homework1and2

Homework1

打開安裝檔並指定數據及了解內容

pacman::p_load(Ecdat)
data(Caschool,package="Ecdat")
knitr::kable(head(Caschool))

distcod	county	district	grspan	enrltot	teachers	calwpct	mealpct	computer	testscr	compstu	expnstu	str	avginc	elpct	readscr	mathscr
75119	Alameda	Sunol Glen Unified	KK-08	195	10.90	0.5102	2.0408	67	690.80	0.3435898	6384.911	17.88991	22.690001	0.000000	691.6	690.0
61499	Butte	Manzanita Elementary	KK-08	240	11.15	15.4167	47.9167	101	661.20	0.4208333	5099.381	21.52466	9.824000	4.583334	660.5	661.9
61549	Butte	Thermalito Union Elementary	KK-08	1550	82.90	55.0323	76.3226	169	643.60	0.1090323	5501.955	18.69723	8.978000	30.000002	636.3	650.9
61457	Butte	Golden Feather Union Elementary	KK-08	243	14.00	36.4754	77.0492	85	647.70	0.3497942	7101.831	17.35714	8.978000	0.000000	651.9	643.5
61523	Butte	Palermo Union Elementary	KK-08	1335	71.50	33.1086	78.4270	171	640.85	0.1280899	5235.988	18.67133	9.080333	13.857677	641.8	639.9
62042	Fresno	Burrel Union Elementary	KK-08	137	6.40	12.3188	86.9565	25	605.55	0.1824818	5580.147	21.40625	10.415000	12.408759	605.7	605.4

names(Caschool)

##  [1] "distcod"  "county"   "district" "grspan"   "enrltot"  "teachers"
##  [7] "calwpct"  "mealpct"  "computer" "testscr"  "compstu"  "expnstu" 
## [13] "str"      "avginc"   "elpct"    "readscr"  "mathscr"

dta <- Ecdat::Caschool

設定語法並隨機取樣後畫散布圖

library(tidyr)
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

set.seed(99999)
dta %>% dplyr::transmute(mathscr, readscr) %T>%
  plot(., xlab="readscr Status", ylab="mathscr score", pch='.') %>% colMeans

##  mathscr  readscr 
## 653.3426 654.9705

homework2

An exercise of 95%-confidence intervals for score means

dta<-MASS::nlschools
head(dta)

##   lang   IQ class GS SES COMB
## 1   46 15.0   180 29  23    0
## 2   45 14.5   180 29  10    0
## 3   33  9.5   180 29  15    0
## 4   46 11.0   180 29  23    0
## 5   20  8.0   180 29  10    0
## 6   30  9.5   180 29  10    0

dta1<-dta%>%group_by(class)%>%
 dplyr::summarize(n=n(), # using dplyr:: to avoid conflict
                  IQ_mean=mean(IQ),
                  language_mean=mean(lang),
                  language_se=sd(lang)/sqrt(n), 
                  language_lb=language_mean-1.96*language_se,
                  language_ub=language_mean+1.96*language_se) %>% 
  mutate(classID= 1:length(levels(dta$class))) %>%
  select(classID, IQ_mean, language_mean, language_lb, language_ub) 
tail(dta1)

## # A tibble: 6 x 5
##   classID IQ_mean language_mean language_lb language_ub
##     <int>   <dbl>         <dbl>       <dbl>       <dbl>
## 1     128    12.8          45.5        41.1        49.9
## 2     129    12.2          41.5        39.0        44.0
## 3     130    11.9          40.3        35.2        45.3
## 4     131    11.3          38.1        34.7        41.4
## 5     132    10.6          29.3        21.1        37.5
## 6     133    10.6          28.4        23.3        33.6