403 0 1 4.8 8
## 6 89 0 424 0 2 4.8 9
## 7 111 0 380 0 1 3.4 8
## 8 130 0 575 0 1 4.4 8
## 9 82 0 348 0 2 4.2 8
## 10 184 0 846 0 1 4.6 9
## 11 255 0 1,033 0 1 4.1 9
## 12 172 0 784 0 1 4.6 9
## -------- -------- -------- -------- -------- -------- -------- --------
## 12 1,414 0 6,155 0 1 4.4 9
## ------------------
## 6,155
##
## . svy: mean bmival
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.41424 .1007122 27.21667 27.6118
## --------------------------------------------------------------
##
## . svy: mean bmival if C == 1
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 3,995
## Number of PSUs = 1,362 Population size = 3,839.1006
## Design df = 1,350
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.58884 .1261062 27.34146 27.83623
## --------------------------------------------------------------
##
## . svy: mean bmival if C == 2
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 1,767
## Number of PSUs = 998 Population size = 1,843.9456
## Design df = 986
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.05071 .1526066 26.75124 27.35018
## --------------------------------------------------------------
##
## .
## .
## .
## . svy: regress bmival i.C
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
## F( 1, 1396) = 7.69
## Prob > F = 0.0056
## R-squared = 0.0022
##
## ------------------------------------------------------------------------------
## | Linearized
## bmival | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.C | -.5381346 .1940585 -2.77 0.006 -.9188123 -.1574569
## _cons | 27.58884 .1261553 218.69 0.000 27.34137 27.83632
## ------------------------------------------------------------------------------
##
## . svy: regress bmival i.C age i.Sex i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 5,759
## Number of PSUs = 1,408 Population size = 5,678.1909
## Design df = 1,396
## F( 6, 1391) = 18.02
## Prob > F = 0.0000
## R-squared = 0.0361
##
## ------------------------------------------------------------------------------
## | Linearized
## bmival | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.C | -.7014704 .190913 -3.67 0.000 -1.075978 -.3269631
## age | .0443449 .0057965 7.65 0.000 .032974 .0557157
## |
## Sex |
## Women | -.2403073 .1847549 -1.30 0.194 -.6027345 .1221198
## |
## cigsta3 |
## ex-smoker | 1.170385 .2986249 3.92 0.000 .5845836 1.756187
## Never | .4235318 .2485641 1.70 0.089 -.0640676 .9111313
## |
## dnnow |
## yes | .3127793 .2413658 1.30 0.195 -.1606995 .786258
## _cons | 25.08751 .3500082 71.68 0.000 24.40091 25.77411
## ------------------------------------------------------------------------------##
## . use "/home/wangcc-me/Downloads/UKDA-6533-stata11_se/stata11_se/LCGA_3class.dt
## > a", clear
##
## .
## . label define smoking 1 "current" 2 "ex-smoker" 3 "Never"
##
## . label values cigsta3 smoking
##
## . label define drinking 1 "no" 2 "yes"
##
## . label values dnnow drinking
##
## . label define gender 1 "Men" 2 "Women"
##
## . label values Sex gender
##
## .
## .
## . svyset area [pweight = wti1to8], strata(gor)
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## . svy: mean bmival
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.41424 .1007122 27.21667 27.6118
## --------------------------------------------------------------
##
## . svy: mean bmival if C == 1
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 1,653
## Number of PSUs = 964 Population size = 1,588.6944
## Design df = 952
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.50674 .2127282 27.08927 27.92421
## --------------------------------------------------------------
##
## . svy: mean bmival if C == 2
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 351
## Number of PSUs = 305 Population size = 406.06487
## Design df = 293
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.03672 .3064126 26.43367 27.63977
## --------------------------------------------------------------
##
## . svy: mean bmival if C == 3
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 3,758
## Number of PSUs = 1,330 Population size = 3,688.287
## Design df = 1,318
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## bmival | 27.41596 .1174526 27.18554 27.64637
## --------------------------------------------------------------
##
## . svy: regress bmival i.C
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 5,762
## Number of PSUs = 1,408 Population size = 5,683.0462
## Design df = 1,396
## F( 2, 1395) = 0.84
## Prob > F = 0.4330
## R-squared = 0.0004
##
## ------------------------------------------------------------------------------
## | Linearized
## bmival | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## C |
## 2 | -.4700138 .3713259 -1.27 0.206 -1.198431 .2584031
## 3 | -.0907806 .238746 -0.38 0.704 -.5591203 .3775591
## |
## _cons | 27.50674 .2125638 129.40 0.000 27.08976 27.92372
## ------------------------------------------------------------------------------
##
## . svy: regress bmival i.C age i.Sex i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 5,759
## Number of PSUs = 1,408 Population size = 5,678.1909
## Design df = 1,396
## F( 7, 1390) = 13.90
## Prob > F = 0.0000
## R-squared = 0.0340
##
## ------------------------------------------------------------------------------
## | Linearized
## bmival | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## C |
## 2 | -.7507808 .3720919 -2.02 0.044 -1.4807 -.0208612
## 3 | -.3979093 .2410511 -1.65 0.099 -.8707707 .0749522
## |
## age | .0443295 .0058438 7.59 0.000 .0328659 .0557931
## |
## Sex |
## Women | -.2195277 .1850225 -1.19 0.236 -.5824798 .1434244
## |
## cigsta3 |
## ex-smoker | 1.184243 .2999359 3.95 0.000 .5958689 1.772616
## Never | .4416676 .2489203 1.77 0.076 -.0466307 .9299658
## |
## dnnow |
## yes | .3043295 .2443122 1.25 0.213 -.1749292 .7835882
## _cons | 25.15022 .3712491 67.74 0.000 24.42196 25.87849
## ------------------------------------------------------------------------------##
## . use "/home/wangcc-me/Downloads/UKDA-6533-stata11_se/stata11_se/CW2CB2_regss.d
## > ta", clear
##
## .
## . label define smoking 1 "current" 2 "ex-smoker" 3 "Never"
##
## . label values cigsta3 smoking
##
## . label define drinking 1 "no" 2 "yes"
##
## . label values dnnow drinking
##
## . label define gender 1 "Men" 2 "Women"
##
## . label values Sex gender
##
## .
## .
## . svyset area [pweight = wti1to8], strata(gor)
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## .
## . //svydescribe wti
## . svy: mean wstval
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 4,866
## Number of PSUs = 1,370 Population size = 4,526.3997
## Design df = 1,358
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## wstval | 93.14676 .3030883 92.55219 93.74133
## --------------------------------------------------------------
##
## . svy: mean wstval if CB == 1
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 3,269
## Number of PSUs = 1,270 Population size = 2,963.6088
## Design df = 1,258
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## wstval | 92.59988 .354112 91.90516 93.29459
## --------------------------------------------------------------
##
## . svy: mean wstval if CB == 2
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 1,597
## Number of PSUs = 953 Population size = 1,562.7909
## Design df = 941
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## wstval | 94.18384 .5374614 93.12908 95.2386
## --------------------------------------------------------------
##
## .
## .
## . svy: regress wst i.CB
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 4,866
## Number of PSUs = 1,370 Population size = 4,526.3997
## Design df = 1,358
## F( 1, 1358) = 6.21
## Prob > F = 0.0128
## R-squared = 0.0026
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | 1.58396 .6354687 2.49 0.013 .3373536 2.830567
## _cons | 92.59988 .3542883 261.37 0.000 91.90487 93.29489
## ------------------------------------------------------------------------------
##
## . svy: regress wst i.CB age i.Sex i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 4,864
## Number of PSUs = 1,370 Population size = 4,522.9738
## Design df = 1,358
## F( 6, 1353) = 122.48
## Prob > F = 0.0000
## R-squared = 0.2045
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .5044856 .5701978 0.88 0.376 -.6140785 1.62305
## age | .2319529 .0158976 14.59 0.000 .2007663 .2631394
## |
## Sex |
## Women | -9.966613 .4960872 -20.09 0.000 -10.93979 -8.993432
## |
## cigsta3 |
## ex-smoker | 1.760095 .8669077 2.03 0.043 .0594715 3.460719
## Never | -1.02313 .7444026 -1.37 0.170 -2.483433 .4371741
## |
## dnnow |
## yes | 2.137331 .6651172 3.21 0.001 .8325619 3.442099
## _cons | 86.54583 1.037529 83.42 0.000 84.5105 88.58116
## ------------------------------------------------------------------------------
##
## . svy: regress wstval i.CB#i.Sex age i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 4,864
## Number of PSUs = 1,370 Population size = 4,522.9738
## Design df = 1,358
## F( 7, 1352) = 105.53
## Prob > F = 0.0000
## R-squared = 0.2049
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## CB#Sex |
## 1#Women | -9.548281 .5987538 -15.95 0.000 -10.72286 -8.373698
## 2#Men | 1.101516 .8381474 1.31 0.189 -.5426876 2.74572
## 2#Women | -9.654859 .7472127 -12.92 0.000 -11.12068 -8.189043
## |
## age | .2321863 .0158729 14.63 0.000 .2010482 .2633243
## |
## cigsta3 |
## ex-smoker | 1.770304 .8655538 2.05 0.041 .0723361 3.468271
## Never | -1.013585 .7438516 -1.36 0.173 -2.472808 .4456378
## |
## dnnow |
## yes | 2.118908 .6652328 3.19 0.001 .8139127 3.423904
## _cons | 86.30946 1.019941 84.62 0.000 84.30863 88.31029
## ------------------------------------------------------------------------------
##
## .
## . svy: regress wst i.CB age i.cigsta3 i.dnnow if Sex == 1
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 2,004
## Number of PSUs = 1,055 Population size = 2,210.0429
## Design df = 1,043
## F( 5, 1039) = 35.14
## Prob > F = 0.0000
## R-squared = 0.1472
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | 1.007916 .8319585 1.21 0.226 -.624587 2.640419
## age | .2729095 .0246606 11.07 0.000 .2245195 .3212996
## |
## cigsta3 |
## ex-smoker | 2.220963 1.246324 1.78 0.075 -.2246258 4.666551
## Never | -.2888131 1.089376 -0.27 0.791 -2.426431 1.848805
## |
## dnnow |
## yes | 1.321979 1.015162 1.30 0.193 -.6700136 3.313973
## _cons | 84.01739 1.525234 55.08 0.000 81.02451 87.01027
## ------------------------------------------------------------------------------
##
## . svy: regress wst i.CB age i.cigsta3 i.dnnow if Sex == 2
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 2,860
## Number of PSUs = 1,230 Population size = 2,312.9309
## Design df = 1,218
## F( 5, 1214) = 25.13
## Prob > F = 0.0000
## R-squared = 0.0817
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .0698594 .7441777 0.09 0.925 -1.390153 1.529872
## age | .1972089 .0197849 9.97 0.000 .1583927 .2360251
## |
## cigsta3 |
## ex-smoker | .8837992 1.164231 0.76 0.448 -1.400322 3.16792
## Never | -1.825048 1.008156 -1.81 0.070 -3.802964 .1528668
## |
## dnnow |
## yes | 2.801683 .8710974 3.22 0.001 1.092665 4.5107
## _cons | 78.97532 1.246172 63.37 0.000 76.53044 81.4202
## ------------------------------------------------------------------------------##
## . use "/home/wangcc-me/Downloads/UKDA-6533-stata11_se/stata11_se/CW3CB2_regss.d
## > ta", clear
##
## .
## . label define smoking 1 "current" 2 "ex-smoker" 3 "Never"
##
## . label values cigsta3 smoking
##
## . label define drinking 1 "no" 2 "yes"
##
## . label values dnnow drinking
##
## . label define gender 1 "Men" 2 "Women"
##
## . label values Sex gender
##
## .
## .
## . svyset area [pweight = wti1to8], strata(gor)
##
## pweight: wti1to8
## VCE: linearized
## Single unit: missing
## Strata 1: gor
## SU 1: area
## FPC 1: <zero>
##
## . //svydescribe wti
## . svy: mean wstval
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 4,866
## Number of PSUs = 1,370 Population size = 4,526.3997
## Design df = 1,358
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## wstval | 93.14676 .3030883 92.55219 93.74133
## --------------------------------------------------------------
##
## . svy: mean wstval if CB == 1
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 2,935
## Number of PSUs = 1,245 Population size = 2,634.0044
## Design df = 1,233
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## wstval | 92.60728 .3779162 91.86585 93.34871
## --------------------------------------------------------------
##
## . svy: mean wstval if CB == 2
## (running mean on estimation sample)
##
## Survey: Mean estimation
##
## Number of strata = 12 Number of obs = 1,931
## Number of PSUs = 1,050 Population size = 1,892.3952
## Design df = 1,038
##
## --------------------------------------------------------------
## | Linearized
## | Mean Std. Err. [95% Conf. Interval]
## -------------+------------------------------------------------
## wstval | 93.89765 .4802864 92.9552 94.84009
## --------------------------------------------------------------
##
## .
## . svy: regress wstval i.CB
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 4,866
## Number of PSUs = 1,370 Population size = 4,526.3997
## Design df = 1,358
## F( 1, 1358) = 4.57
## Prob > F = 0.0327
## R-squared = 0.0019
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | 1.290361 .6036378 2.14 0.033 .1061974 2.474525
## _cons | 92.60728 .3783073 244.79 0.000 91.86515 93.34941
## ------------------------------------------------------------------------------
##
## . svy: regress wstval i.CB age i.Sex i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 4,864
## Number of PSUs = 1,370 Population size = 4,522.9738
## Design df = 1,358
## F( 6, 1353) = 122.68
## Prob > F = 0.0000
## R-squared = 0.2043
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .3030171 .5443727 0.56 0.578 -.7648856 1.37092
## age | .2322472 .0159144 14.59 0.000 .2010277 .2634667
## |
## Sex |
## Women | -9.974058 .4961632 -20.10 0.000 -10.94739 -9.000728
## |
## cigsta3 |
## ex-smoker | 1.756207 .867831 2.02 0.043 .0537724 3.458642
## Never | -1.047745 .7458575 -1.40 0.160 -2.510903 .4154127
## |
## dnnow |
## yes | 2.11752 .6700737 3.16 0.002 .8030285 3.432012
## _cons | 86.60076 1.03881 83.37 0.000 84.56292 88.63861
## ------------------------------------------------------------------------------
##
## . svy: regress wstval i.CB#i.Sex age i.cigsta3 i.dnnow
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 4,864
## Number of PSUs = 1,370 Population size = 4,522.9738
## Design df = 1,358
## F( 7, 1352) = 106.35
## Prob > F = 0.0000
## R-squared = 0.2048
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## CB#Sex |
## 1#Women | -9.433292 .6485554 -14.55 0.000 -10.70557 -8.161013
## 2#Men | .9544724 .7865362 1.21 0.225 -.5884855 2.49743
## 2#Women | -9.772736 .7145914 -13.68 0.000 -11.17456 -8.370913
## |
## age | .2326582 .0158705 14.66 0.000 .2015249 .2637915
## |
## cigsta3 |
## ex-smoker | 1.779444 .8660151 2.05 0.040 .0805716 3.478317
## Never | -1.023565 .744927 -1.37 0.170 -2.484897 .4377677
## |
## dnnow |
## yes | 2.11134 .6704899 3.15 0.002 .7960313 3.426648
## _cons | 86.27719 1.032217 83.58 0.000 84.25228 88.30211
## ------------------------------------------------------------------------------
##
## .
## . svy: regress wst i.CB age i.cigsta3 i.dnnow if Sex == 1
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 2,004
## Number of PSUs = 1,055 Population size = 2,210.0429
## Design df = 1,043
## F( 5, 1039) = 34.97
## Prob > F = 0.0000
## R-squared = 0.1469
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | .8469548 .7862104 1.08 0.282 -.6957794 2.389689
## age | .2730792 .0246291 11.09 0.000 .2247509 .3214075
## |
## cigsta3 |
## ex-smoker | 2.228784 1.246717 1.79 0.074 -.2175751 4.675143
## Never | -.3074656 1.094631 -0.28 0.779 -2.455395 1.840464
## |
## dnnow |
## yes | 1.354839 1.036369 1.31 0.191 -.6787675 3.388445
## _cons | 84.01157 1.538635 54.60 0.000 80.9924 87.03075
## ------------------------------------------------------------------------------
##
## . svy: regress wst i.CB age i.cigsta3 i.dnnow if Sex == 2
## (running regress on estimation sample)
##
## Survey: Linear regression
##
## Number of strata = 12 Number of obs = 2,860
## Number of PSUs = 1,230 Population size = 2,312.9309
## Design df = 1,218
## F( 5, 1214) = 25.07
## Prob > F = 0.0000
## R-squared = 0.0817
##
## ------------------------------------------------------------------------------
## | Linearized
## wstval | Coef. Std. Err. t P>|t| [95% Conf. Interval]
## -------------+----------------------------------------------------------------
## 2.CB | -.1199631 .7232051 -0.17 0.868 -1.538829 1.298903
## age | .1977461 .0198613 9.96 0.000 .15878 .2367123
## |
## cigsta3 |
## ex-smoker | .8888833 1.165275 0.76 0.446 -1.397286 3.175053
## Never | -1.832319 1.009376 -1.82 0.070 -3.812628 .1479893
## |
## dnnow |
## yes | 2.76985 .875656 3.16 0.002 1.051889 4.487811
## _cons | 79.02893 1.242135 63.62 0.000 76.59197 81.46589
## ------------------------------------------------------------------------------