Progress Report Project
Federico Ferrero
4/14/2021
Final Project Knowledge Mining
# clear your memory
rm(list=ls())Argentine Aprender Evaluation
Reading in the data
mydata <- read.delim("/Users/feder/Desktop/km_project/aprender_cordoba_dataset.txt")Names of variables
names(mydata)## [1] "ID1" "cod_provincia"
## [3] "sector" "ambito"
## [5] "claveseccion" "idalumno"
## [7] "ap01_01" "ap01_02"
## [9] "ap02" "gender"
## [11] "female" "ap03"
## [13] "ap04" "ap05"
## [15] "ap06" "ap07"
## [17] "ap08_a" "ap08_b"
## [19] "ap08_c" "ap08_d"
## [21] "ap08_e" "ap08_f"
## [23] "ap08_g" "ap08_h"
## [25] "ap08_i" "ap09"
## [27] "ap10" "ap11_01"
## [29] "ap11_02" "ap11_03"
## [31] "ap11_04" "ap11_05"
## [33] "ap11_06" "ap11_07"
## [35] "ap11_08" "ap12"
## [37] "ap13" "ap14_01"
## [39] "ap14_02" "ap15"
## [41] "ap16" "ap17"
## [43] "ap18_01" "ap18_02"
## [45] "ap18_03" "ap19"
## [47] "ap21" "ap22"
## [49] "ap23_01" "ap23_02"
## [51] "ap23_03" "ap23_04"
## [53] "ap23_05" "ap23_06"
## [55] "ap24" "ap25_01"
## [57] "ap25_02" "ap25_03"
## [59] "ap26" "ap27_a"
## [61] "ap27_b" "ap27_c"
## [63] "ap27_d" "ap27_e"
## [65] "ap27_f" "ap28_01"
## [67] "ap28_02" "ap28_03"
## [69] "ap28_04" "ap29_01"
## [71] "ap29_02" "ap29_03"
## [73] "ap29_04" "ap29_05"
## [75] "ap29_06" "ap29_07"
## [77] "ap30" "ap31_01"
## [79] "ap31_02" "ap31_03"
## [81] "ap31_04" "ap31_05"
## [83] "ap31_06" "ap32_a"
## [85] "ap32_b" "ap32_c"
## [87] "ap32_d" "ap32_e"
## [89] "ap32_f" "ap33_01_a"
## [91] "ap33_02_a" "ap33_03_a"
## [93] "ap33_04_a" "ap33_01_b"
## [95] "ap33_02_b" "ap33_03_b"
## [97] "ap33_04_b" "ap33_01bis"
## [99] "ap33_02bis" "ap33_03bis"
## [101] "ap33_04bis" "ap33_05bis"
## [103] "ap33_06bis" "ap33_07bis"
## [105] "ap33_08bis" "ap33_09bis"
## [107] "ap33_10bis" "ap33_11bis"
## [109] "ap34" "ap35_01"
## [111] "ap35_02" "ap35_03"
## [113] "ap35_04" "ap35_05"
## [115] "ap36_a" "ap36_b"
## [117] "ap36_c" "ap36_d"
## [119] "ap36_e" "ap36_f"
## [121] "ap37_a" "ap37_b"
## [123] "ap37_c" "ap37_d"
## [125] "ap37_e" "ap37_f"
## [127] "ap37_g" "ap37_h"
## [129] "ap37_i" "ap37_j"
## [131] "ap37_k" "ap37_l"
## [133] "ap37_m" "ap37_n"
## [135] "ap38_a" "ap38_b"
## [137] "ap38_c" "ap38_d"
## [139] "ap38_e" "ap38_f"
## [141] "ap38_g" "ap38_h"
## [143] "ap38_i" "ap38_j"
## [145] "ap38_k" "ap38_l"
## [147] "ap38_m" "ap38_n"
## [149] "ap39_01" "ap39_02"
## [151] "ap39_03" "ap39_04"
## [153] "ap40_01" "ap40_02"
## [155] "ap40_03" "ap40_04"
## [157] "ap40_05" "ap40_06"
## [159] "ap41_01" "ap41_02"
## [161] "ap41_03" "ap41_04"
## [163] "ap41_05" "ap41_06"
## [165] "ap41_07" "ap41_08"
## [167] "ap41_09" "ap41_10"
## [169] "ap41_11" "ap42_01"
## [171] "ap42_02" "ap42_03"
## [173] "ap42_04" "ap43_a"
## [175] "ap43_b" "ap43_c"
## [177] "ap43_d" "ap43_e"
## [179] "ap43_f" "ap43_g"
## [181] "ap43_h" "ap44_01"
## [183] "ap44_02" "ap44_03"
## [185] "ap44_04" "ap44_05"
## [187] "ap45" "ap46_01"
## [189] "ap46_02" "ap46_03"
## [191] "ap46_04" "ap46_05"
## [193] "ap47_01" "ap47_02"
## [195] "ap47_03" "ap47_04"
## [197] "ap47_05" "ap47_06"
## [199] "ap47_07" "ap47_08"
## [201] "ap47_09" "ap47_10"
## [203] "ap47_11" "ap47_12"
## [205] "ap48_a" "ap48_b"
## [207] "ap48_c" "ap48_d"
## [209] "ap48_e" "ap48_f"
## [211] "ap48_g" "ap48_h"
## [213] "ap48_i" "ap49_01"
## [215] "ap49_02" "ap50_01"
## [217] "ap50_02" "ap50_03"
## [219] "ap50_04" "ap50_05"
## [221] "ap51_01" "ap51_02"
## [223] "ap51_03" "ap51_04"
## [225] "ap51_05" "ap51_06"
## [227] "ap51_07" "ap51_08"
## [229] "ap51_09" "ap51_10"
## [231] "ponder" "lpondera"
## [233] "mpondera" "ldesemp"
## [235] "mdesemp" "TEL"
## [237] "TEM" "modelo"
## [239] "isocioa_puntaje" "isocioa"
## [241] "isocioal_puntaje" "isocioal"
## [243] "isocioam_puntaje" "isocioam"
## [245] "repitencia_dicotomica" "jardÃn"
## [247] "ap37_dicotomica" "ap29_01.dico"
## [249] "ap29_02.dico" "ap29_03.dico"
## [251] "ap29_04.dico" "ap29_05.dico"
## [253] "ap29_06.dico" "ap29_07.dico"
## [255] "ap26_rec" "trabaja_fuera_hogar"
## [257] "trabaja_fuera_hogar_remunerado" "migración"
## [259] "edadA_junio2019" "sobreedad"
## [261] "infraestructura" "iinfraestructura"
## [263] "ap42_01rec" "ap42_02rec"
## [265] "ap42_03rec" "ap42_04rec"Performance by Sector and Ambit
par(mfrow=c(2, 2))
boxplot(ldesemp~sector,data=mydata, main="Language Performance by Sector", sub="1= Public 2= Private",
xlab="Sector", ylab="Language Performance", col="orange")
boxplot(ldesemp~ambito,data=mydata, main="Language Performance by Ambit", sub="1= Urban 2= Rural",
xlab="Ambit", ylab="Language Performance", col="orange")
boxplot(mdesemp~sector,data=mydata, main="Math Performance by Sector", sub="1= Public 2= Private",
xlab="Sector", ylab="Math Performance", col="lightblue")
boxplot(mdesemp~ambito,data=mydata, main="Math Performance by Ambit", sub="1= Urban 2= Rural",
xlab="Ambit", ylab="Math Performance", col="lightblue")
Performance by Gender
par(mfrow=c(1, 2))
counts1 <- table(mydata$ldesemp, mydata$gender)
barplot(counts1, main="Language Perf. Level by Gender", sub="1= Male 2= Female 3= Other",
xlab="Gender", col=c("red","orange","lightblue","forestgreen"))
counts2 <- table(mydata$mdesemp, mydata$gender)
barplot(counts2, main="Math Perf. Level by Gender", sub="1= Male 2= Female 3= Other",
xlab="Gender", col=c("red","orange","lightblue","forestgreen"))
Performance by School Repetition and Students Who Work
par(mfrow=c(2, 2))
boxplot(ldesemp~repitencia_dicotomica,data=mydata, main="Language Performance by School Repetition", sub="1= Repeated 2= Non Repeated 3= No answer",
xlab="School Repetition", ylab="Language Performance", col="pink")
boxplot(mdesemp~repitencia_dicotomica,data=mydata, main="Math Performance by School Repetition", sub="1= Repeated 2= Non Repeated 3= No answer",
xlab="School Repetition", ylab="Math Performance", col="pink")
boxplot(ldesemp~trabaja_fuera_hogar,data=mydata, main="Language Performance by Students Who Work", sub="1= Yes 2= No 3= No answer",
xlab="Students Who Work", ylab="Language Performance", col="darkkhaki")
boxplot(mdesemp~trabaja_fuera_hogar,data=mydata, main="Math Performance by Students Who Work", sub="1= Yes 2= No 3= No answer",
xlab="Students Who Work", ylab="Math Performance", col="darkkhaki")
Performance by Socioeconomic level
par(mfrow=c(1, 2))
counts1 <- table(mydata$ldesemp, mydata$isocioa)
barplot(counts1, main="Language Perfor. by Socioeconomic", sub="-1=Non Answer, 1= Low 2= Medium 3= High",
xlab="Socioeconomic Level", col=c("red","orange","lightblue","forestgreen"))
counts2 <- table(mydata$mdesemp, mydata$isocioa)
barplot(counts2, main="Math Perfor. by Socioeconomic", sub="-1=Non Answer, 1= Low 2= Medium 3= High",
xlab="Socioeconomic Level", col=c("red","orange","lightblue","forestgreen"))
Percentages in tables
prop.table(counts1)##
## -1 1 2 3
## 1 0.007986887 0.029563403 0.070868723 0.011592907
## 2 0.007510058 0.030546863 0.103352705 0.021248696
## 3 0.013857845 0.047921323 0.322455670 0.115601252
## 4 0.004112651 0.006854418 0.121531813 0.084994785prop.table(counts2)##
## -1 1 2 3
## 1 0.0149030851 0.0637039692 0.1952035361 0.0383776842
## 2 0.0087208434 0.0341068602 0.1878565242 0.0533106352
## 3 0.0081533913 0.0154406714 0.2175133650 0.1222112714
## 4 0.0009855748 0.0006271839 0.0184869934 0.0203984111Correlations using subset of variables (until 15 variables)
#library(ggplot2)
#library(GGally)
#mydata[,c("ldesemp","mdesemp","gender","sector","ambito","isocioa")]Testing regressions
fit1=lm(mdesemp~ female + factor(sector)+ factor(ambito) + factor(isocioa), data=mydata)
summary(fit1)##
## Call:
## lm(formula = mdesemp ~ female + factor(sector) + factor(ambito) +
## factor(isocioa), data = mydata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7191 -0.7191 0.1510 0.6035 2.6035
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.721431 0.026585 64.753 < 2e-16 ***
## female -0.122334 0.009206 -13.288 < 2e-16 ***
## factor(sector)2 0.500041 0.009903 50.494 < 2e-16 ***
## factor(ambito)2 -0.095448 0.017572 -5.432 5.62e-08 ***
## factor(isocioa)1 -0.107166 0.029513 -3.631 0.000283 ***
## factor(isocioa)2 0.222974 0.026710 8.348 < 2e-16 ***
## factor(isocioa)3 0.497616 0.027978 17.786 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.829 on 33044 degrees of freedom
## (1140 observations deleted due to missingness)
## Multiple R-squared: 0.1624, Adjusted R-squared: 0.1623
## F-statistic: 1068 on 6 and 33044 DF, p-value: < 2.2e-16fit2=lm(ldesemp~ female + factor(sector)+ factor(ambito) + factor(isocioa),data=mydata)
summary(fit2)##
## Call:
## lm(formula = ldesemp ~ female + factor(sector) + factor(ambito) +
## factor(isocioa), data = mydata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.32520 -0.36500 0.03754 0.67480 1.96059
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.250895 0.027003 83.356 < 2e-16 ***
## female 0.114102 0.009393 12.147 < 2e-16 ***
## factor(sector)2 0.386280 0.010104 38.229 < 2e-16 ***
## factor(ambito)2 -0.141506 0.017909 -7.901 2.84e-15 ***
## factor(isocioa)1 -0.069978 0.029977 -2.334 0.0196 *
## factor(isocioa)2 0.325282 0.027136 11.987 < 2e-16 ***
## factor(isocioa)3 0.573918 0.028438 20.182 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8462 on 33087 degrees of freedom
## (1097 observations deleted due to missingness)
## Multiple R-squared: 0.1316, Adjusted R-squared: 0.1314
## F-statistic: 835.6 on 6 and 33087 DF, p-value: < 2.2e-16GRADUATE Admissions Case
Clear my memory
rm(list=ls())Reading in the data
mydata <- read.delim("/Users/feder/Desktop/km_project/admission_predict.txt")Names of variables
names(mydata)## [1] "Serial.No." "GRE.Score" "TOEFL.Score"
## [4] "University.Rating" "SOP" "LOR"
## [7] "CGPA" "Research" "Chance.of.Admit"Checking for linearity (for each predictor against the dep variable) with scatterplots
par(mfrow=c(3,3))
scatter.smooth(x=mydata$GRE.Score, y=mydata$Chance.of.Admit, main="Chance of Admission ~ GRES Scores")
scatter.smooth(x=mydata$TOEFL.Score, y=mydata$Chance.of.Admit, main="Chance of Admission ~ TOEFL Scores")
scatter.smooth(x=mydata$University.Rating, y=mydata$Chance.of.Admit, main="Chance of Admission ~ University Ranking") ## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at 3## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at 3## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at 3## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at 3## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at 3## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1scatter.smooth(x=mydata$SOP, y=mydata$Chance.of.Admit, main="Chance of Admission ~ Statement of Purpose Strength")
scatter.smooth(x=mydata$LOR, y=mydata$Chance.of.Admit, main="Chance of Admission ~ Letter of Recommendation Strength")
scatter.smooth(x=mydata$CGPA, y=mydata$Chance.of.Admit, main="Chance of Admission ~ Undergraduate GPA")
scatter.smooth(x=mydata$Research, y=mydata$Chance.of.Admit, main="Chance of Admission ~ Research Experience") ## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 6.1612e-016## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1.01## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1.01## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1.01## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1.01## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 1.005## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 6.1612e-016## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## There are other near singularities as well. 1.01
Checking for outliers with boxplots
par(mfrow=c(2, 3))
boxplot(mydata$Chance.of.Admit, main="Chance of Admission", sub=paste("Outlier rows: ", boxplot.stats(mydata$Chance.of.Admit)$out))
boxplot(mydata$GRE.Score, main="GRE Scores", sub=paste("Outlier rows: ", boxplot.stats(mydata$GRE.Score)$out))
boxplot(mydata$TOEFL.Score, main="TOEFL Scores", sub=paste("Outlier rows: ", boxplot.stats(mydata$TOEFL.Score)$out))
boxplot(mydata$University.Rating, main="University Ranking", sub=paste("Outlier rows: ", boxplot.stats(mydata$University.Rating)$out))
boxplot(mydata$SOP, main="Statement of Purpose Strength", sub=paste("Outlier rows: ", boxplot.stats(mydata$SOP)$out))
boxplot(mydata$LOR, main="Letter of Recommendation Strength", sub=paste("Outlier rows: ", boxplot.stats(mydata$LOR)$out)) 
Checking for normality with density plots
library(e1071)## Warning: package 'e1071' was built under R version 4.0.4par(mfrow=c(3, 3))
plot(density(mydata$Chance.of.Admit), main="Chance of Admission", ylab="Frequency", sub=paste("Skewness:", round(e1071::skewness(mydata$Chance.of.Admit), 2)))
polygon(density(mydata$Chance.of.Admit), col="lightblue")
plot(density(mydata$GRE.Score), main="GRE Scores", ylab="Frequency", sub=paste("Skewness:", round(e1071::skewness(mydata$GRE.Score), 2)))
polygon(density(mydata$GRE.Score), col="lightblue")
plot(density(mydata$TOEFL.Score), main="TOEFL Scores", ylab="Frequency", sub=paste("Skewness:", round(e1071::skewness(mydata$TOEFL.Score), 2)))
polygon(density(mydata$TOEFL.Score), col="lightblue")
plot(density(mydata$University.Rating), main="University Ranking", ylab="Frequency", sub=paste("Skewness:", round(e1071::skewness(mydata$University.Rating), 2)))
polygon(density(mydata$University.Rating), col="lightblue")
plot(density(mydata$SOP), main="Statement of Purpose Strength", ylab="Frequency", sub=paste("Skewness:", round(e1071::skewness(mydata$SOP), 2)))
polygon(density(mydata$SOP), col="lightblue")
plot(density(mydata$LOR), main="Letter of Recommendation Strength", ylab="Frequency", sub=paste("Skewness:", round(e1071::skewness(mydata$LOR), 2)))
polygon(density(mydata$LOR), col="lightblue")
plot(density(mydata$Research), main="Research", ylab="Frequency", sub=paste("Skewness:", round(e1071::skewness(mydata$Research), 2)))
polygon(density(mydata$Research), col="lightblue")
Checking correlations: scatterplot matrix
library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.0.3library(GGally)## Warning: package 'GGally' was built under R version 4.0.4## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2ggpairs(mydata)
Regression analysis
fit1=lm(Chance.of.Admit ~ GRE.Score + TOEFL.Score + University.Rating + SOP + LOR + CGPA + Research, mydata)
summary(fit1) # University Ranking and SOP are statistically insignificant, f-statistic lower##
## Call:
## lm(formula = Chance.of.Admit ~ GRE.Score + TOEFL.Score + University.Rating +
## SOP + LOR + CGPA + Research, data = mydata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.266657 -0.023327 0.009191 0.033714 0.156818
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.2757251 0.1042962 -12.232 < 2e-16 ***
## GRE.Score 0.0018585 0.0005023 3.700 0.000240 ***
## TOEFL.Score 0.0027780 0.0008724 3.184 0.001544 **
## University.Rating 0.0059414 0.0038019 1.563 0.118753
## SOP 0.0015861 0.0045627 0.348 0.728263
## LOR 0.0168587 0.0041379 4.074 5.38e-05 ***
## CGPA 0.1183851 0.0097051 12.198 < 2e-16 ***
## Research 0.0243075 0.0066057 3.680 0.000259 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.05999 on 492 degrees of freedom
## Multiple R-squared: 0.8219, Adjusted R-squared: 0.8194
## F-statistic: 324.4 on 7 and 492 DF, p-value: < 2.2e-16fit2=lm(Chance.of.Admit ~ GRE.Score + TOEFL.Score + LOR + CGPA + Research, mydata)
summary(fit2)##
## Call:
## lm(formula = Chance.of.Admit ~ GRE.Score + TOEFL.Score + LOR +
## CGPA + Research, data = mydata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.265965 -0.023835 0.008003 0.035543 0.158379
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.3357018 0.0990753 -13.482 < 2e-16 ***
## GRE.Score 0.0018892 0.0005024 3.760 0.000190 ***
## TOEFL.Score 0.0030174 0.0008619 3.501 0.000506 ***
## LOR 0.0193203 0.0037939 5.092 5.04e-07 ***
## CGPA 0.1229798 0.0093018 13.221 < 2e-16 ***
## Research 0.0251649 0.0065988 3.814 0.000154 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.06007 on 494 degrees of freedom
## Multiple R-squared: 0.8207, Adjusted R-squared: 0.8188
## F-statistic: 452.1 on 5 and 494 DF, p-value: < 2.2e-163D visualization
library(plotly)## Warning: package 'plotly' was built under R version 4.0.3##
## Attaching package: 'plotly'## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layoutplot <- plot_ly(mydata,
x = ~CGPA,
y = ~Chance.of.Admit,
z = ~Research,
type = "scatter3d",
size = 0.02)
plot## No scatter3d mode specifed:
## Setting the mode to markers
## Read more about this attribute -> https://plotly.com/r/reference/#scatter-mode