年齡抓在20至65，刪除自營者，學歷在五專至博士
對照組設定：
女、私立、遊憩運動學群、技術學院、宜花東離島、過量教育(符合工作要求)、客評關聯（無關聯）
#
#
dta <- read.csv("data0419.csv", header = T)
options(digits = 3)
pacman::p_load(tidyverse, ggplot2, MASS)
dta <- dta %>% mutate( Gender = relevel(Gender, ref = "女"),
Sector = relevel(Sector, ref = "私立"),
Field1 = relevel(Field1, ref = "遊憩與運動學群"),
EduLv = factor(EduLv, levels=c("博士","碩士","普通大學","科技大學",
"技術學院","五專","三專",
"二專","高中","高職","國中")),
EduLv = relevel(EduLv, ref = "技術學院"),
Region = factor(Region, levels =c("宜花東離島","北北基","桃竹苗",
"中彰投","雲嘉南","高屏澎")),
Age = as.numeric(Age),
J_year = as.numeric(J_year),
JobZone = as.numeric(JobZone),
EduZone = as.numeric(EduZone),
JobZone_D = as.numeric(EduZone-JobZone),
Salary = as.numeric(Salary),
SubEduOver = relevel(SubEduOver, ref="符合工作要求"),
Core = recode_factor(as.factor(JobCor), "1" = "無關聯",
"2" = "部分關聯",
"3" = "核心關聯"),
SubEduOver = factor(SubEduOver,levels =c("符合工作要求","高於工作要求","低於工作要求")))%>%
filter(Age <= 65 & Age >= 20 & Category != "自營者" )
# data construction
glimpse(dta)## Observations: 1,518
## Variables: 25
## $ SID <fctr> A10, A100, A103, A104, A105, A106, A107, A108, A1...
## $ Gender <fctr> 女, 女, 男, 女, 女, 女, 女, 女, 男, 男, 男, 女, 男, 男, 女, 女, 女...
## $ Sector <fctr> 國立（公立）, 私立, 國立（公立）, 國立（公立）, 國立（公立）, 私立, 私立, 國立（公立...
## $ EduLv <fctr> 碩士, 普通大學, 高職, 普通大學, 普通大學, 普通大學, 普通大學, 普通大學, 碩士, 五...
## $ SubEduOver <fctr> 高於工作要求, 符合工作要求, 符合工作要求, 符合工作要求, 符合工作要求, 符合工作要求, 符...
## $ Require <fctr> 高中/高職, 普通大學, 高中/高職, 普通大學, 普通大學, 普通大學, 普通大學, 普通大學,...
## $ Field1 <fctr> 資訊學群, 外語學群, 工程學群, 文史哲學群, 文史哲學群, 大眾傳播學群, 大眾傳播學群, 藝...
## $ City <fctr> 高雄市, 苗栗縣, 高雄市, 南投縣, 嘉義市, 臺北市, 臺北市, 南投縣, 臺中市, 桃園市,...
## $ Category <fctr> 受雇於公營機關, 受雇於公營機關, 受雇者於私營企業, 受雇於公營機關, 受雇者於私營企業, 受雇...
## $ Staff <fctr> 50-99人, 50-99人, 2-9人, 100-199人, 10-29人, 30-49人, 3...
## $ Hours <int> 40, 70, 57, 51, 64, 50, 50, 47, 60, 45, 40, 56, 42...
## $ J_year <dbl> 8, 4, 21, 1, 6, 0, 1, 1, 7, 3, 23, 1, 2, 1, 1, 14,...
## $ J_total <dbl> 8, 4, 30, 1, 6, 0, 2, 2, 7, 30, 26, 1, 10, 1, 2, 1...
## $ income <fctr> 2-3萬以下, 3-4萬以下, 3-4萬以下, 4-5萬以下, 2萬以下, 3-4萬以下, 3-4...
## $ SubMismatch <int> 2, 3, 5, 4, 5, 4, 3, 3, 4, 4, 4, 5, 5, 3, 2, 4, 1,...
## $ JobSat <int> 4, 3, 5, 6, 7, 5, 3, 6, 5, 4, 7, 3, 4, 4, 4, 5, 5,...
## $ EduZone <dbl> 5, 4, 2, 4, 4, 4, 4, 4, 5, 3, 5, 4, 4, 4, 4, 5, 4,...
## $ Region <fctr> 高屏澎, 桃竹苗, 高屏澎, 中彰投, 雲嘉南, 北北基, 北北基, 中彰投, 中彰投, 桃竹苗,...
## $ Salary <dbl> 25000, 35000, 35000, 45000, 20000, 35000, 35000, 4...
## $ Age <dbl> 34, 30, 62, 25, 21, 24, 25, 26, 35, 54, 54, 23, 34...
## $ JobZone <dbl> 3, 4, 3, 4, 4, 4, 4, 4, 4, 4, 5, 4, 4, 3, 2, 4, 3,...
## $ JobCor <int> 1, 2, 1, 2, 1, 3, 1, 1, 3, 1, 1, 3, 1, 3, 1, 2, 1,...
## $ Core <fctr> 無關聯, 部分關聯, 無關聯, 部分關聯, 無關聯, 核心關聯, 無關聯, 無關聯, 核心關聯, ...
## $ ObjOver <fctr> over, adequate, under, adequate, adequate, adequa...
## $ JobZone_D <dbl> 2, 0, -1, 0, 0, 0, 0, 0, 1, -1, 0, 0, 0, 1, 2, 1, ...# NA
apply(apply(dta, 1, is.na), 1, sum)## SID Gender Sector EduLv SubEduOver Require
## 0 0 0 0 0 0
## Field1 City Category Staff Hours J_year
## 0 0 0 0 0 0
## J_total income SubMismatch JobSat EduZone Region
## 0 0 0 0 0 0
## Salary Age JobZone JobCor Core ObjOver
## 0 0 0 0 0 0
## JobZone_D
## 0# check and pick out
lapply(dta[,c("Sector", "Field1", "City", "Region","EduLv", "SubEduOver", "ObjOver")], levels)## $Sector
## [1] "私立" "國外學校" "國立（公立）"
##
## $Field1
## [1] "遊憩與運動學群" "大眾傳播學群" "工程學群" "文史哲學群"
## [5] "外語學群" "生命科學學群" "生物資源學群" "地球與環境學群"
## [9] "法政學群" "社會與心理學群" "建築與設計學群" "財經學群"
## [13] "教育學群" "資訊學群" "管理學群" "數理化學群"
## [17] "醫藥衛生學群" "藝術學群"
##
## $City
## [1] "宜蘭縣" "花蓮縣" "金門縣" "南投縣" "屏東縣" "苗栗縣" "桃園市"
## [8] "高雄市" "基隆市" "雲林縣" "新北市" "新竹市" "新竹縣" "嘉義市"
## [15] "嘉義縣" "彰化縣" "臺中市" "臺北市" "臺東縣" "臺南市" "澎湖縣"
##
## $Region
## [1] "宜花東離島" "北北基" "桃竹苗" "中彰投" "雲嘉南"
## [6] "高屏澎"
##
## $EduLv
## [1] "技術學院" "博士" "碩士" "普通大學" "科技大學" "五專"
## [7] "三專" "二專" "高中" "高職" "國中"
##
## $SubEduOver
## [1] "符合工作要求" "高於工作要求" "低於工作要求"
##
## $ObjOver
## [1] "adequate" "over" "under"names(dta)## [1] "SID" "Gender" "Sector" "EduLv" "SubEduOver"
## [6] "Require" "Field1" "City" "Category" "Staff"
## [11] "Hours" "J_year" "J_total" "income" "SubMismatch"
## [16] "JobSat" "EduZone" "Region" "Salary" "Age"
## [21] "JobZone" "JobCor" "Core" "ObjOver" "JobZone_D"p <- dplyr::select(dta, -City, -income, -JobSat)
p <- p[p$EduLv %in% c("博士","碩士", "普通大學", "科技大學", "技術學院", "五專"),]#
# Fit the full model
full<- lm(Salary ~Gender+ Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours, data = p)
# Fit the null model
null <- lm(Salary ~1, data= p)#
#以AIC為指標自動選取
# Forward
fm <- step(null, scope=list(lower=null, upper=full), direction="forward")## Start: AIC=29401
## Salary ~ 1
##
## Df Sum of Sq RSS AIC
## + EduLv 5 1.17e+11 7.62e+11 29204
## + EduZone 1 9.24e+10 7.86e+11 29241
## + J_year 1 6.07e+10 8.18e+11 29299
## + Field1 17 7.39e+10 8.04e+11 29307
## + Gender 1 5.42e+10 8.24e+11 29310
## + Staff 8 5.02e+10 8.28e+11 29331
## + Sector 2 3.66e+10 8.42e+11 29343
## + SubMismatch 1 2.59e+10 8.52e+11 29359
## + SubEduOver 2 2.55e+10 8.53e+11 29362
## + Region 5 2.72e+10 8.51e+11 29365
## + Core 2 1.23e+10 8.66e+11 29384
## + Hours 1 1.11e+10 8.67e+11 29384
## <none> 8.78e+11 29401
## + ObjOver 2 1.67e+09 8.77e+11 29402
##
## Step: AIC=29204
## Salary ~ EduLv
##
## Df Sum of Sq RSS AIC
## + J_year 1 4.77e+10 7.14e+11 29111
## + Gender 1 4.31e+10 7.19e+11 29121
## + Field1 17 5.82e+10 7.03e+11 29122
## + SubEduOver 2 2.99e+10 7.32e+11 29149
## + Staff 8 3.00e+10 7.32e+11 29161
## + ObjOver 2 1.28e+10 7.49e+11 29183
## + SubMismatch 1 1.06e+10 7.51e+11 29185
## + Region 5 1.40e+10 7.48e+11 29187
## + Core 2 7.72e+09 7.54e+11 29193
## + Hours 1 6.43e+09 7.55e+11 29193
## + Sector 2 4.28e+09 7.57e+11 29199
## <none> 7.62e+11 29204
##
## Step: AIC=29111
## Salary ~ EduLv + J_year
##
## Df Sum of Sq RSS AIC
## + Field1 17 6.10e+10 6.53e+11 29015
## + Gender 1 4.16e+10 6.72e+11 29026
## + SubEduOver 2 2.34e+10 6.91e+11 29067
## + Staff 8 2.73e+10 6.87e+11 29071
## + Region 5 1.80e+10 6.96e+11 29084
## + ObjOver 2 1.09e+10 7.03e+11 29093
## + SubMismatch 1 9.75e+09 7.04e+11 29093
## + Core 2 1.00e+10 7.04e+11 29095
## + Hours 1 8.60e+09 7.05e+11 29096
## + Sector 2 3.68e+09 7.10e+11 29108
## <none> 7.14e+11 29111
##
## Step: AIC=29015
## Salary ~ EduLv + J_year + Field1
##
## Df Sum of Sq RSS AIC
## + SubEduOver 2 2.44e+10 6.29e+11 28964
## + Gender 1 1.53e+10 6.38e+11 28983
## + ObjOver 2 1.51e+10 6.38e+11 28985
## + Region 5 1.37e+10 6.39e+11 28995
## + Staff 8 1.63e+10 6.37e+11 28995
## + SubMismatch 1 8.62e+09 6.44e+11 28998
## + Core 2 9.21e+09 6.44e+11 28999
## + Hours 1 4.86e+09 6.48e+11 29007
## + Sector 2 4.64e+09 6.48e+11 29009
## <none> 6.53e+11 29015
##
## Step: AIC=28964
## Salary ~ EduLv + J_year + Field1 + SubEduOver
##
## Df Sum of Sq RSS AIC
## + Gender 1 1.75e+10 6.11e+11 28925
## + ObjOver 2 1.11e+10 6.17e+11 28942
## + Region 5 1.24e+10 6.16e+11 28945
## + Staff 8 1.45e+10 6.14e+11 28946
## + Hours 1 6.02e+09 6.22e+11 28952
## + Sector 2 5.51e+09 6.23e+11 28955
## + Core 2 5.51e+09 6.23e+11 28955
## + SubMismatch 1 1.90e+09 6.27e+11 28962
## <none> 6.29e+11 28964
##
## Step: AIC=28925
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender
##
## Df Sum of Sq RSS AIC
## + Region 5 1.27e+10 5.98e+11 28905
## + ObjOver 2 9.80e+09 6.01e+11 28906
## + Staff 8 1.22e+10 5.99e+11 28912
## + Hours 1 5.98e+09 6.05e+11 28913
## + Core 2 5.74e+09 6.05e+11 28915
## + Sector 2 4.85e+09 6.06e+11 28918
## + SubMismatch 1 2.72e+09 6.08e+11 28921
## <none> 6.11e+11 28925
##
## Step: AIC=28905
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region
##
## Df Sum of Sq RSS AIC
## + ObjOver 2 1.06e+10 5.88e+11 28883
## + Hours 1 5.51e+09 5.93e+11 28893
## + Core 2 5.77e+09 5.93e+11 28894
## + Staff 8 9.70e+09 5.89e+11 28897
## + Sector 2 4.16e+09 5.94e+11 28898
## + SubMismatch 1 2.60e+09 5.96e+11 28900
## <none> 5.98e+11 28905
##
## Step: AIC=28883
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver
##
## Df Sum of Sq RSS AIC
## + Hours 1 5.12e+09 5.83e+11 28872
## + Staff 8 9.91e+09 5.78e+11 28874
## + Sector 2 3.68e+09 5.84e+11 28877
## + Core 2 2.96e+09 5.85e+11 28879
## + SubMismatch 1 1.14e+09 5.87e+11 28882
## <none> 5.88e+11 28883
##
## Step: AIC=28872
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours
##
## Df Sum of Sq RSS AIC
## + Staff 8 1.00e+10 5.73e+11 28863
## + Sector 2 3.55e+09 5.79e+11 28867
## + Core 2 2.90e+09 5.80e+11 28869
## + SubMismatch 1 1.20e+09 5.81e+11 28871
## <none> 5.83e+11 28872
##
## Step: AIC=28863
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff
##
## Df Sum of Sq RSS AIC
## + Sector 2 3.40e+09 5.69e+11 28858
## + Core 2 2.52e+09 5.70e+11 28860
## + SubMismatch 1 1.15e+09 5.71e+11 28862
## <none> 5.73e+11 28863
##
## Step: AIC=28858
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff + Sector
##
## Df Sum of Sq RSS AIC
## + Core 2 2.61e+09 5.67e+11 28855
## + SubMismatch 1 1.21e+09 5.68e+11 28857
## <none> 5.69e+11 28858
##
## Step: AIC=28855
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff + Sector + Core
##
## Df Sum of Sq RSS AIC
## <none> 5.67e+11 28855
## + SubMismatch 1 5.52e+08 5.66e+11 28856summary(fm)##
## Call:
## lm(formula = Salary ~ EduLv + J_year + Field1 + SubEduOver +
## Gender + Region + ObjOver + Hours + Staff + Sector + Core,
## data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -45438 -10553 -2060 6092 235151
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 12250.2 13234.6 0.93 0.35480
## EduLv博士 12794.5 7645.8 1.67 0.09447 .
## EduLv碩士 18045.9 3517.4 5.13 3.3e-07 ***
## EduLv普通大學 4026.7 3402.0 1.18 0.23677
## EduLv科技大學 -2440.7 3487.9 -0.70 0.48419
## EduLv五專 1902.0 5114.5 0.37 0.71004
## J_year 1158.2 112.3 10.32 < 2e-16 ***
## Field1大眾傳播學群 -3055.3 4825.1 -0.63 0.52670
## Field1工程學群 9511.1 3948.7 2.41 0.01614 *
## Field1文史哲學群 -4791.0 4333.8 -1.11 0.26914
## Field1外語學群 1889.2 4319.9 0.44 0.66194
## Field1生命科學學群 1424.5 5040.5 0.28 0.77752
## Field1生物資源學群 -1368.0 5588.2 -0.24 0.80665
## Field1地球與環境學群 -4047.8 5607.4 -0.72 0.47050
## Field1法政學群 1281.0 4523.8 0.28 0.77709
## Field1社會與心理學群 -4373.4 4128.5 -1.06 0.28963
## Field1建築與設計學群 3920.7 4651.7 0.84 0.39945
## Field1財經學群 1802.4 4138.5 0.44 0.66325
## Field1教育學群 -2696.9 4241.8 -0.64 0.52502
## Field1資訊學群 3484.2 4142.8 0.84 0.40047
## Field1管理學群 -2136.0 4031.2 -0.53 0.59629
## Field1數理化學群 407.2 4540.5 0.09 0.92855
## Field1醫藥衛生學群 8033.9 4228.0 1.90 0.05762 .
## Field1藝術學群 -5437.0 5080.0 -1.07 0.28468
## SubEduOver高於工作要求 -8559.3 1381.1 -6.20 7.5e-10 ***
## SubEduOver低於工作要求 -7597.6 1834.9 -4.14 3.7e-05 ***
## Gender男 7470.0 1266.7 5.90 4.6e-09 ***
## Region北北基 2501.5 3015.1 0.83 0.40686
## Region桃竹苗 6603.0 3222.4 2.05 0.04064 *
## Region中彰投 1165.1 3177.8 0.37 0.71394
## Region雲嘉南 -2108.0 3138.2 -0.67 0.50188
## Region高屏澎 -1071.5 3132.9 -0.34 0.73238
## ObjOverover -4222.3 1351.6 -3.12 0.00182 **
## ObjOverunder 5519.0 2773.7 1.99 0.04681 *
## Hours 200.6 57.1 3.51 0.00046 ***
## Staff10-29人 7349.9 11790.1 0.62 0.53312
## Staff100-199人 9576.9 11756.1 0.81 0.41542
## Staff1人 -4042.2 13768.7 -0.29 0.76912
## Staff2-9人 3032.0 11857.1 0.26 0.79821
## Staff200-499 6511.6 11779.7 0.55 0.58050
## Staff30-49人 8535.2 11851.6 0.72 0.47154
## Staff50-99人 8748.5 11782.4 0.74 0.45790
## Staff500人以上 11397.9 11717.3 0.97 0.33085
## Sector國外學校 11295.0 4315.3 2.62 0.00895 **
## Sector國立（公立） 2481.4 1299.7 1.91 0.05644 .
## Core部分關聯 3648.9 1677.2 2.18 0.02975 *
## Core核心關聯 2505.0 1384.3 1.81 0.07058 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20100 on 1407 degrees of freedom
## Multiple R-squared: 0.355, Adjusted R-squared: 0.334
## F-statistic: 16.8 on 46 and 1407 DF, p-value: <2e-16formula(fm)## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff + Sector + Core# Backward
bm <- step(full, p, direction="backward")## Start: AIC=28856
## Salary ~ Gender + Sector + Field1 + Region + EduLv + SubEduOver +
## SubMismatch + ObjOver + Core + J_year + Staff + EduZone +
## Hours
##
##
## Step: AIC=28856
## Salary ~ Gender + Sector + Field1 + Region + EduLv + SubEduOver +
## SubMismatch + ObjOver + Core + J_year + Staff + Hours
##
## Df Sum of Sq RSS AIC
## - SubMismatch 1 5.52e+08 5.67e+11 28855
## <none> 5.66e+11 28856
## - Core 2 1.95e+09 5.68e+11 28857
## - Sector 2 3.52e+09 5.70e+11 28861
## - Staff 8 9.46e+09 5.76e+11 28864
## - Hours 1 5.02e+09 5.71e+11 28867
## - ObjOver 2 6.73e+09 5.73e+11 28869
## - Region 5 9.91e+09 5.76e+11 28871
## - Field1 17 2.51e+10 5.91e+11 28885
## - Gender 1 1.43e+10 5.80e+11 28890
## - SubEduOver 2 1.60e+10 5.82e+11 28892
## - J_year 1 4.28e+10 6.09e+11 28960
## - EduLv 5 5.25e+10 6.18e+11 28975
##
## Step: AIC=28855
## Salary ~ Gender + Sector + Field1 + Region + EduLv + SubEduOver +
## ObjOver + Core + J_year + Staff + Hours
##
## Df Sum of Sq RSS AIC
## <none> 5.67e+11 28855
## - Core 2 2.61e+09 5.69e+11 28858
## - Sector 2 3.49e+09 5.70e+11 28860
## - Staff 8 9.45e+09 5.76e+11 28863
## - Hours 1 4.97e+09 5.72e+11 28866
## - ObjOver 2 7.23e+09 5.74e+11 28870
## - Region 5 1.00e+10 5.77e+11 28871
## - Field1 17 2.56e+10 5.92e+11 28886
## - Gender 1 1.40e+10 5.81e+11 28889
## - SubEduOver 2 1.93e+10 5.86e+11 28900
## - J_year 1 4.29e+10 6.09e+11 28959
## - EduLv 5 5.61e+10 6.23e+11 28983summary(bm)##
## Call:
## lm(formula = Salary ~ Gender + Sector + Field1 + Region + EduLv +
## SubEduOver + ObjOver + Core + J_year + Staff + Hours, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -45438 -10553 -2060 6092 235151
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 12250.2 13234.6 0.93 0.35480
## Gender男 7470.0 1266.7 5.90 4.6e-09 ***
## Sector國外學校 11295.0 4315.3 2.62 0.00895 **
## Sector國立（公立） 2481.4 1299.7 1.91 0.05644 .
## Field1大眾傳播學群 -3055.3 4825.1 -0.63 0.52670
## Field1工程學群 9511.1 3948.7 2.41 0.01614 *
## Field1文史哲學群 -4791.0 4333.8 -1.11 0.26914
## Field1外語學群 1889.2 4319.9 0.44 0.66194
## Field1生命科學學群 1424.5 5040.5 0.28 0.77752
## Field1生物資源學群 -1368.0 5588.2 -0.24 0.80665
## Field1地球與環境學群 -4047.8 5607.4 -0.72 0.47050
## Field1法政學群 1281.0 4523.8 0.28 0.77709
## Field1社會與心理學群 -4373.4 4128.5 -1.06 0.28963
## Field1建築與設計學群 3920.7 4651.7 0.84 0.39945
## Field1財經學群 1802.4 4138.5 0.44 0.66325
## Field1教育學群 -2696.9 4241.8 -0.64 0.52502
## Field1資訊學群 3484.2 4142.8 0.84 0.40047
## Field1管理學群 -2136.0 4031.2 -0.53 0.59629
## Field1數理化學群 407.2 4540.5 0.09 0.92855
## Field1醫藥衛生學群 8033.9 4228.0 1.90 0.05762 .
## Field1藝術學群 -5437.0 5080.0 -1.07 0.28468
## Region北北基 2501.5 3015.1 0.83 0.40686
## Region桃竹苗 6603.0 3222.4 2.05 0.04064 *
## Region中彰投 1165.1 3177.8 0.37 0.71394
## Region雲嘉南 -2108.0 3138.2 -0.67 0.50188
## Region高屏澎 -1071.5 3132.9 -0.34 0.73238
## EduLv博士 12794.5 7645.8 1.67 0.09447 .
## EduLv碩士 18045.9 3517.4 5.13 3.3e-07 ***
## EduLv普通大學 4026.7 3402.0 1.18 0.23677
## EduLv科技大學 -2440.7 3487.9 -0.70 0.48419
## EduLv五專 1902.0 5114.5 0.37 0.71004
## SubEduOver高於工作要求 -8559.3 1381.1 -6.20 7.5e-10 ***
## SubEduOver低於工作要求 -7597.6 1834.9 -4.14 3.7e-05 ***
## ObjOverover -4222.3 1351.6 -3.12 0.00182 **
## ObjOverunder 5519.0 2773.7 1.99 0.04681 *
## Core部分關聯 3648.9 1677.2 2.18 0.02975 *
## Core核心關聯 2505.0 1384.3 1.81 0.07058 .
## J_year 1158.2 112.3 10.32 < 2e-16 ***
## Staff10-29人 7349.9 11790.1 0.62 0.53312
## Staff100-199人 9576.9 11756.1 0.81 0.41542
## Staff1人 -4042.2 13768.7 -0.29 0.76912
## Staff2-9人 3032.0 11857.1 0.26 0.79821
## Staff200-499 6511.6 11779.7 0.55 0.58050
## Staff30-49人 8535.2 11851.6 0.72 0.47154
## Staff50-99人 8748.5 11782.4 0.74 0.45790
## Staff500人以上 11397.9 11717.3 0.97 0.33085
## Hours 200.6 57.1 3.51 0.00046 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20100 on 1407 degrees of freedom
## Multiple R-squared: 0.355, Adjusted R-squared: 0.334
## F-statistic: 16.8 on 46 and 1407 DF, p-value: <2e-16formula(bm)## Salary ~ Gender + Sector + Field1 + Region + EduLv + SubEduOver +
## ObjOver + Core + J_year + Staff + Hours# Auto
bbm <- step(null, scope = list(upper=full), data=p, direction="both")## Start: AIC=29401
## Salary ~ 1
##
## Df Sum of Sq RSS AIC
## + EduLv 5 1.17e+11 7.62e+11 29204
## + EduZone 1 9.24e+10 7.86e+11 29241
## + J_year 1 6.07e+10 8.18e+11 29299
## + Field1 17 7.39e+10 8.04e+11 29307
## + Gender 1 5.42e+10 8.24e+11 29310
## + Staff 8 5.02e+10 8.28e+11 29331
## + Sector 2 3.66e+10 8.42e+11 29343
## + SubMismatch 1 2.59e+10 8.52e+11 29359
## + SubEduOver 2 2.55e+10 8.53e+11 29362
## + Region 5 2.72e+10 8.51e+11 29365
## + Core 2 1.23e+10 8.66e+11 29384
## + Hours 1 1.11e+10 8.67e+11 29384
## <none> 8.78e+11 29401
## + ObjOver 2 1.67e+09 8.77e+11 29402
##
## Step: AIC=29204
## Salary ~ EduLv
##
## Df Sum of Sq RSS AIC
## + J_year 1 4.77e+10 7.14e+11 29111
## + Gender 1 4.31e+10 7.19e+11 29121
## + Field1 17 5.82e+10 7.03e+11 29122
## + SubEduOver 2 2.99e+10 7.32e+11 29149
## + Staff 8 3.00e+10 7.32e+11 29161
## + ObjOver 2 1.28e+10 7.49e+11 29183
## + SubMismatch 1 1.06e+10 7.51e+11 29185
## + Region 5 1.40e+10 7.48e+11 29187
## + Core 2 7.72e+09 7.54e+11 29193
## + Hours 1 6.43e+09 7.55e+11 29193
## + Sector 2 4.28e+09 7.57e+11 29199
## <none> 7.62e+11 29204
## - EduLv 5 1.17e+11 8.78e+11 29401
##
## Step: AIC=29111
## Salary ~ EduLv + J_year
##
## Df Sum of Sq RSS AIC
## + Field1 17 6.10e+10 6.53e+11 29015
## + Gender 1 4.16e+10 6.72e+11 29026
## + SubEduOver 2 2.34e+10 6.91e+11 29067
## + Staff 8 2.73e+10 6.87e+11 29071
## + Region 5 1.80e+10 6.96e+11 29084
## + ObjOver 2 1.09e+10 7.03e+11 29093
## + SubMismatch 1 9.75e+09 7.04e+11 29093
## + Core 2 1.00e+10 7.04e+11 29095
## + Hours 1 8.60e+09 7.05e+11 29096
## + Sector 2 3.68e+09 7.10e+11 29108
## <none> 7.14e+11 29111
## - J_year 1 4.77e+10 7.62e+11 29204
## - EduLv 5 1.04e+11 8.18e+11 29299
##
## Step: AIC=29015
## Salary ~ EduLv + J_year + Field1
##
## Df Sum of Sq RSS AIC
## + SubEduOver 2 2.44e+10 6.29e+11 28964
## + Gender 1 1.53e+10 6.38e+11 28983
## + ObjOver 2 1.51e+10 6.38e+11 28985
## + Region 5 1.37e+10 6.39e+11 28995
## + Staff 8 1.63e+10 6.37e+11 28995
## + SubMismatch 1 8.62e+09 6.44e+11 28998
## + Core 2 9.21e+09 6.44e+11 28999
## + Hours 1 4.86e+09 6.48e+11 29007
## + Sector 2 4.64e+09 6.48e+11 29009
## <none> 6.53e+11 29015
## - Field1 17 6.10e+10 7.14e+11 29111
## - J_year 1 5.06e+10 7.03e+11 29122
## - EduLv 5 9.27e+10 7.46e+11 29198
##
## Step: AIC=28964
## Salary ~ EduLv + J_year + Field1 + SubEduOver
##
## Df Sum of Sq RSS AIC
## + Gender 1 1.75e+10 6.11e+11 28925
## + ObjOver 2 1.11e+10 6.17e+11 28942
## + Region 5 1.24e+10 6.16e+11 28945
## + Staff 8 1.45e+10 6.14e+11 28946
## + Hours 1 6.02e+09 6.22e+11 28952
## + Sector 2 5.51e+09 6.23e+11 28955
## + Core 2 5.51e+09 6.23e+11 28955
## + SubMismatch 1 1.90e+09 6.27e+11 28962
## <none> 6.29e+11 28964
## - SubEduOver 2 2.44e+10 6.53e+11 29015
## - J_year 1 4.38e+10 6.72e+11 29060
## - Field1 17 6.20e+10 6.91e+11 29067
## - EduLv 5 9.29e+10 7.21e+11 29155
##
## Step: AIC=28925
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender
##
## Df Sum of Sq RSS AIC
## + Region 5 1.27e+10 5.98e+11 28905
## + ObjOver 2 9.80e+09 6.01e+11 28906
## + Staff 8 1.22e+10 5.99e+11 28912
## + Hours 1 5.98e+09 6.05e+11 28913
## + Core 2 5.74e+09 6.05e+11 28915
## + Sector 2 4.85e+09 6.06e+11 28918
## + SubMismatch 1 2.72e+09 6.08e+11 28921
## <none> 6.11e+11 28925
## - Gender 1 1.75e+10 6.29e+11 28964
## - Field1 17 3.35e+10 6.45e+11 28969
## - SubEduOver 2 2.66e+10 6.38e+11 28983
## - J_year 1 4.07e+10 6.52e+11 29017
## - EduLv 5 9.17e+10 7.03e+11 29118
##
## Step: AIC=28905
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region
##
## Df Sum of Sq RSS AIC
## + ObjOver 2 1.06e+10 5.88e+11 28883
## + Hours 1 5.51e+09 5.93e+11 28893
## + Core 2 5.77e+09 5.93e+11 28894
## + Staff 8 9.70e+09 5.89e+11 28897
## + Sector 2 4.16e+09 5.94e+11 28898
## + SubMismatch 1 2.60e+09 5.96e+11 28900
## <none> 5.98e+11 28905
## - Region 5 1.27e+10 6.11e+11 28925
## - Gender 1 1.78e+10 6.16e+11 28945
## - Field1 17 3.19e+10 6.30e+11 28946
## - SubEduOver 2 2.51e+10 6.23e+11 28960
## - J_year 1 4.41e+10 6.42e+11 29006
## - EduLv 5 8.25e+10 6.81e+11 29082
##
## Step: AIC=28883
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver
##
## Df Sum of Sq RSS AIC
## + Hours 1 5.12e+09 5.83e+11 28872
## + Staff 8 9.91e+09 5.78e+11 28874
## + Sector 2 3.68e+09 5.84e+11 28877
## + Core 2 2.96e+09 5.85e+11 28879
## + SubMismatch 1 1.14e+09 5.87e+11 28882
## <none> 5.88e+11 28883
## - ObjOver 2 1.06e+10 5.98e+11 28905
## - Region 5 1.35e+10 6.01e+11 28906
## - Gender 1 1.64e+10 6.04e+11 28921
## - SubEduOver 2 2.10e+10 6.09e+11 28930
## - Field1 17 3.43e+10 6.22e+11 28931
## - J_year 1 4.33e+10 6.31e+11 28984
## - EduLv 5 9.18e+10 6.80e+11 29084
##
## Step: AIC=28872
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours
##
## Df Sum of Sq RSS AIC
## + Staff 8 1.00e+10 5.73e+11 28863
## + Sector 2 3.55e+09 5.79e+11 28867
## + Core 2 2.90e+09 5.80e+11 28869
## + SubMismatch 1 1.20e+09 5.81e+11 28871
## <none> 5.83e+11 28872
## - Hours 1 5.12e+09 5.88e+11 28883
## - ObjOver 2 1.02e+10 5.93e+11 28893
## - Region 5 1.30e+10 5.96e+11 28894
## - Gender 1 1.64e+10 5.99e+11 28910
## - Field1 17 3.13e+10 6.14e+11 28914
## - SubEduOver 2 2.21e+10 6.05e+11 28922
## - J_year 1 4.45e+10 6.27e+11 28977
## - EduLv 5 8.84e+10 6.71e+11 29067
##
## Step: AIC=28863
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff
##
## Df Sum of Sq RSS AIC
## + Sector 2 3.40e+09 5.69e+11 28858
## + Core 2 2.52e+09 5.70e+11 28860
## + SubMismatch 1 1.15e+09 5.71e+11 28862
## <none> 5.73e+11 28863
## - Staff 8 1.00e+10 5.83e+11 28872
## - Hours 1 5.22e+09 5.78e+11 28874
## - Region 5 1.06e+10 5.83e+11 28879
## - ObjOver 2 1.05e+10 5.83e+11 28885
## - Field1 17 2.62e+10 5.99e+11 28894
## - Gender 1 1.43e+10 5.87e+11 28897
## - SubEduOver 2 2.06e+10 5.93e+11 28910
## - J_year 1 4.25e+10 6.15e+11 28965
## - EduLv 5 8.04e+10 6.53e+11 29044
##
## Step: AIC=28858
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff + Sector
##
## Df Sum of Sq RSS AIC
## + Core 2 2.61e+09 5.67e+11 28855
## + SubMismatch 1 1.21e+09 5.68e+11 28857
## <none> 5.69e+11 28858
## - Sector 2 3.40e+09 5.73e+11 28863
## - Staff 8 9.86e+09 5.79e+11 28867
## - Hours 1 5.05e+09 5.74e+11 28869
## - Region 5 1.00e+10 5.79e+11 28873
## - ObjOver 2 9.98e+09 5.79e+11 28879
## - Field1 17 2.62e+10 5.95e+11 28890
## - Gender 1 1.38e+10 5.83e+11 28891
## - SubEduOver 2 2.15e+10 5.91e+11 28908
## - J_year 1 4.15e+10 6.11e+11 28958
## - EduLv 5 6.10e+10 6.30e+11 28996
##
## Step: AIC=28855
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff + Sector + Core
##
## Df Sum of Sq RSS AIC
## <none> 5.67e+11 28855
## + SubMismatch 1 5.52e+08 5.66e+11 28856
## - Core 2 2.61e+09 5.69e+11 28858
## - Sector 2 3.49e+09 5.70e+11 28860
## - Staff 8 9.45e+09 5.76e+11 28863
## - Hours 1 4.97e+09 5.72e+11 28866
## - ObjOver 2 7.23e+09 5.74e+11 28870
## - Region 5 1.00e+10 5.77e+11 28871
## - Field1 17 2.56e+10 5.92e+11 28886
## - Gender 1 1.40e+10 5.81e+11 28889
## - SubEduOver 2 1.93e+10 5.86e+11 28900
## - J_year 1 4.29e+10 6.09e+11 28959
## - EduLv 5 5.61e+10 6.23e+11 28983summary(bbm)##
## Call:
## lm(formula = Salary ~ EduLv + J_year + Field1 + SubEduOver +
## Gender + Region + ObjOver + Hours + Staff + Sector + Core,
## data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -45438 -10553 -2060 6092 235151
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 12250.2 13234.6 0.93 0.35480
## EduLv博士 12794.5 7645.8 1.67 0.09447 .
## EduLv碩士 18045.9 3517.4 5.13 3.3e-07 ***
## EduLv普通大學 4026.7 3402.0 1.18 0.23677
## EduLv科技大學 -2440.7 3487.9 -0.70 0.48419
## EduLv五專 1902.0 5114.5 0.37 0.71004
## J_year 1158.2 112.3 10.32 < 2e-16 ***
## Field1大眾傳播學群 -3055.3 4825.1 -0.63 0.52670
## Field1工程學群 9511.1 3948.7 2.41 0.01614 *
## Field1文史哲學群 -4791.0 4333.8 -1.11 0.26914
## Field1外語學群 1889.2 4319.9 0.44 0.66194
## Field1生命科學學群 1424.5 5040.5 0.28 0.77752
## Field1生物資源學群 -1368.0 5588.2 -0.24 0.80665
## Field1地球與環境學群 -4047.8 5607.4 -0.72 0.47050
## Field1法政學群 1281.0 4523.8 0.28 0.77709
## Field1社會與心理學群 -4373.4 4128.5 -1.06 0.28963
## Field1建築與設計學群 3920.7 4651.7 0.84 0.39945
## Field1財經學群 1802.4 4138.5 0.44 0.66325
## Field1教育學群 -2696.9 4241.8 -0.64 0.52502
## Field1資訊學群 3484.2 4142.8 0.84 0.40047
## Field1管理學群 -2136.0 4031.2 -0.53 0.59629
## Field1數理化學群 407.2 4540.5 0.09 0.92855
## Field1醫藥衛生學群 8033.9 4228.0 1.90 0.05762 .
## Field1藝術學群 -5437.0 5080.0 -1.07 0.28468
## SubEduOver高於工作要求 -8559.3 1381.1 -6.20 7.5e-10 ***
## SubEduOver低於工作要求 -7597.6 1834.9 -4.14 3.7e-05 ***
## Gender男 7470.0 1266.7 5.90 4.6e-09 ***
## Region北北基 2501.5 3015.1 0.83 0.40686
## Region桃竹苗 6603.0 3222.4 2.05 0.04064 *
## Region中彰投 1165.1 3177.8 0.37 0.71394
## Region雲嘉南 -2108.0 3138.2 -0.67 0.50188
## Region高屏澎 -1071.5 3132.9 -0.34 0.73238
## ObjOverover -4222.3 1351.6 -3.12 0.00182 **
## ObjOverunder 5519.0 2773.7 1.99 0.04681 *
## Hours 200.6 57.1 3.51 0.00046 ***
## Staff10-29人 7349.9 11790.1 0.62 0.53312
## Staff100-199人 9576.9 11756.1 0.81 0.41542
## Staff1人 -4042.2 13768.7 -0.29 0.76912
## Staff2-9人 3032.0 11857.1 0.26 0.79821
## Staff200-499 6511.6 11779.7 0.55 0.58050
## Staff30-49人 8535.2 11851.6 0.72 0.47154
## Staff50-99人 8748.5 11782.4 0.74 0.45790
## Staff500人以上 11397.9 11717.3 0.97 0.33085
## Sector國外學校 11295.0 4315.3 2.62 0.00895 **
## Sector國立（公立） 2481.4 1299.7 1.91 0.05644 .
## Core部分關聯 3648.9 1677.2 2.18 0.02975 *
## Core核心關聯 2505.0 1384.3 1.81 0.07058 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20100 on 1407 degrees of freedom
## Multiple R-squared: 0.355, Adjusted R-squared: 0.334
## F-statistic: 16.8 on 46 and 1407 DF, p-value: <2e-16formula(bbm)## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff + Sector + Core# 三個模型 向前選取>向後選取>電腦選取
lapply(c("fm","bm","bbm"),formula)## [[1]]
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff + Sector + Core
## <environment: 0x000000002394e908>
##
## [[2]]
## Salary ~ Gender + Sector + Field1 + Region + EduLv + SubEduOver +
## ObjOver + Core + J_year + Staff + Hours
## <environment: 0x000000002394e908>
##
## [[3]]
## Salary ~ EduLv + J_year + Field1 + SubEduOver + Gender + Region +
## ObjOver + Hours + Staff + Sector + Core
## <environment: 0x000000002394e908>#
#Manual F-test-base forward selection
#
add1(null,scope = ~ Gender+ Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours,test = "F" )## Single term additions
##
## Model:
## Salary ~ 1
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 8.78e+11 29401
## Gender 1 5.42e+10 8.24e+11 29310 95.50 < 2e-16 ***
## Sector 2 3.66e+10 8.42e+11 29343 31.52 4.0e-14 ***
## Field1 17 7.39e+10 8.04e+11 29307 7.76 < 2e-16 ***
## Region 5 2.72e+10 8.51e+11 29365 9.24 1.1e-08 ***
## EduLv 5 1.17e+11 7.62e+11 29204 44.34 < 2e-16 ***
## SubEduOver 2 2.55e+10 8.53e+11 29362 21.70 5.2e-10 ***
## SubMismatch 1 2.59e+10 8.52e+11 29359 44.05 4.5e-11 ***
## ObjOver 2 1.67e+09 8.77e+11 29402 1.39 0.25
## Core 2 1.23e+10 8.66e+11 29384 10.33 3.5e-05 ***
## J_year 1 6.07e+10 8.18e+11 29299 107.76 < 2e-16 ***
## Staff 8 5.02e+10 8.28e+11 29331 10.95 4.4e-15 ***
## EduZone 1 9.24e+10 7.86e+11 29241 170.63 < 2e-16 ***
## Hours 1 1.11e+10 8.67e+11 29384 18.55 1.8e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1add1(update(null,~.+Gender),
scope = ~ Gender+Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours,test = "F" )## Single term additions
##
## Model:
## Salary ~ Gender
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 8.24e+11 29310
## Sector 2 3.15e+10 7.93e+11 29257 28.77 5.6e-13 ***
## Field1 17 3.87e+10 7.85e+11 29274 4.16 2.7e-08 ***
## Region 5 2.37e+10 8.00e+11 29278 8.57 5.2e-08 ***
## EduLv 5 1.06e+11 7.19e+11 29121 42.49 < 2e-16 ***
## SubEduOver 2 3.24e+10 7.92e+11 29256 29.66 2.4e-13 ***
## SubMismatch 1 3.10e+10 7.93e+11 29256 56.62 9.2e-14 ***
## ObjOver 2 1.28e+09 8.23e+11 29312 1.13 0.32
## Core 2 1.42e+10 8.10e+11 29289 12.67 3.5e-06 ***
## J_year 1 5.76e+10 7.67e+11 29207 109.03 < 2e-16 ***
## Staff 8 3.69e+10 7.87e+11 29259 8.46 2.7e-11 ***
## EduZone 1 7.99e+10 7.44e+11 29164 155.89 < 2e-16 ***
## Hours 1 9.64e+09 8.14e+11 29295 17.18 3.6e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1add1(update(null,~.+Gender+Sector+ EduLv+ Field1),
scope = ~ Gender+Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours,test = "F" )## Single term additions
##
## Model:
## Salary ~ Gender + Sector + EduLv + Field1
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 6.81e+11 29080
## Region 5 9.60e+09 6.71e+11 29069 4.07 0.00112 **
## SubEduOver 2 3.48e+10 6.46e+11 29007 38.44 < 2e-16 ***
## SubMismatch 1 1.15e+10 6.69e+11 29057 24.63 7.8e-07 ***
## ObjOver 2 1.52e+10 6.65e+11 29051 16.28 1.0e-07 ***
## Core 2 7.34e+09 6.73e+11 29068 7.77 0.00044 ***
## J_year 1 4.70e+10 6.34e+11 28978 105.95 < 2e-16 ***
## Staff 8 1.59e+10 6.65e+11 29061 4.25 4.7e-05 ***
## EduZone 0 0.00e+00 6.81e+11 29080
## Hours 1 3.16e+09 6.77e+11 29075 6.66 0.00998 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1add1(update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours),
scope = ~ Gender+Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours,test = "F" )## Single term additions
##
## Model:
## Salary ~ Gender + Sector + EduLv + Field1 + Region + Staff +
## J_year + Hours
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 6.05e+11 28938
## SubEduOver 2 2.54e+10 5.79e+11 28879 31.0 6.7e-14 ***
## SubMismatch 1 1.01e+10 5.95e+11 28915 24.0 1.1e-06 ***
## ObjOver 2 1.40e+10 5.91e+11 28908 16.7 7.0e-08 ***
## Core 2 9.35e+09 5.95e+11 28919 11.1 1.7e-05 ***
## EduZone 0 0.00e+00 6.05e+11 28938
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1add1(update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours+ SubEduOver),
scope = ~ Gender+Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours,test = "F" )## Single term additions
##
## Model:
## Salary ~ Gender + Sector + EduLv + Field1 + Region + Staff +
## J_year + Hours + SubEduOver
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 5.79e+11 28879
## SubMismatch 1 2.67e+09 5.77e+11 28875 6.54 0.0107 *
## ObjOver 2 9.98e+09 5.69e+11 28858 12.35 4.8e-06 ***
## Core 2 5.36e+09 5.74e+11 28870 6.58 0.0014 **
## EduZone 0 0.00e+00 5.79e+11 28879
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1add1(update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours+ SubEduOver+SubMismatch),
scope = ~ Gender+Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours,test = "F" )## Single term additions
##
## Model:
## Salary ~ Gender + Sector + EduLv + Field1 + Region + Staff +
## J_year + Hours + SubEduOver + SubMismatch
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 5.77e+11 28875
## ObjOver 2 8.52e+09 5.68e+11 28857 10.6 2.8e-05 ***
## Core 2 3.74e+09 5.73e+11 28869 4.6 0.01 *
## EduZone 0 0.00e+00 5.77e+11 28875
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1add1(update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours+ ObjOver),
scope = ~ Gender+Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours,test = "F" )## Single term additions
##
## Model:
## Salary ~ Gender + Sector + EduLv + Field1 + Region + Staff +
## J_year + Hours + ObjOver
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 5.91e+11 28908
## SubEduOver 2 2.15e+10 5.69e+11 28858 26.58 4.7e-12 ***
## SubMismatch 1 6.13e+09 5.85e+11 28895 14.78 0.00013 ***
## Core 2 4.78e+09 5.86e+11 28900 5.75 0.00325 **
## EduZone 0 0.00e+00 5.91e+11 28908
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1add1(update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours+ ObjOver+ Core),
scope = ~ Gender+Sector+ Field1+ Region+ EduLv+ SubEduOver +SubMismatch +ObjOver +Core + J_year+ Staff+ EduZone+ Hours,test = "F" )## Single term additions
##
## Model:
## Salary ~ Gender + Sector + EduLv + Field1 + Region + Staff +
## J_year + Hours + ObjOver + Core
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 5.86e+11 28900
## SubEduOver 2 1.93e+10 5.67e+11 28855 24.0 5.8e-11 ***
## SubMismatch 1 3.89e+09 5.82e+11 28892 9.4 0.0022 **
## EduZone 0 0.00e+00 5.86e+11 28900
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# 薪資對性別
a1 <- update(null,~.+Gender)
summary(a1)##
## Call:
## lm(formula = Salary ~ Gender, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -33970 -16456 -6456 3544 246030
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 41456 800 51.80 <2e-16 ***
## Gender男 12514 1280 9.77 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 23800 on 1452 degrees of freedom
## Multiple R-squared: 0.0617, Adjusted R-squared: 0.0611
## F-statistic: 95.5 on 1 and 1452 DF, p-value: <2e-16# 薪資對性別 / 公私立.教育程度.學群
a2 <- update(null,~.+Gender+Sector+ EduLv+ Field1)
summary(a2)##
## Call:
## lm(formula = Salary ~ Gender + Sector + EduLv + Field1, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -46127 -11496 -2719 6733 236723
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 33151 5135 6.46 1.5e-10 ***
## Gender男 8218 1358 6.05 1.8e-09 ***
## Sector國外學校 13136 4631 2.84 0.0046 **
## Sector國立（公立） 2740 1380 1.99 0.0472 *
## EduLv博士 23705 8206 2.89 0.0039 **
## EduLv碩士 16464 3758 4.38 1.3e-05 ***
## EduLv普通大學 2615 3667 0.71 0.4759
## EduLv科技大學 -4590 3765 -1.22 0.2230
## EduLv五專 7434 5442 1.37 0.1722
## Field1大眾傳播學群 -3265 5177 -0.63 0.5284
## Field1工程學群 10553 4244 2.49 0.0130 *
## Field1文史哲學群 -2526 4665 -0.54 0.5882
## Field1外語學群 3612 4664 0.77 0.4388
## Field1生命科學學群 -2245 5430 -0.41 0.6794
## Field1生物資源學群 -4154 6044 -0.69 0.4920
## Field1地球與環境學群 -1096 6037 -0.18 0.8560
## Field1法政學群 -1451 4860 -0.30 0.7654
## Field1社會與心理學群 -2010 4426 -0.45 0.6498
## Field1建築與設計學群 2703 5022 0.54 0.5904
## Field1財經學群 2432 4466 0.54 0.5862
## Field1教育學群 -241 4547 -0.05 0.9578
## Field1資訊學群 5133 4462 1.15 0.2502
## Field1管理學群 -2160 4357 -0.50 0.6202
## Field1數理化學群 1547 4892 0.32 0.7519
## Field1醫藥衛生學群 11426 4493 2.54 0.0111 *
## Field1藝術學群 -6495 5481 -1.18 0.2363
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 21800 on 1428 degrees of freedom
## Multiple R-squared: 0.225, Adjusted R-squared: 0.212
## F-statistic: 16.6 on 25 and 1428 DF, p-value: <2e-16# 薪資對性別 / 公私立.教育程度.學群 / 地區.公司人數.年資.工時
a3 <- update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours)
summary(a3)##
## Call:
## lm(formula = Salary ~ Gender + Sector + EduLv + Field1 + Region +
## Staff + J_year + Hours, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -40250 -10516 -2106 6322 237176
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5741.0 13578.0 0.42 0.6725
## Gender男 7199.7 1299.4 5.54 3.6e-08 ***
## Sector國外學校 8954.5 4427.1 2.02 0.0433 *
## Sector國立（公立） 2907.0 1326.7 2.19 0.0286 *
## EduLv博士 14650.3 7860.4 1.86 0.0626 .
## EduLv碩士 16825.9 3593.4 4.68 3.1e-06 ***
## EduLv普通大學 5334.5 3498.6 1.52 0.1275
## EduLv科技大學 -1658.8 3592.6 -0.46 0.6443
## EduLv五專 4868.0 5185.8 0.94 0.3480
## Field1大眾傳播學群 -2636.2 4943.9 -0.53 0.5940
## Field1工程學群 9724.1 4067.3 2.39 0.0169 *
## Field1文史哲學群 -3985.5 4442.1 -0.90 0.3698
## Field1外語學群 2041.5 4436.7 0.46 0.6455
## Field1生命科學學群 -560.9 5181.4 -0.11 0.9138
## Field1生物資源學群 -1965.7 5755.1 -0.34 0.7327
## Field1地球與環境學群 -4167.5 5748.7 -0.72 0.4686
## Field1法政學群 -418.6 4636.4 -0.09 0.9281
## Field1社會與心理學群 -1467.1 4208.3 -0.35 0.7274
## Field1建築與設計學群 4506.5 4780.3 0.94 0.3460
## Field1財經學群 2780.6 4255.4 0.65 0.5136
## Field1教育學群 -308.6 4335.4 -0.07 0.9433
## Field1資訊學群 4860.2 4250.6 1.14 0.2531
## Field1管理學群 -3083.4 4145.1 -0.74 0.4571
## Field1數理化學群 855.0 4670.7 0.18 0.8548
## Field1醫藥衛生學群 10046.6 4321.7 2.32 0.0202 *
## Field1藝術學群 -4841.0 5215.6 -0.93 0.3535
## Region北北基 3695.9 3101.0 1.19 0.2335
## Region桃竹苗 7370.9 3313.0 2.22 0.0263 *
## Region中彰投 1696.3 3265.2 0.52 0.6035
## Region雲嘉南 -1156.7 3226.5 -0.36 0.7200
## Region高屏澎 -510.2 3221.8 -0.16 0.8742
## Staff10-29人 8521.2 12149.8 0.70 0.4832
## Staff100-199人 10919.7 12112.7 0.90 0.3675
## Staff1人 -6856.0 14178.7 -0.48 0.6288
## Staff2-9人 3516.5 12217.2 0.29 0.7735
## Staff200-499 7458.2 12140.4 0.61 0.5391
## Staff30-49人 9729.3 12213.0 0.80 0.4258
## Staff50-99人 9346.2 12139.5 0.77 0.4415
## Staff500人以上 12308.4 12074.6 1.02 0.3082
## J_year 1237.3 114.4 10.82 < 2e-16 ***
## Hours 185.4 58.7 3.16 0.0016 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20700 on 1413 degrees of freedom
## Multiple R-squared: 0.312, Adjusted R-squared: 0.292
## F-statistic: 16 on 40 and 1413 DF, p-value: <2e-16# 薪資對性別 / 公私立.教育程度.學群 / 地區.公司人數.年資.工時 / 自評過量
a41 <- update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours+ SubEduOver)
summary(a41)##
## Call:
## lm(formula = Salary ~ Gender + Sector + EduLv + Field1 + Region +
## Staff + J_year + Hours + SubEduOver, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -43320 -10300 -2252 6208 232961
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8566.3 13304.7 0.64 0.51977
## Gender男 7703.3 1275.4 6.04 2.0e-09 ***
## Sector國外學校 11680.8 4351.0 2.68 0.00735 **
## Sector國立（公立） 2703.7 1306.6 2.07 0.03870 *
## EduLv博士 13018.6 7703.7 1.69 0.09126 .
## EduLv碩士 17042.0 3522.2 4.84 1.5e-06 ***
## EduLv普通大學 4907.6 3427.2 1.43 0.15237
## EduLv科技大學 -1772.9 3519.2 -0.50 0.61450
## EduLv五專 5982.9 5081.1 1.18 0.23920
## Field1大眾傳播學群 -1712.9 4854.9 -0.35 0.72428
## Field1工程學群 10180.9 3984.1 2.56 0.01071 *
## Field1文史哲學群 -3133.4 4352.6 -0.72 0.47171
## Field1外語學群 2569.2 4347.7 0.59 0.55466
## Field1生命科學學群 1545.7 5083.7 0.30 0.76114
## Field1生物資源學群 -1886.4 5639.0 -0.33 0.73803
## Field1地球與環境學群 -2208.7 5636.5 -0.39 0.69522
## Field1法政學群 1589.1 4557.4 0.35 0.72738
## Field1社會與心理學群 -1752.3 4126.6 -0.42 0.67116
## Field1建築與設計學群 5433.2 4685.2 1.16 0.24638
## Field1財經學群 2479.2 4176.1 0.59 0.55284
## Field1教育學群 -662.3 4246.7 -0.16 0.87610
## Field1資訊學群 5214.4 4163.4 1.25 0.21062
## Field1管理學群 -1581.8 4065.1 -0.39 0.69725
## Field1數理化學群 1518.6 4575.8 0.33 0.74003
## Field1醫藥衛生學群 10080.0 4233.6 2.38 0.01740 *
## Field1藝術學群 -3681.0 5112.1 -0.72 0.47161
## Region北北基 2360.4 3042.0 0.78 0.43792
## Region桃竹苗 6267.2 3248.9 1.93 0.05393 .
## Region中彰投 649.0 3200.8 0.20 0.83935
## Region雲嘉南 -2092.9 3162.3 -0.66 0.50820
## Region高屏澎 -1086.5 3158.2 -0.34 0.73087
## Staff10-29人 8006.9 11900.7 0.67 0.50118
## Staff100-199人 10705.9 11864.1 0.90 0.36701
## Staff1人 -4246.6 13893.5 -0.31 0.75991
## Staff2-9人 4249.2 11966.8 0.36 0.72258
## Staff200-499 7267.5 11891.7 0.61 0.54120
## Staff30-49人 9213.6 11962.5 0.77 0.44131
## Staff50-99人 9307.6 11891.5 0.78 0.43393
## Staff500人以上 12268.4 11826.7 1.04 0.29975
## J_year 1145.1 112.7 10.16 < 2e-16 ***
## Hours 208.3 57.6 3.62 0.00031 ***
## SubEduOver高於工作要求 -9690.9 1372.7 -7.06 2.6e-12 ***
## SubEduOver低於工作要求 -8540.9 1843.3 -4.63 3.9e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20300 on 1411 degrees of freedom
## Multiple R-squared: 0.341, Adjusted R-squared: 0.321
## F-statistic: 17.4 on 42 and 1411 DF, p-value: <2e-16# 薪資對性別 / 公私立.教育程度.學群 / 地區.公司人數.年資.工時 / 自評過量.自評關聯
a42 <- update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours+ SubEduOver+SubMismatch)
summary(a42)##
## Call:
## lm(formula = Salary ~ Gender + Sector + EduLv + Field1 + Region +
## Staff + J_year + Hours + SubEduOver + SubMismatch, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -42485 -10370 -2109 6104 231342
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5053.3 13349.6 0.38 0.70509
## Gender男 7909.1 1275.5 6.20 7.4e-10 ***
## Sector國外學校 11898.6 4343.3 2.74 0.00623 **
## Sector國立（公立） 2649.8 1304.2 2.03 0.04236 *
## EduLv博士 11260.7 7719.3 1.46 0.14485
## EduLv碩士 16210.0 3530.3 4.59 4.8e-06 ***
## EduLv普通大學 4800.0 3420.7 1.40 0.16078
## EduLv科技大學 -2094.9 3514.6 -0.60 0.55123
## EduLv五專 5785.2 5071.7 1.14 0.25420
## Field1大眾傳播學群 -1436.0 4846.6 -0.30 0.76705
## Field1工程學群 10178.9 3976.3 2.56 0.01057 *
## Field1文史哲學群 -3039.1 4344.3 -0.70 0.48432
## Field1外語學群 2869.2 4340.8 0.66 0.50874
## Field1生命科學學群 2500.4 5087.5 0.49 0.62316
## Field1生物資源學群 -586.6 5650.9 -0.10 0.91734
## Field1地球與環境學群 -2241.8 5625.5 -0.40 0.69031
## Field1法政學群 1532.7 4548.5 0.34 0.73619
## Field1社會與心理學群 -1857.3 4118.7 -0.45 0.65210
## Field1建築與設計學群 5612.1 4676.5 1.20 0.23032
## Field1財經學群 2720.0 4169.0 0.65 0.51422
## Field1教育學群 -885.7 4239.3 -0.21 0.83453
## Field1資訊學群 5327.5 4155.5 1.28 0.20005
## Field1管理學群 -1214.9 4059.7 -0.30 0.76479
## Field1數理化學群 1600.3 4566.9 0.35 0.72608
## Field1醫藥衛生學群 9696.0 4227.9 2.29 0.02198 *
## Field1藝術學群 -2987.8 5109.3 -0.58 0.55879
## Region北北基 2470.1 3036.3 0.81 0.41605
## Region桃竹苗 6432.7 3243.1 1.98 0.04751 *
## Region中彰投 793.2 3195.0 0.25 0.80398
## Region雲嘉南 -1920.7 3156.9 -0.61 0.54300
## Region高屏澎 -860.8 3153.3 -0.27 0.78489
## Staff10-29人 7386.4 11879.9 0.62 0.53421
## Staff100-199人 9925.4 11844.8 0.84 0.40220
## Staff1人 -5186.2 13871.2 -0.37 0.70855
## Staff2-9人 3610.3 11946.0 0.30 0.76253
## Staff200-499 6575.1 11871.6 0.55 0.57977
## Staff30-49人 8487.1 11942.5 0.71 0.47741
## Staff50-99人 8503.0 11872.4 0.72 0.47399
## Staff500人以上 11628.9 11806.3 0.98 0.32480
## J_year 1150.2 112.5 10.23 < 2e-16 ***
## Hours 209.1 57.5 3.64 0.00029 ***
## SubEduOver高於工作要求 -8595.2 1435.5 -5.99 2.7e-09 ***
## SubEduOver低於工作要求 -7640.1 1873.1 -4.08 4.8e-05 ***
## SubMismatch 1231.3 481.6 2.56 0.01068 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20200 on 1410 degrees of freedom
## Multiple R-squared: 0.344, Adjusted R-squared: 0.324
## F-statistic: 17.2 on 43 and 1410 DF, p-value: <2e-16# 薪資對性別 / 公私立.教育程度.學群 / 地區.公司人數.年資.工時 / 客評過量
a51 <- update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours+ ObjOver)
summary(a51)##
## Call:
## lm(formula = Salary ~ Gender + Sector + EduLv + Field1 + Region +
## Staff + J_year + Hours + ObjOver, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -39783 -10215 -2215 6286 237864
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11493.7 13483.2 0.85 0.3941
## Gender男 6919.5 1287.1 5.38 8.9e-08 ***
## Sector國外學校 8438.5 4380.4 1.93 0.0543 .
## Sector國立（公立） 2570.9 1317.9 1.95 0.0513 .
## EduLv博士 15250.6 7776.7 1.96 0.0501 .
## EduLv碩士 18820.2 3572.9 5.27 1.6e-07 ***
## EduLv普通大學 4264.2 3468.3 1.23 0.2191
## EduLv科技大學 -2253.0 3555.0 -0.63 0.5263
## EduLv五專 625.2 5208.7 0.12 0.9045
## Field1大眾傳播學群 -4306.9 4904.8 -0.88 0.3800
## Field1工程學群 9275.8 4023.8 2.31 0.0213 *
## Field1文史哲學群 -5091.7 4399.1 -1.16 0.2473
## Field1外語學群 1856.9 4388.7 0.42 0.6723
## Field1生命科學學群 -1043.3 5126.3 -0.20 0.8388
## Field1生物資源學群 -1318.4 5694.2 -0.23 0.8169
## Field1地球與環境學群 -5437.8 5692.6 -0.96 0.3396
## Field1法政學群 -37.0 4591.9 -0.01 0.9936
## Field1社會與心理學群 -4256.0 4203.7 -1.01 0.3115
## Field1建築與設計學群 3275.7 4735.3 0.69 0.4892
## Field1財經學群 2011.1 4211.4 0.48 0.6331
## Field1教育學群 -1790.1 4296.3 -0.42 0.6770
## Field1資訊學群 3690.2 4211.0 0.88 0.3810
## Field1管理學群 -3244.9 4100.2 -0.79 0.4288
## Field1數理化學群 -606.9 4627.2 -0.13 0.8957
## Field1醫藥衛生學群 8604.7 4292.4 2.00 0.0452 *
## Field1藝術學群 -6525.7 5170.8 -1.26 0.2071
## Region北北基 3639.6 3068.3 1.19 0.2357
## Region桃竹苗 7602.0 3280.8 2.32 0.0206 *
## Region中彰投 2083.2 3235.9 0.64 0.5198
## Region雲嘉南 -1360.3 3196.4 -0.43 0.6705
## Region高屏澎 -552.3 3191.0 -0.17 0.8626
## Staff10-29人 7744.8 12019.1 0.64 0.5194
## Staff100-199人 10083.9 11982.7 0.84 0.4002
## Staff1人 -5656.3 14028.8 -0.40 0.6869
## Staff2-9人 2757.5 12085.8 0.23 0.8196
## Staff200-499 6803.7 12008.6 0.57 0.5711
## Staff30-49人 9125.1 12081.6 0.76 0.4502
## Staff50-99人 9109.7 12008.4 0.76 0.4482
## Staff500人以上 11877.4 11943.4 0.99 0.3202
## J_year 1214.7 113.3 10.72 < 2e-16 ***
## Hours 180.4 58.1 3.10 0.0019 **
## ObjOverover -5993.6 1334.8 -4.49 7.7e-06 ***
## ObjOverunder 6162.0 2806.2 2.20 0.0283 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20500 on 1411 degrees of freedom
## Multiple R-squared: 0.327, Adjusted R-squared: 0.307
## F-statistic: 16.4 on 42 and 1411 DF, p-value: <2e-16# 薪資對性別 / 公私立.教育程度.學群 / 地區.公司人數.年資.工時 / 客評過量.客評關聯
a52 <- update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ Staff+ J_year+ Hours+ ObjOver+ Core)
summary(a52)##
## Call:
## lm(formula = Salary ~ Gender + Sector + EduLv + Field1 + Region +
## Staff + J_year + Hours + ObjOver + Core, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -43456 -10367 -2184 5992 239420
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10435.0 13445.3 0.78 0.43782
## Gender男 7028.0 1284.2 5.47 5.2e-08 ***
## Sector國外學校 8931.2 4370.4 2.04 0.04118 *
## Sector國立（公立） 2601.1 1313.9 1.98 0.04794 *
## EduLv博士 13932.6 7764.5 1.79 0.07296 .
## EduLv碩士 17949.4 3570.4 5.03 5.6e-07 ***
## EduLv普通大學 4205.7 3456.9 1.22 0.22395
## EduLv科技大學 -2488.0 3543.8 -0.70 0.48274
## EduLv五專 384.5 5192.2 0.07 0.94098
## Field1大眾傳播學群 -4131.3 4889.8 -0.84 0.39832
## Field1工程學群 8949.6 4011.6 2.23 0.02584 *
## Field1文史哲學群 -5905.6 4400.1 -1.34 0.17976
## Field1外語學群 1266.1 4386.8 0.29 0.77292
## Field1生命科學學群 -284.7 5114.5 -0.06 0.95562
## Field1生物資源學群 -1332.1 5676.1 -0.23 0.81448
## Field1地球與環境學群 -6147.8 5689.2 -1.08 0.28006
## Field1法政學群 -501.7 4579.1 -0.11 0.91277
## Field1社會與心理學群 -4503.0 4190.8 -1.07 0.28279
## Field1建築與設計學群 2762.5 4721.9 0.59 0.55861
## Field1財經學群 1967.1 4197.3 0.47 0.63939
## Field1教育學群 -2940.4 4309.7 -0.68 0.49518
## Field1資訊學群 2711.6 4208.2 0.64 0.51944
## Field1管理學群 -3534.0 4090.4 -0.86 0.38774
## Field1數理化學群 -338.6 4612.4 -0.07 0.94149
## Field1醫藥衛生學群 7593.4 4294.7 1.77 0.07727 .
## Field1藝術學群 -6805.9 5156.6 -1.32 0.18710
## Region北北基 3706.3 3058.7 1.21 0.22581
## Region桃竹苗 7670.4 3269.8 2.35 0.01912 *
## Region中彰投 2231.2 3225.4 0.69 0.48921
## Region雲嘉南 -1239.5 3186.4 -0.39 0.69733
## Region高屏澎 -518.8 3180.6 -0.16 0.87047
## Staff10-29人 7639.5 11979.8 0.64 0.52378
## Staff100-199人 9464.5 11945.6 0.79 0.42832
## Staff1人 -6445.5 13984.7 -0.46 0.64494
## Staff2-9人 2066.3 12047.5 0.17 0.86384
## Staff200-499 6509.3 11969.1 0.54 0.58663
## Staff30-49人 8786.7 12042.5 0.73 0.46573
## Staff50-99人 8589.4 11971.1 0.72 0.47318
## Staff500人以上 11189.4 11906.2 0.94 0.34749
## J_year 1243.1 113.4 10.96 < 2e-16 ***
## Hours 179.7 57.9 3.10 0.00197 **
## ObjOverover -5033.1 1367.3 -3.68 0.00024 ***
## ObjOverunder 5577.0 2818.0 1.98 0.04801 *
## Core部分關聯 4760.2 1694.3 2.81 0.00503 **
## Core核心關聯 3489.3 1396.4 2.50 0.01258 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20400 on 1409 degrees of freedom
## Multiple R-squared: 0.333, Adjusted R-squared: 0.312
## F-statistic: 16 on 44 and 1409 DF, p-value: <2e-16# 或許拿掉公司人數?
# 薪資對性別 / 公私立.教育程度.學群 / 地區.年資.工時 / 自評過量.自評關聯
a53 <- update(null,~.+Gender+Sector+ EduLv+ Field1+ Region+ J_year+ Hours+ ObjOver+ Core)
summary(a53)##
## Call:
## lm(formula = Salary ~ Gender + Sector + EduLv + Field1 + Region +
## J_year + Hours + ObjOver + Core, data = p)
##
## Residuals:
## Min 1Q Median 3Q Max
## -45434 -10790 -2176 6517 240433
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 17629.4 6366.3 2.77 0.00569 **
## Gender男 7517.8 1286.3 5.84 6.3e-09 ***
## Sector國外學校 8865.8 4381.4 2.02 0.04321 *
## Sector國立（公立） 2852.6 1306.0 2.18 0.02911 *
## EduLv博士 14460.2 7799.9 1.85 0.06396 .
## EduLv碩士 19048.2 3580.7 5.32 1.2e-07 ***
## EduLv普通大學 4958.0 3470.6 1.43 0.15335
## EduLv科技大學 -2236.5 3561.2 -0.63 0.53008
## EduLv五專 312.8 5216.4 0.06 0.95219
## Field1大眾傳播學群 -3875.8 4901.2 -0.79 0.42921
## Field1工程學群 9427.7 4003.5 2.35 0.01867 *
## Field1文史哲學群 -5647.1 4411.0 -1.28 0.20067
## Field1外語學群 1052.1 4405.9 0.24 0.81130
## Field1生命科學學群 -1305.8 5117.5 -0.26 0.79863
## Field1生物資源學群 -1492.8 5688.6 -0.26 0.79304
## Field1地球與環境學群 -5943.3 5704.9 -1.04 0.29768
## Field1法政學群 -130.9 4585.5 -0.03 0.97723
## Field1社會與心理學群 -4522.7 4206.1 -1.08 0.28244
## Field1建築與設計學群 1880.6 4741.0 0.40 0.69167
## Field1財經學群 2473.6 4207.1 0.59 0.55664
## Field1教育學群 -3078.3 4313.5 -0.71 0.47557
## Field1資訊學群 3107.5 4217.6 0.74 0.46137
## Field1管理學群 -2854.7 4102.8 -0.70 0.48667
## Field1數理化學群 338.8 4611.5 0.07 0.94144
## Field1醫藥衛生學群 8902.4 4274.6 2.08 0.03746 *
## Field1藝術學群 -7529.4 5172.3 -1.46 0.14569
## Region北北基 3872.3 3072.8 1.26 0.20781
## Region桃竹苗 8045.8 3283.4 2.45 0.01439 *
## Region中彰投 1858.5 3242.9 0.57 0.56668
## Region雲嘉南 -1492.1 3200.4 -0.47 0.64112
## Region高屏澎 -940.3 3191.3 -0.29 0.76832
## J_year 1263.2 113.3 11.15 < 2e-16 ***
## Hours 177.2 58.2 3.05 0.00236 **
## ObjOverover -4888.1 1370.4 -3.57 0.00037 ***
## ObjOverunder 5883.9 2825.0 2.08 0.03745 *
## Core部分關聯 5118.9 1694.7 3.02 0.00257 **
## Core核心關聯 3442.0 1400.8 2.46 0.01412 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20500 on 1417 degrees of freedom
## Multiple R-squared: 0.321, Adjusted R-squared: 0.303
## F-statistic: 18.6 on 36 and 1417 DF, p-value: <2e-16