##
## Присоединяю пакет: 'dplyr'
## Следующие объекты скрыты от 'package:stats':
##
## filter, lag
## Следующие объекты скрыты от 'package:base':
##
## intersect, setdiff, setequal, union
##
## Присоединяю пакет: 'kableExtra'
## Следующий объект скрыт от 'package:dplyr':
##
## group_rows
##
## Присоединяю пакет: 'table1'
## Следующие объекты скрыты от 'package:base':
##
## units, units<-
##
## Присоединяю пакет: 'data.table'
## Следующие объекты скрыты от 'package:dplyr':
##
## between, first, last
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.5
## ✔ lubridate 1.9.3 ✔ stringr 1.5.1
## ✔ purrr 1.0.2 ✔ tibble 3.2.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ data.table::between() masks dplyr::between()
## ✖ dplyr::filter() masks stats::filter()
## ✖ data.table::first() masks dplyr::first()
## ✖ kableExtra::group_rows() masks dplyr::group_rows()
## ✖ lubridate::hour() masks data.table::hour()
## ✖ lubridate::isoweek() masks data.table::isoweek()
## ✖ dplyr::lag() masks stats::lag()
## ✖ data.table::last() masks dplyr::last()
## ✖ lubridate::mday() masks data.table::mday()
## ✖ lubridate::minute() masks data.table::minute()
## ✖ lubridate::month() masks data.table::month()
## ✖ lubridate::quarter() masks data.table::quarter()
## ✖ lubridate::second() masks data.table::second()
## ✖ purrr::transpose() masks data.table::transpose()
## ✖ lubridate::wday() masks data.table::wday()
## ✖ lubridate::week() masks data.table::week()
## ✖ lubridate::yday() masks data.table::yday()
## ✖ lubridate::year() masks data.table::year()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
##
## Присоединяю пакет: 'magrittr'
##
## Следующий объект скрыт от 'package:purrr':
##
## set_names
##
## Следующий объект скрыт от 'package:tidyr':
##
## extract
##
## Присоединяю пакет: 'gridExtra'
##
## Следующий объект скрыт от 'package:dplyr':
##
## combine
## Загрузка требуемого пакета: carData
##
## Присоединяю пакет: 'car'
##
## Следующий объект скрыт от 'package:purrr':
##
## some
##
## Следующий объект скрыт от 'package:dplyr':
##
## recode
##
## Присоединяю пакет: 'psych'
##
## Следующий объект скрыт от 'package:car':
##
## logit
##
## Следующие объекты скрыты от 'package:ggplot2':
##
## %+%, alpha
##
## Присоединяю пакет: 'scales'
##
## Следующие объекты скрыты от 'package:psych':
##
## alpha, rescale
##
## Следующий объект скрыт от 'package:purrr':
##
## discard
##
## Следующий объект скрыт от 'package:readr':
##
## col_factor
##
## Присоединяю пакет: 'DescTools'
##
## Следующие объекты скрыты от 'package:psych':
##
## AUC, ICC, SD
##
## Следующий объект скрыт от 'package:car':
##
## Recode
##
## Следующий объект скрыт от 'package:data.table':
##
## %like%
db <- import("C:/Users/DP/Downloads/F00011356-WVS_Cross-National_Wave_7_csv_v5_0//WVS_Cross-National_Wave_7_csv_v5_0.csv")Select observations from Cyprus
I will keep only the variables necessary for further analysis.
Значения переменной из codebook:
1.- Never justifiable 2.- 2 3.- 3 4.- 4 5.- 5 6.- 6 7.- 7 8.- 8 9.- 9 10.- Always justifiable
-1-.- Don´t know -2-.- No answer -4-.- Not asked in survey -5-.- Missing; Not available
Accordingly, I will recode -1, -2, -4, and -5 as NA so that these values do not affect the results of further analysis.
Changing the name of the variable for convenient use in the analysis
Encoding the variable as numeric
Variable values from codebook:
Numeric variable – numbers of years -1-.- Don’t know -2-.- No answer -4-.- Not asked -5-.- Missing; Not available
Changing the name of the variable for convenient use in the analysis
Encoding the variable as numeric
Variable values from codebook: 1.- Male 2.- Female -2-.- No answer -4-.- Not asked -5-.- Missing; Not available; AU: Other
Changing the name of the variable for convenient use in the analysis
I change the value of 1 to male, and the value of 2 to female to make it easier to work with the variable
Encoding the variable as a factor
Variable values from codebook: 1.- Lower 2.- Middle 3.- Higher -1-.- Don´t know -2-.- No answer -4-.- Not asked -5-.- Missing; Not available
Changing the name of the variable for convenient use in the analysis
I change the value 1 to lower, 2 to middle, 3 to higher to make it easier to work with the variable
Variable values from codebook:
1.- Daily 2.- Weekly 3.- Monthly 4.- Less than monthly 5.- Never -1-.- Don´t know -2-.- No answer -4-.- Not asked -5-.- Missing; Not available
Changing the name of the variable for convenient use in the analysis
I change the value 1 to daily, 2 to weekly, 3 to monthly, 4 to less than monthly, 5 to never to make it easier to work with the variable
Variable values from codebook:
if Y001_1>-2 and Y001_2>-2 and Y001_3>-2 and Y001_4>-2 and Y001_5>-2 THEN Y001_1+Y001_2+Y001_3+Y001_4+Y001_5 else -2
Changing the name of the variable for convenient use in the analysis
Encoding the variable as numeric
Checking the types of variables
## [1] "factor"
## [1] "factor"
## [1] "numeric"
## [1] "factor"
## [1] "numeric"
## [1] "numeric"
Creating a beautiful table :)
label(db$int_use) = 'frequency of Internet use'
label(db$gndr) = 'gender'
label(db$age) = 'age'
label(db$educ_lvl) = 'highest educational level'
label(db$ind_mat) = 'index of postmaterialism'
label(db$sex_bef_mar) = 'justification of sexual relationship before marriage'
t1kable(table1(~int_use + gndr + age + educ_lvl + ind_mat + sex_bef_mar, data = db))%>%
kable_styling(font_size = 16)| Overall | |
|---|---|
| (N=824) | |
| frequency of Internet use | |
| daily | 483 (58.6%) |
| weekly | 113 (13.7%) |
| monthly | 26 (3.2%) |
| less than monthly | 18 (2.2%) |
| never | 184 (22.3%) |
| gender | |
| male | 401 (48.7%) |
| female | 423 (51.3%) |
| age | |
| Mean (SD) | 43.7 (16.2) |
| Median [Min, Max] | 42.0 [18.0, 92.0] |
| highest educational level | |
| lower | 182 (22.1%) |
| middle | 228 (27.7%) |
| higher | 414 (50.2%) |
| index of postmaterialism | |
| Mean (SD) | 2.31 (1.25) |
| Median [Min, Max] | 2.00 [0, 5.00] |
| justification of sexual relationship before marriage | |
| Mean (SD) | 5.26 (3.15) |
| Median [Min, Max] | 5.00 [1.00, 10.0] |
Seems relatively legit, now I need to understand our variables from our dataset graphically.
For that i will need to create:
Box plot, to show the continuous variables and spot outliers.
Density plot, to check if the distribution of our continuous variables is close to normal.
Barplot, to see if the categoricalal variables are representative.
Scatter plot, to visualize the linear relationship between the variables.
db %>%
pivot_longer(c(age, ind_mat, sex_bef_mar),
names_to = 'Var', values_to = 'Score') %>%
ggplot(aes(y = Score)) +
geom_boxplot() +
ggtitle("Distribution of scores") +
xlab("Variable") +
ylab("Score") +
theme_bw() +
theme(legend.position = "none") +
facet_wrap(~Var, scales = 'free')
It can be seen that there are no outliers
db %>%
pivot_longer(c(age, ind_mat, sex_bef_mar),
names_to = 'Var', values_to = 'Score') %>%
ggplot(aes(x=Score, fill=Var)) +
geom_histogram(aes(y=..density.., fill = Var), bins = 10) +
geom_density(alpha = .5, color="blue")+
ggtitle("Distribution of scores") +
xlab("Variable") +
ylab("Score") +
theme_bw()+
theme(legend.position="none") +
facet_wrap(~Var, scales = 'free')## Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(density)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
As it can be seen from the histograms, ind_mat is slightly close to
normal distribution. As for sex_bef_mar and age , the histograms are not
normally distributed. However, I can surely work with that.
db %>%
ggplot(aes(x = gndr)) +
geom_bar(fill = "lightpink", color = "lightblue") +
xlab("Category") +
ylab("Frequency") +
theme_bw()
I see that the groups are comparable in size, there are slightly more
female than male
db %>%
ggplot(aes(x = int_use)) +
geom_bar(fill = "lightpink", color = "lightblue") +
xlab("Category") +
ylab("Frequency") +
theme_bw() ##
## daily weekly monthly less than monthly
## 0.58616505 0.13713592 0.03155340 0.02184466
## never
## 0.22330097
You can see that the data is not of comparable size, it is better to combine some categories so that they are approximately the same size. So, if I combine the smallest categories (weekly, monthly, less than monthly) into the category rarely, I get the following:
db$int_use <- ifelse(db$int_use %in% c("weekly", "monthly", "less than monthly"), "rarely",
ifelse(db$int_use == "daily", "daily",
ifelse(db$int_use == "never", "never", NA)))##
## daily never rarely
## 0.586165 0.223301 0.190534
db %>%
ggplot(aes(x = int_use)) +
geom_bar(fill = "lightpink", color = "lightblue") +
xlab("Category") +
ylab("Frequency") +
theme_bw()
The groups have become more comparable in size
db %>%
ggplot(aes(x = educ_lvl)) +
geom_bar(fill = "lightpink", color = "lightblue") +
xlab("Category") +
ylab("Frequency") +
theme_bw() ##
## lower middle higher
## 0.2208738 0.2766990 0.5024272
I can see that the data is not very comparable, but I can use
plot = ggplot(data = db, aes(x = age, y = ind_mat)) + geom_point() + geom_smooth(method = lm, fill="blue", color="blue", se = FALSE) + ggtitle("Age by index of postmaterialism") + xlab("Age") + ylab("index of postmaterialism")
plot## `geom_smooth()` using formula = 'y ~ x'
there is a negative correlation between age and ind_mat
plot1 = ggplot(data = db, aes(x = age, y = sex_bef_mar)) + geom_point() + geom_smooth(method = lm, fill="blue", color="blue", se = FALSE) + ggtitle("Age by justification of sexual relationship before marriage") + xlab("Age") + ylab("justification of sexual relationship before marriage")
plot1## `geom_smooth()` using formula = 'y ~ x'
very weak negative relationship between age and sex_bef_mr
plot2 = ggplot(data = db, aes(x = ind_mat, y = sex_bef_mar)) + geom_point() + geom_smooth(method = lm, fill="blue", color="blue", se = FALSE) + ggtitle("Iindex of postmaterialism by justification of sexual relationship before marriage") + xlab("index of postmaterialism") + ylab("justification of sexual relationship before marriage")
plot2## `geom_smooth()` using formula = 'y ~ x'
there is a rather weak negative relationship between age and
sex_bef_mr
## Загрузка требуемого пакета: plotly
##
## Присоединяю пакет: 'plotly'
## Следующий объект скрыт от 'package:ggplot2':
##
## last_plot
## Следующий объект скрыт от 'package:rio':
##
## export
## Следующий объект скрыт от 'package:stats':
##
## filter
## Следующий объект скрыт от 'package:graphics':
##
## layout
## Загрузка требуемого пакета: viridis
## Загрузка требуемого пакета: viridisLite
##
## Присоединяю пакет: 'viridis'
## Следующий объект скрыт от 'package:scales':
##
## viridis_pal
## Registered S3 methods overwritten by 'registry':
## method from
## print.registry_field proxy
## print.registry_entry proxy
##
## ======================
## Welcome to heatmaply version 1.5.0
##
## Type citation('heatmaply') for how to cite the package.
## Type ?heatmaply for the main documentation.
##
## The github page is: https://github.com/talgalili/heatmaply/
## Please submit your suggestions and bug-reports at: https://github.com/talgalili/heatmaply/issues
## You may ask questions at stackoverflow, use the r and heatmaply tags:
## https://stackoverflow.com/questions/tagged/heatmaply
## ======================
From what I can see, all the relationships between our variables are quite insignificant and have a negative orientation. What is interesting, that the highest correlation coefficient is between age and ind_mat. The presented values confirm the situation on the scatterplots.
Estimate a model to predict justification of sexual relationship before marriage (Q186) by age (Q262), gender (Q260), highest educational level (3 groups) (Q275R), frequency of Internet use as a source of information (Q206), 12-item index of postmaterialism (Y001), as well as an interaction between age and gender (1 point).
##
## Call:
## lm(formula = Zsex_bef_mar ~ educ_lvl + int_use + Zind_mat + Zage *
## gndr, data = db)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.85663 -0.88954 0.03154 0.76192 1.95172
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.06898 0.10695 0.645 0.51915
## educ_lvlmiddle 0.26994 0.10765 2.508 0.01235 *
## educ_lvlhigher -0.13089 0.11202 -1.168 0.24298
## int_usenever -0.29839 0.11184 -2.668 0.00778 **
## int_userarely -0.28243 0.09028 -3.128 0.00182 **
## Zind_mat -0.04262 0.03473 -1.227 0.22011
## Zage 0.10664 0.05599 1.904 0.05721 .
## gndrfemale 0.07720 0.06847 1.127 0.25991
## Zage:gndrfemale -0.19422 0.06938 -2.799 0.00524 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9769 on 815 degrees of freedom
## Multiple R-squared: 0.05488, Adjusted R-squared: 0.0456
## F-statistic: 5.916 on 8 and 815 DF, p-value: 2.207e-07
| Zsex_bef_mar | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.07 | -0.14 – 0.28 | 0.519 |
|
highest educational level: middle |
0.27 | 0.06 – 0.48 | 0.012 |
|
highest educational level: higher |
-0.13 | -0.35 – 0.09 | 0.243 |
| int_usenever | -0.30 | -0.52 – -0.08 | 0.008 |
| int_userarely | -0.28 | -0.46 – -0.11 | 0.002 |
| Zind_mat | -0.04 | -0.11 – 0.03 | 0.220 |
| Zage | 0.11 | -0.00 – 0.22 | 0.057 |
| gender: female | 0.08 | -0.06 – 0.21 | 0.260 |
| Zage:gndrfemale | -0.19 | -0.33 – -0.06 | 0.005 |
| Observations | 824 | ||
| R2 / R2 adjusted | 0.055 / 0.046 | ||
Significant coefficients: If the respondent has a middle level of education, then the indicator of justification sex before the marriage increases by 0.27 If the respondent has never used the Internet, the indicator of justification sex before the marriage decreases by 0.30 If the respondent rarely used the Internet, the indicator of justification sex before the marriage decreases by -0.28
In the model the interaction effect between age (Zage) and gender (gndr) on the dependent variable Zsex_bef_mar. The coefficient of -0.19 suggests that for females, for each one-unit increase in age, the predicted value of Zsex_bef_mar decreases by approximately 0.19 units on average. The p-value of 0.005 suggests that this interaction effect is statistically significant, indicating that the relationship between age and Zsex_bef_mar significantly differs between genders. Specifically, the negative coefficient suggests that as females get older, their attitude towards premarital sex tends to decrease more compared to males.
Insignificant coefficients: The coefficients for the variables educ_lvlhigher, Zind_mat, Zage, and gndrfemale are not statistically significant at the 0.05 level.
The multiple R-squared is 0.055, indicating that approximately 5.5% of the variance in the dependent variable is explained by the predictors used. The adjusted R-squared is 0.046.
The F-statistic is 5.916, and the p-value is less than 0.001 (2.207e-07), indicating that the model1 as a whole is statistically significant.
2.1 Non-linearity 2.2 Residual distribution 2.3 Heteroscedasticity 2.4 Multicollinearity 2.5 Outliers
Linearity assumption: at the Residuals vs.Fitted plot a horizontal line, without distinct patterns can be seen, which is surely a good thing. (Our data is linear)
The Q-Q plot shows deviations of residues from both one and the other sides of a straight line (that is, the points of residues are not evenly spaced on both sides of the line), this may be evidence of an abnormal distribution of residues.
Scale-Location & Residuals vs. Leverage plot show us a red horizontal line with equally spread points. This corresponds with the homoscedasticity of our data.
On Residuals vs Leverage plot I can spot only a couple of outliers
Checking Multicollinearity
## GVIFs computed for predictors
## GVIF Df GVIF^(1/(2*Df)) Interacts With
## educ_lvl 1.694660 2 1.140961 --
## int_use 1.764996 2 1.152619 --
## Zind_mat 1.040038 1 1.019823 --
## Zage 1.925850 3 1.115417 gndr
## gndr 1.925850 3 1.115417 Zage
## Other Predictors
## educ_lvl int_use, Zind_mat, Zage, gndr
## int_use educ_lvl, Zind_mat, Zage, gndr
## Zind_mat educ_lvl, int_use, Zage, gndr
## Zage educ_lvl, int_use, Zind_mat
## gndr educ_lvl, int_use, Zind_mat
Multicollinearity отсутствует
##
## Call:
## lm(formula = Zsex_bef_mar ~ educ_lvl + int_use + Zind_mat + Zage *
## gndr, data = db)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.85663 -0.88954 0.03154 0.76192 1.95172
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.06898 0.10695 0.645 0.51915
## educ_lvlmiddle 0.26994 0.10765 2.508 0.01235 *
## educ_lvlhigher -0.13089 0.11202 -1.168 0.24298
## int_usenever -0.29839 0.11184 -2.668 0.00778 **
## int_userarely -0.28243 0.09028 -3.128 0.00182 **
## Zind_mat -0.04262 0.03473 -1.227 0.22011
## Zage 0.10664 0.05599 1.904 0.05721 .
## gndrfemale 0.07720 0.06847 1.127 0.25991
## Zage:gndrfemale -0.19422 0.06938 -2.799 0.00524 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9769 on 815 degrees of freedom
## Multiple R-squared: 0.05488, Adjusted R-squared: 0.0456
## F-statistic: 5.916 on 8 and 815 DF, p-value: 2.207e-07
Let’s try to improve the model by squaring
db <- db %>%
mutate(Zage_sq = Zage^2,
Zsex_bef_mar_sq = Zsex_bef_mar^2,
Zind_mat_sq = Zind_mat^2)
model2 <- lm(Zsex_bef_mar ~ educ_lvl + int_use + Zind_mat + Zage * gndr + Zage_sq + Zsex_bef_mar_sq + Zind_mat_sq, data = db)
summary(model2)##
## Call:
## lm(formula = Zsex_bef_mar ~ educ_lvl + int_use + Zind_mat + Zage *
## gndr + Zage_sq + Zsex_bef_mar_sq + Zind_mat_sq, data = db)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1276 -0.8996 0.1045 0.7866 1.9599
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.03416 0.12521 -0.273 0.785047
## educ_lvlmiddle 0.29556 0.10673 2.769 0.005745 **
## educ_lvlhigher -0.10829 0.11103 -0.975 0.329684
## int_usenever -0.39983 0.11553 -3.461 0.000567 ***
## int_userarely -0.26113 0.09010 -2.898 0.003854 **
## Zind_mat -0.03198 0.03450 -0.927 0.354228
## Zage 0.10296 0.05561 1.851 0.064471 .
## gndrfemale 0.08259 0.06790 1.216 0.224187
## Zage_sq 0.10918 0.03771 2.895 0.003891 **
## Zsex_bef_mar_sq 0.07415 0.03895 1.904 0.057281 .
## Zind_mat_sq -0.08244 0.02846 -2.897 0.003872 **
## Zage:gndrfemale -0.17842 0.06883 -2.592 0.009704 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9668 on 812 degrees of freedom
## Multiple R-squared: 0.07775, Adjusted R-squared: 0.06525
## F-statistic: 6.223 on 11 and 812 DF, p-value: 6.748e-10
| Zsex_bef_mar | Zsex_bef_mar | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.07 | -0.14 – 0.28 | 0.519 | -0.03 | -0.28 – 0.21 | 0.785 |
|
highest educational level: middle |
0.27 | 0.06 – 0.48 | 0.012 | 0.30 | 0.09 – 0.51 | 0.006 |
|
highest educational level: higher |
-0.13 | -0.35 – 0.09 | 0.243 | -0.11 | -0.33 – 0.11 | 0.330 |
| int_usenever | -0.30 | -0.52 – -0.08 | 0.008 | -0.40 | -0.63 – -0.17 | 0.001 |
| int_userarely | -0.28 | -0.46 – -0.11 | 0.002 | -0.26 | -0.44 – -0.08 | 0.004 |
| Zind_mat | -0.04 | -0.11 – 0.03 | 0.220 | -0.03 | -0.10 – 0.04 | 0.354 |
| Zage | 0.11 | -0.00 – 0.22 | 0.057 | 0.10 | -0.01 – 0.21 | 0.064 |
| gender: female | 0.08 | -0.06 – 0.21 | 0.260 | 0.08 | -0.05 – 0.22 | 0.224 |
| Zage:gndrfemale | -0.19 | -0.33 – -0.06 | 0.005 | -0.18 | -0.31 – -0.04 | 0.010 |
| Zage_sq | 0.11 | 0.04 – 0.18 | 0.004 | |||
| Zsex_bef_mar_sq | 0.07 | -0.00 – 0.15 | 0.057 | |||
| Zind_mat_sq | -0.08 | -0.14 – -0.03 | 0.004 | |||
| Observations | 824 | 824 | ||||
| R2 / R2 adjusted | 0.055 / 0.046 | 0.078 / 0.065 | ||||
The model has improved: The multiple R-squared is 0.078, indicating that approximately 7.8% of the variance in the dependent variable is explained by the predictors used. The adjusted R-squared is 0.065. Significant coefficients: If the respondent has a middle level of education, then the indicator of justification sex before the marriage increases by 0.30 If the respondent has never used the Internet, the indicator of justification sex before the marriage decreases by 0.40 If the respondent rarely used the Internet, the indicator of justification sex before the marriage decreases by -0.26
Also, Age and Index of postmaterialism became statistically significant after squaring.
In the model the interaction effect between age (Zage) and gender (gndr) on the dependent variable Zsex_bef_mar. The coefficient of -0.18 suggests that for females, for each one-unit increase in age, the predicted value of Zsex_bef_mar decreases by approximately 0.18 units on average. The p-value of 0.010 suggests that this interaction effect is statistically significant, indicating that the relationship between age and Zsex_bef_mar significantly differs between genders. Specifically, the negative coefficient suggests that as females get older, their attitude towards premarital sex tends to decrease more compared to males.
The F-statistic is 6.223, and the p-value is 6.748e-10, indicating the overall statistical significance of the model.
db <- db %>%
mutate(log_age = log(age),
log_sex_bef_mar = log(sex_bef_mar))
db$log_ind_mat <- log(db$ind_mat + 0.0001) # Добавляем небольшое смещение, чтобы избежать нулей
model3 <- lm(log_sex_bef_mar ~ educ_lvl + int_use + log_ind_mat + scale(log_age) * gndr, data = db)
summary(model3)##
## Call:
## lm(formula = log_sex_bef_mar ~ educ_lvl + int_use + log_ind_mat +
## scale(log_age) * gndr, data = db)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7840 -0.5690 0.2708 0.6273 1.1361
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.39129 0.08919 15.600 < 2e-16 ***
## educ_lvlmiddle 0.23475 0.08948 2.624 0.00886 **
## educ_lvlhigher -0.08589 0.09265 -0.927 0.35416
## int_usenever -0.15769 0.09057 -1.741 0.08206 .
## int_userarely -0.13925 0.07552 -1.844 0.06557 .
## log_ind_mat 0.01259 0.01059 1.189 0.23484
## scale(log_age) 0.07250 0.04592 1.579 0.11476
## gndrfemale 0.06915 0.05717 1.210 0.22675
## scale(log_age):gndrfemale -0.15162 0.05772 -2.627 0.00878 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8163 on 815 degrees of freedom
## Multiple R-squared: 0.04202, Adjusted R-squared: 0.03262
## F-statistic: 4.469 on 8 and 815 DF, p-value: 2.546e-05
|
justification of sexual relationship before marriage |
|||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 1.39 | 1.22 – 1.57 | <0.001 |
|
highest educational level: middle |
0.23 | 0.06 – 0.41 | 0.009 |
|
highest educational level: higher |
-0.09 | -0.27 – 0.10 | 0.354 |
| int_usenever | -0.16 | -0.34 – 0.02 | 0.082 |
| int_userarely | -0.14 | -0.29 – 0.01 | 0.066 |
| index of postmaterialism | 0.01 | -0.01 – 0.03 | 0.235 |
| scale(log_age) | 0.07 | -0.02 – 0.16 | 0.115 |
| gender: female | 0.07 | -0.04 – 0.18 | 0.227 |
| scale(log_age):gndrfemale | -0.15 | -0.26 – -0.04 | 0.009 |
| Observations | 824 | ||
| R2 / R2 adjusted | 0.042 / 0.033 | ||
The model has deteriorated, so I will not consider it further.
Linearity assumption: The Residuals vs. Fitted plot shows a horizontal line without distinct patterns, indicating that our data exhibits linearity.
The Q-Q plot displays deviations of residuals on both sides of the straight line (i.e., residual points are not evenly distributed on both sides of the line), which may indicate non-normal distribution of residuals.
The Scale-Location and Residuals vs. Leverage plots show a red horizontal line with equally spread points, indicating homoscedasticity of our data.
On the Residuals vs. Leverage plot, I can observe only a couple of outliers.
Checking for Multicollinearity.
## GVIFs computed for predictors
## GVIF Df GVIF^(1/(2*Df)) Interacts With
## educ_lvl 1.705226 2 1.142735 --
## int_use 1.978579 2 1.186010 --
## Zind_mat 1.048154 1 1.023794 --
## Zage 1.952611 3 1.117985 gndr
## gndr 1.952611 3 1.117985 Zage
## Zage_sq 1.220723 1 1.104863 --
## Zsex_bef_mar_sq 1.028098 1 1.013951 --
## Zind_mat_sq 1.010410 1 1.005192 --
## Other Predictors
## educ_lvl int_use, Zind_mat, Zage, gndr, Zage_sq, Zsex_bef_mar_sq, Zind_mat_sq
## int_use educ_lvl, Zind_mat, Zage, gndr, Zage_sq, Zsex_bef_mar_sq, Zind_mat_sq
## Zind_mat educ_lvl, int_use, Zage, gndr, Zage_sq, Zsex_bef_mar_sq, Zind_mat_sq
## Zage educ_lvl, int_use, Zind_mat, Zage_sq, Zsex_bef_mar_sq, Zind_mat_sq
## gndr educ_lvl, int_use, Zind_mat, Zage_sq, Zsex_bef_mar_sq, Zind_mat_sq
## Zage_sq educ_lvl, int_use, Zind_mat, Zage, gndr, Zsex_bef_mar_sq, Zind_mat_sq
## Zsex_bef_mar_sq educ_lvl, int_use, Zind_mat, Zage, gndr, Zage_sq, Zind_mat_sq
## Zind_mat_sq educ_lvl, int_use, Zind_mat, Zage, gndr, Zage_sq, Zsex_bef_mar_sq
Multicollinearity is missing
## Explanation intereaction plot
My explanation of the interaction in the models was confirmed by the graph, indicating that as women age, their attitude towards premarital sex tends to decrease more compared to men. It’s also important to note that the lines intersected, suggesting that the influence of age on the approval of premarital sex is more pronounced among women at a younger age, whereas in men, this effect is more pronounced at an older age.