##常用的指令都先loading
library(lattice)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyr)
library(magrittr)
##
## Attaching package: 'magrittr'
## The following object is masked from 'package:tidyr':
##
## extract
dta<- read.table("C:/tmp/brainsize.txt", h = T)
##看一下讀檔狀況
head(dta)
## Sbj Gender FSIQ VIQ PIQ Weight Height MRICount
## 1 1 Female 133 132 124 118 64.5 816932
## 2 2 Male 140 150 124 NA 72.5 1001121
## 3 3 Male 139 123 150 143 73.3 1038437
## 4 4 Male 133 129 128 172 68.8 965353
## 5 5 Female 137 132 134 147 65.0 951545
## 6 6 Female 99 90 110 146 69.0 928799
##畫散佈圖
stripplot(FSIQ ~ PIQ | Gender,
data=dta,
pch=1,
cex=.5,
alpha=.5,
type=c('g','p'),
jitter.data=TRUE,
xlab="VIQ",
ylab='PIQ',
auto.key=list(space="top",
columns=4),
par.settings=standard.theme(color=FALSE))
##三種智力與男女性別差異p值均大於.05，男女之間智力未達顯著差異
t.test(dta$FSIQ ~ dta$Gender, paired=F, na.action = na.pass)
##
## Welch Two Sample t-test
##
## data: dta$FSIQ by dta$Gender
## t = -0.40267, df = 37.892, p-value = 0.6895
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -18.68639 12.48639
## sample estimates:
## mean in group Female mean in group Male
## 111.9 115.0
t.test(dta$VIQ ~ dta$Gender, paired=F, na.action = na.pass)
##
## Welch Two Sample t-test
##
## data: dta$VIQ by dta$Gender
## t = -0.77262, df = 36.973, p-value = 0.4447
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -21.010922 9.410922
## sample estimates:
## mean in group Female mean in group Male
## 109.45 115.25
t.test(dta$PIQ ~ dta$Gender, paired=F, na.action = na.pass)
##
## Welch Two Sample t-test
##
## data: dta$PIQ by dta$Gender
## t = -0.1598, df = 37.815, p-value = 0.8739
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -15.72079 13.42079
## sample estimates:
## mean in group Female mean in group Male
## 110.45 111.60
##選QQ圖看
qqmath( Weight~ Height | Gender,
aspect="xy",
data=dta,
type=c('p','g'),
prepanel=prepanel.qqmathline,
panel=function(x, ...) {
panel.qqmathline(x, ...)
panel.qqmath(x, ...)
},
par.settings=standard.theme(color=FALSE))
##統計性別和身高體重關係，均有顯著影響力
summary(lm(dta$Weight ~ dta$Gender, data=dta, na.action = na.omit))
##
## Call:
## lm(formula = dta$Weight ~ dta$Gender, data = dta, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -34.444 -15.383 3.678 13.306 37.800
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 137.200 4.132 33.203 < 2e-16 ***
## dta$GenderMale 29.244 6.004 4.871 2.23e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 18.48 on 36 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.3972, Adjusted R-squared: 0.3805
## F-statistic: 23.73 on 1 and 36 DF, p-value: 2.227e-05
summary(lm(dta$Height ~ dta$Gender, data=dta, na.action = na.omit))
##
## Call:
## lm(formula = dta$Height ~ dta$Gender, data = dta, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.132 -2.432 0.235 2.152 5.568
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 65.7650 0.6298 104.42 < 2e-16 ***
## dta$GenderMale 5.6666 0.9023 6.28 2.62e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.816 on 37 degrees of freedom
## (1 observation deleted due to missingness)
## Multiple R-squared: 0.516, Adjusted R-squared: 0.5029
## F-statistic: 39.44 on 1 and 37 DF, p-value: 2.624e-07
##用圖來看性別、大腦大小、智商有沒有顯著影響力
xyplot(FSIQ ~ MRICount | Gender,
data=dta,
type="smooth",
panel=function(x, y, ...) {
panel.xyplot(x, y, ...)
panel.grid(h=-1,
v=-1,
col="gray80",
lty=3, ...)
panel.average(x, y, fun=mean,
horizontal=FALSE,
col='gray', ...)},
par.settings=standard.theme(color=FALSE))
##不同性別大腦大小有顯著影響力，但性別與智力沒有影響力
summary(lm(dta$MRICount ~ dta$Gender, data=dta, na.action = na.omit))
##
## Call:
## lm(formula = dta$MRICount ~ dta$Gender, data = dta, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -74868 -34593 -7290 20014 128650
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 862655 12500 69.011 < 2e-16 ***
## dta$GenderMale 92201 17678 5.216 6.76e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 55900 on 38 degrees of freedom
## Multiple R-squared: 0.4172, Adjusted R-squared: 0.4019
## F-statistic: 27.2 on 1 and 38 DF, p-value: 6.758e-06
summary(lm(dta$FSIQ ~ dta$Gender, data=dta, na.action = na.omit))
##
## Call:
## lm(formula = dta$FSIQ ~ dta$Gender, data = dta, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -35.00 -24.18 3.55 23.32 29.00
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 111.900 5.444 20.556 <2e-16 ***
## dta$GenderMale 3.100 7.699 0.403 0.689
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 24.34 on 38 degrees of freedom
## Multiple R-squared: 0.004249, Adjusted R-squared: -0.02196
## F-statistic: 0.1621 on 1 and 38 DF, p-value: 0.6894