ABA

EXP 1
> name<-c("ramu","raju","ravi","vamsi","naveen","kishor","chatu","rani","sita","lakshmi")
> t1<-c(15,17,20,12,14,9,15,19,25,19)
> t2<-c(NA,19,24,16,19,20,18,16,20,NA)
> gd<-c(1,1,1,1,0,1,0,1,1,0)
> dt<-data.frame(name,t1,t2,gd)
> str(dt)
'data.frame': 10 obs. of 4 variables:
$ name: chr "ramu" "raju" "ravi" "vamsi" ...
$ t1 : num 15 17 20 12 14 9 15 19 25 19
$ t2 : num NA 19 24 16 19 20 18 16 20 NA
$ gd : num 1 1 1 1 0 1 0 1 1 0
> dt['gd']<-as.factor(dt$gd)
> str(dt)
$ t1 : num 15 17 20 12 14 9 15 19 25 19
$ t2 : num NA 19 24 16 19 20 18 16 20 NA
$ gd : Factor w/ 2 levels "0","1": 2 2 2 2 1 2 1 2 2 1
> dt$t2[is.na(dt$t2)]<-mean(dt$t2,na.rm = T)
> str(dt)
$ t1 : num 15 17 20 12 14 9 15 19 25 19
$ t2 : num 19 19 24 16 19 20 18 16 20 19
$ gd : Factor w/ 2 levels "0","1": 2 2 2 2 1 2 1 2 2 1
> boxplot(dt$t1,dt$t2)
pg. 1
> out<-boxplot.stats(dt$t2)$out
> out
[1] 24
> dt$t2[dt$t2%in%out]<-median(dt$t2)
> boxplot(dt$t1,dt$t2)
pg. 2
EXP 2
> #exp 2
> #ABA-K.CHATURVEDA REDDY
> x=c(60,60,60)
> p=c(1/3,1/3,1/3)
> chisq.test(x=x,p=p)
Chi-squared test for given probabilities
data: x
X-squared = 0, df = 2, p-value = 1
> x=c(70,50,30)
> p=x/sum(x)
>p
[1] 0.4666667 0.3333333 0.2000000
> chisq.test(x=x,p=p)
data: x
X-squared = 0, df = 2, p-value = 1
> p1=c(1/2,1/6,1/5)
> p1=c(1/2,1/6,1/3)
> chisq.test(x=x,p=p1)
data: x
X-squared = 33.333, df = 2, p-value = 5.778e-08
> #NH:the distribution of observed data is same as expecte
> #AH: the distribution of observed data is not same as expecte
pg. 3
EXP 3
> #exp3
> #ABA-Correlation Analysis -K.Chaturveda reddy
> dt<-mtcars
> cor(dt$mpg,dt$wt)
[1] -0.8676594
> cor(dt$hp,dt$cyl)
[1] 0.8324475
> #multi-variant correlation
> dt1<-mtcars[,c(1,3:7)]
> dt11<-cor(dt1)
> library(corrplot)
corrplot 0.92 loaded
Warning message:
package ‘corrplot’ was built under R version 4.1.2
> corrplot(dt11,method = 'number')
pg. 4
EXP 4
> #EXP 4
> #ABA-K.CHATURVEDA REDDY
> #simple liner regression
> dt<-lm(mpg~hp,data = mtcars)
> dt
Call:
lm(formula = mpg ~ hp, data = mtcars)
Coefficients:
(Intercept) hp
30.09886 -0.06823
> summary(dt)
Call:
lm(formula = mpg ~ hp, data = mtcars)
Residuals:
Min 1Q Median 3Q Max
-5.7121 -2.1122 -0.8854 1.5819 8.2360
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 30.09886 1.63392 18.421 < 2e-16 ***
hp -0.06823 0.01012 -6.742 1.79e-07 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 3.863 on 30 degrees of freedom
pg. 5
Multiple R-squared: 0.6024, Adjusted R-squared: 0.5892
F-statistic: 45.46 on 1 and 30 DF, p-value: 1.788e-07
> #multiple liner regression
> dt<-lm(mpg~.,data = mtcars)
> dt
Call:
lm(formula = mpg ~ ., data = mtcars)
Coefficients:
(Intercept) cyl disp hp drat
12.30337 -0.11144 0.01334 -0.02148 0.78711
wt qsec vs am gear
-3.71530 0.82104 0.31776 2.52023 0.65541
carb
-0.19942
> summary(dt)
Call:
lm(formula = mpg ~ ., data = mtcars)
Residuals:
-3.4506 -1.6044 -0.1196 1.2193 4.6271
Coefficients:
(Intercept) 12.30337 18.71788 0.657 0.5181
cyl -0.11144 1.04502 -0.107 0.9161
pg. 6
disp 0.01334 0.01786 0.747 0.4635
hp -0.02148 0.02177 -0.987 0.3350
drat 0.78711 1.63537 0.481 0.6353
wt -3.71530 1.89441 -1.961 0.0633 .
qsec 0.82104 0.73084 1.123 0.2739
vs 0.31776 2.10451 0.151 0.8814
am 2.52023 2.05665 1.225 0.2340
gear 0.65541 1.49326 0.439 0.6652
carb -0.19942 0.82875 -0.241 0.8122
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
pg. 7
EXP 5
> #exp 5
> #ABA LOGISTIC REGRESSION
> #binomial logistic regression
> str(mtcars)
$ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
$ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
$ disp: num 160 160 108 258 360 ...
$ hp : num 110 110 93 110 175 105 245 62 95 123 ...
$ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
$ wt : num 2.62 2.88 2.32 3.21 3.44 ...
$ qsec: num 16.5 17 18.6 19.4 17 ...
$ vs : num 0 0 1 1 0 1 0 1 1 1 ...
$ am : num 1 1 1 0 0 0 0 0 0 0 ...
$ gear: num 4 4 4 3 3 3 3 4 4 4 ...
$ carb: num 4 4 1 1 2 1 4 2 2 4 ...
> dt<-as.factor(mtcars$am)
> str(dt)
Factor w/ 2 levels "0","1": 2 2 2 1 1 1 1 1 1 1 ...
> am<-as.factor(mtcars$am)
> str(am)
Factor w/ 2 levels "0","1": 2 2 2 1 1 1 1 1 1 1 ...
> mt<-mtcars[,c(3:7)]
> dt<-sample(c(1,2),32,32)
> str(dt)
num [1:32] 2 1 1 1 1 1 1 2 1 2 ...
> dt<-as.factor(dt)
> md<-glm(dt~mtcars$mpg,family = 'binomial')
> md
pg. 8
Call: glm(formula = dt ~ mtcars$mpg, family = "binomial")
Coefficients:
(Intercept) mtcars$mpg
-0.202813 -0.002415
Degrees of Freedom: 31 Total (i.e. Null); 30 Residual
Null Deviance: 43.86
Residual Deviance: 43.86 AIC: 47.86
> summary(md)
Call:
glm(formula = dt ~ mtcars$mpg, family = "binomial")
Deviance Residuals:
-1.082 -1.074 -1.066 1.281 1.299
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -0.202813 1.258501 -0.161 0.872
mtcars$mpg -0.002415 0.060110 -0.040 0.968
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 43.860 on 31 degrees of freedom
Residual deviance: 43.858 on 30 degrees of freedom
AIC: 47.858
Number of Fisher Scoring iterations: 3
pg. 9
> library(nnet, lib.loc = "C:/Program Files/R/R-4.1.1/library")
> dt<-sample(1:4,32,32)
> #multinom logistic regression
> md<-multinom(dt~mtcars$mpg)
# weights: 12 (6 variable)
initial value 44.361420
iter 10 value 39.620203
final value 39.619342
converged
> md
Call:
multinom(formula = dt ~ mtcars$mpg)
Coefficients:
2 1.5037549 -0.1088401
3 0.6804832 -0.0142661
4 -3.4490522 0.1509189
Residual Deviance: 79.23868
AIC: 91.23868
> summary(md)
Call:
multinom(formula = dt ~ mtcars$mpg)
Coefficients:
2 1.5037549 -0.1088401
3 0.6804832 -0.0142661
4 -3.4490522 0.1509189
pg. 10
Std. Errors:
2 2.309482 0.12598808
3 1.744554 0.08717987
4 2.173418 0.09592167
AIC: 91.23868
> #ordinal logistic regression
> library(MASS, lib.loc = "C:/Program Files/R/R-4.1.1/library")
> str(dt)
int [1:32] 4 3 4 3 2 1 1 3 3 2 ...
> dt<-factor(dt,levels = c(1,2,3,4),ordered = T)
> str(dt)
Ord.factor w/ 4 levels "1"<"2"<"3"<"4": 4 3 4 3 2 1 1 3 3 2 ...
> md<-polr(dt~mtcars$mpg)
> md<-polr(dt~mtcars$mpg,Hess = T)
> summary(md)
Call:
polr(formula = dt ~ mtcars$mpg, Hess = T)
Coefficients:
Value Std. Error t value
mtcars$mpg 0.1199 0.06425 1.866
Intercepts:
Value Std. Error t value
1|2 1.1288 1.2427 0.9083
2|3 1.8821 1.2534 1.5017
3|4 3.7377 1.4184 2.6352
AIC: 89.79075
pg. 11
EXP 6
> #EXP 6
> #ABA- MEDIATION ANALYSIS -K.CHATURVEDA
> dt<-trees
> library(psych)
> md<-mediate(x='Height',m='Volume',y='Girth',data=dt)
> print(md,short = F)
Mediation/Moderation Analysis
Call: mediate(y = "Girth", x = "Height", m = "Volume",
data = dt)
The DV (Y) was Girth . The IV (X) was Height . The mediating variable(s) = Volume .
Total effect(c) of Height on Girth = 0.26 S.E. = 0.08 t = 3.27 df= 29 with p = 0.0028
Direct effect (c') of Height on Girth removing Volume = -0.05 S.E. = 0.03 t = -1.61 df= 28
with p = 0.12
Indirect effect (ab) of Height on Girth through Volume = 0.3
Mean bootstrapped indirect effect = 0.3 with standard error = 0.08 Lower CI = 0.16 Upper CI =
0.46
R = 0.97 R2 = 0.94 F = 222.47 on 2 and 28 DF p-value: 1.25e-19
Full output
Call: mediate(y = "Girth", x = "Height", m = "Volume",
data = dt)
Direct effect estimates (traditional regression) (c') X + M on Y
Girth se t df Prob
Intercept 10.82 1.97 5.48 28 7.45e-06
Height -0.05 0.03 -1.61 28 1.19e-01
Volume 0.20 0.01 17.82 28 8.22e-17
pg. 12
R = 0.97 R2 = 0.94 F = 222.47 on 2 and 28 DF p-value: 6.5e-18
Total effect estimates (c) (X on Y)
Girth se t df Prob
Intercept -6.19 5.96 -1.04 29 0.30800
Height 0.26 0.08 3.27 29 0.00276
'a' effect estimates (X on M)
Volume se t df Prob
Intercept -87.12 29.27 -2.98 29 0.005830
Height 1.54 0.38 4.02 29 0.000378
'b' effect estimates (M on Y controlling for X)
Girth se t df Prob
Volume 0.2 0.01 17.82 28 8.22e-17
'ab' effect estimates (through mediators)
Girth boot sd lower upper
Height 0.3 0.3 0.08 0.16 0.46
pg. 13
EXP-7
> #exp 7
> #ABA MODRATION ANALYSIS -K.CHATURVEDA
> dt<-trees
> md<-lm(Height~Girth*Volume,data = dt)
> md
Call:
lm(formula = Height ~ Girth * Volume, data = dt)
Coefficients:
(Intercept) Girth Volume Girth:Volume
75.40148 -2.29632 1.86095 -0.05608
> summary(md)
Call:
lm(formula = Height ~ Girth * Volume, data = dt)
Residuals:
-6.7781 -3.5574 -0.1512 2.3631 10.5879
Coefficients:
(Intercept) 75.40148 8.49147 8.880 1.7e-09 ***
Girth -2.29632 1.03601 -2.217 0.035270 *
Volume 1.86095 0.47932 3.882 0.000604 ***
Girth:Volume -0.05608 0.01909 -2.938 0.006689 **
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
pg. 14
pg. 15
EXP 8
> #exp9
> #ABA PRINCIPAL COMPONENT ANALYSIS
> dt<-attitude
> str(dt)
$ rating : num 43 63 71 61 81 43 58 71 72 67 ...
$ complaints: num 51 64 70 63 78 55 67 75 82 61 ...
$ privileges: num 30 51 68 45 56 49 42 50 72 45 ...
$ learning : num 39 54 69 47 66 44 56 55 67 47 ...
$ raises : num 61 63 76 54 71 54 66 70 71 62 ...
$ critical : num 92 73 86 84 83 49 68 66 83 80 ...
$ advance : num 45 47 48 35 47 34 35 41 31 41 ...
> md<-prcomp(rating)
Error in prcomp(rating) : object 'rating' not found
> md<-prcomp(dt)
> md
Standard deviations (1, .., p=7):
[1] 22.798964 11.581920 9.852083 9.232512 6.404264 5.073539
[7] 4.668443
Rotation (n x k) = (7 x 7):
PC1 PC2 PC3 PC4 PC5
rating 0.4467200 0.42184464 -0.2400295 0.1261907 -0.20102006
complaints 0.5206244 0.37207702 -0.1432265 -0.1081087 0.37237853
privileges 0.3757726 -0.07632652 0.6513217 -0.6263275 -0.07783612
learning 0.4209952 -0.14566925 0.1864780 0.4851365 -0.62078169
raises 0.3762536 -0.23339685 -0.2239163 0.1041004 0.44682483
critical 0.1300302 -0.39828981 -0.6330345 -0.5170667 -0.37798712
advance 0.2290738 -0.66592166 0.1095758 0.2579729 0.29490695
PC6 PC7
pg. 16
rating -0.47248738 0.5341317
complaints -0.02200456 -0.6474239
privileges 0.01814123 0.1734231
learning 0.30156007 -0.2347416
raises 0.59329347 0.4374176
critical -0.01806699 -0.1147434
advance -0.57678447 -0.0765914
> install.packages("factoextra")
WARNING: Rtools is required to build R packages but is not currently installed. Please download and
install the appropriate version of Rtools before proceeding:
https://cran.rstudio.com/bin/windows/Rtools/
Installing package into ‘C:/Users/reddy/Documents/R/win-library/4.1’
(as ‘lib’ is unspecified)
also installing the dependencies ‘lazyeval’, ‘carData’, ‘crosstalk’, ‘viridis’, ‘car’, ‘DT’, ‘ellipse’,
‘flashClust’, ‘leaps’, ‘scatterplot3d’, ‘dendextend’, ‘FactoMineR’
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/lazyeval_0.2.2.zip'
Content type 'application/zip' length 173419 bytes (169 KB)
downloaded 169 KB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/carData_3.0-4.zip'
Content type 'application/zip' length 1822339 bytes (1.7 MB)
downloaded 1.7 MB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/crosstalk_1.2.0.zip'
downloaded 400 KB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/viridis_0.6.2.zip'
downloaded 2.9 MB
pg. 17
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/car_3.0-12.zip'
downloaded 1.3 MB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/DT_0.20.zip'
downloaded 1.7 MB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/ellipse_0.4.2.zip'
downloaded 70 KB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/flashClust_1.01-2.zip'
downloaded 36 KB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/leaps_3.1.zip'
downloaded 100 KB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/scatterplot3d_0.3-41.zip'
downloaded 330 KB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/dendextend_1.15.2.zip'
downloaded 3.7 MB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/FactoMineR_2.4.zip'
pg. 18
downloaded 3.6 MB
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.1/factoextra_1.0.7.zip'
downloaded 407 KB
package ‘lazyeval’ successfully unpacked and MD5 sums checked
package ‘carData’ successfully unpacked and MD5 sums checked
package ‘crosstalk’ successfully unpacked and MD5 sums checked
package ‘viridis’ successfully unpacked and MD5 sums checked
package ‘car’ successfully unpacked and MD5 sums checked
package ‘DT’ successfully unpacked and MD5 sums checked
package ‘ellipse’ successfully unpacked and MD5 sums checked
package ‘flashClust’ successfully unpacked and MD5 sums checked
package ‘leaps’ successfully unpacked and MD5 sums checked
package ‘scatterplot3d’ successfully unpacked and MD5 sums checked
package ‘dendextend’ successfully unpacked and MD5 sums checked
package ‘FactoMineR’ successfully unpacked and MD5 sums checked
package ‘factoextra’ successfully unpacked and MD5 sums checked
The downloaded binary packages are in
C:\Users\reddy\AppData\Local\Temp\RtmpsXJTpT\downloaded_packages
> library(factoextra)
Loading required package: ggplot2
Attaching package: ‘ggplot2’
The following objects are masked from ‘package:psych’:
%+%, alpha
pg. 19
Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
Warning message:
package ‘factoextra’ was built under R version 4.1.2
> fviz_eig(md)
pg. 20
EXP 10
> #exp 10
> #ABA CLUSTER ANALYSIS CHATURVEDA
> library(cluster, lib.loc = "C:/Program Files/R/R-4.1.1/library")
> library(NbClust)
> dt<-USArrests
> str(dt)
$ Murder : num 13.2 10 8.1 8.8 9 7.9 3.3 5.9 15.4 17.4 ...
$ Assault : int 236 263 294 190 276 204 110 238 335 211 ...
$ UrbanPop: int 58 48 80 50 91 78 77 72 80 60 ...
$ Rape : num 21.2 44.5 31 19.5 40.6 38.7 11.1 15.8 31.9 25.8 ...
> dt$Assault<-as.numeric(dt$Assault)
> dt$UrbanPop<-as.numeric(dt$UrbanPop)
> str(dt)
$ Murder : num 13.2 10 8.1 8.8 9 7.9 3.3 5.9 15.4 17.4 ...
$ Assault : num 236 263 294 190 276 204 110 238 335 211 ...
$ UrbanPop: num 58 48 80 50 91 78 77 72 80 60 ...
$ Rape : num 21.2 44.5 31 19.5 40.6 38.7 11.1 15.8 31.9 25.8 ...
> NbClust(dt,method = 'complete')
Error in plot.new() : figure margins too large
In addition: Warning message:
In pf(beale, pp, df2) : NaNs produced
> NbClust(dt,method = 'complete')
*** : The Hubert index is a graphical method of determining the number of clusters.
In the plot of Hubert index, we seek a significant knee that corresponds to a
significant increase of the value of the measure i.e the significant peak in Hubert
index second differences plot.
*** : The D index is a graphical method of determining the number of clusters.
pg. 21
In the plot of D index, we seek a significant knee (the significant peak in Dindex
second differences plot) that corresponds to a significant increase of the value of
the measure.
*******************************************************************
* Among all indices:
* 7 proposed 2 as the best number of clusters
***** Conclusion *****
* According to the majority rule, the best number of clusters is 3
*******************************************************************
$All.index
KL CH Hartigan CCC Scott Marriot TrCovW TraceW Friedman Rubin Cindex DB

Silhouette Duda Pseudot2 Beale
2 2.7484 106.9905 62.2745 11.0340 225.9490 2.268713e+15 2035098647 110192.414 87.7922

18.6411 0.3493 0.5764 0.5763 0.3134 70.1152 5.1295
3 12.5168 150.8274 11.3540 9.8880 276.7118 1.849448e+15 313176246 47964.265 119.0856

42.8257 0.3775 0.6366 0.5319 0.5230 12.7699 2.0553
4 0.2839 125.8901 23.9736 8.7049 296.9867 2.191867e+15 171342493 38631.826 148.2522

53.1713 0.4135 0.6356 0.5000 0.3129 39.5217 5.0218
5 2.4327 146.3657 12.8730 9.6776 332.2164 1.692907e+15 70003283 25396.190 209.1949

80.8824 0.4336 0.6313 0.4713 0.3817 19.4368 3.6096
6 2.0103 149.7599 8.0290 9.7387 367.5585 1.202314e+15 37584350 19747.167 257.0256

104.0202 0.4130 0.6859 0.4561 0.6789 5.6766 1.0542
7 2.2030 145.5269 5.0351 9.4186 390.9434 1.025163e+15 31980866 16699.826 293.4762

123.0015 0.4093 0.9055 0.4135 0.6151 5.0060 1.3429
pg. 22
8 0.3533 136.8055 9.0419 8.8535 404.9117 1.012627e+15 24055494 14949.328 308.3085
137.4044 0.4099 1.0192 0.3837 0.3122 13.2186 4.5589
9 1.6765 143.1149 6.3337 9.0249 427.5631 8.147177e+14 13425501 12301.112 420.3586

166.9852 0.4134 0.9307 0.3932 0.3649 6.9626 3.3618
10 0.8074 143.9696 7.5625 8.9161 449.0028 6.550866e+14 9060265 10655.110 511.3989

192.7811 0.4623 0.8379 0.4007 0.1006 26.8341 16.1958
11 3.1807 150.9555 3.5219 9.0915 471.7238 5.031903e+14 6470333 8960.939 719.7569

229.2286 0.4755 0.7076 0.4184 188.9260 0.0000 0.0000
12 0.9683 146.1005 3.4295 8.6998 484.8934 4.601718e+14 5423590 8218.739 739.0346

249.9293 0.5123 0.6310 0.4498 11.4056 -5.4739 -1.8879
13 0.5501 142.4481 5.0238 8.3542 501.5279 3.872205e+14 4491203 7538.402 836.9277

272.4853 0.4954 0.6031 0.4382 0.4683 4.5414 2.1928
14 1.7295 145.6838 3.4164 8.3382 521.9335 2.985981e+14 3958619 6637.208 1032.5740

309.4831 0.5302 0.6426 0.4398 44.1568 -2.9321 -1.7697
15 0.8535 144.2386 3.7724 8.0889 538.6967 2.451377e+14 3664060 6061.935 1320.8021

338.8529 0.5354 0.6232 0.4534 4.2421 -2.2928 -1.3838
Ratkowsky Ball Ptbiserial Frey McClain Dunn Hubert SDindex Dindex SDbw
2 0.3797 55096.2071 0.6979 1.0644 0.3167 0.1533 0 0.0426 40.8403 0.7464
3 0.3849 15988.0885 0.6498 0.6244 0.6320 0.2503 0 0.0395 28.6403 0.3294
4 0.3387 9657.9564 0.6447 1.2331 0.6625 0.2948 0 0.0424 26.2844 0.0736
5 0.3205 5079.2379 0.5736 1.2538 0.8944 0.3438 0 0.0550 20.8217 0.0483
6 0.3072 3291.1945 0.5293 1.0390 1.0648 0.3031 0 0.0729 18.3104 0.0362
7 0.3048 2385.6894 0.4799 1.2690 1.2864 0.2908 0 0.0985 17.0665 0.0353
8 0.2944 1868.6660 0.4480 0.5442 1.4665 0.3107 0 0.1045 16.2498 0.0334
9 0.2795 1366.7902 0.4323 0.5674 1.5339 0.3418 0 0.1027 14.6818 0.0263
10 0.2695 1065.5110 0.4218 0.4409 1.5811 0.4014 0 0.1058 13.7373 0.0229
11 0.2577 814.6308 0.4152 0.4136 1.6009 0.4322 0 0.0971 12.4439 0.0172
12 0.2509 684.8949 0.4141 0.7641 1.6036 0.4519 0 0.0923 11.6733 0.0119
13 0.2436 579.8771 0.4039 0.7303 1.6620 0.4533 0 0.0958 11.0650 0.0107
14 0.2365 474.0863 0.3902 0.6754 1.7431 0.5090 0 0.1135 10.4001 0.0098
15 0.2294 404.1290 0.3840 0.6364 1.7800 0.5266 0 0.1199 9.8584 0.0088
$All.CriticalValues
CritValue_Duda CritValue_PseudoT2 Fvalue_Beale
pg. 23
2 0.4943 32.7341 0.0007
3 0.3357 27.7018 0.0990
4 0.3890 28.2672 0.0013
5 0.3008 27.8883 0.0119
6 0.3008 27.8883 0.3894
7 0.2019 31.6230 0.2756
8 0.1265 41.4361 0.0070
9 0.0160 246.4030 0.0353
10 -0.0628 -50.8045 0.0001
11 -0.5879 0.0000 NaN
12 0.1265 41.4361 1.0000
13 0.0160 246.4030 0.1161
14 -0.0628 -50.8045 1.0000
15 -0.0628 -50.8045 1.0000
$Best.nc
KL CH Hartigan CCC Scott Marriot TrCovW TraceW Friedman Rubin Cindex

DB Silhouette Duda PseudoT2 Beale
Number_clusters 3.0000 11.0000 3.0000 2.000 3.0000 3.000000e+00 3 3.00 15.0000

11.0000 2.0000 2.0000 2.0000 3.000 3.0000 6.0000
Value_Index 12.5168 150.9555 50.9205 11.034 50.7628 7.616833e+14 1721922401 52895.71

288.2281 -15.7469 0.3493 0.5764 0.5763 0.523 12.7699 1.0542
Ratkowsky Ball PtBiserial Frey McClain Dunn Hubert SDindex Dindex SDbw
Number_clusters 3.0000 3.00 2.0000 2.0000 2.0000 15.0000 0 3.0000 0 15.0000
Value_Index 0.3849 39108.12 0.6979 1.0644 0.3167 0.5266 0 0.0395 0 0.0088
$Best.partition
Alabama Alaska Arizona Arkansas California Colorado Connecticut

Delaware Florida Georgia
1 1 1 2 1 2 3 1 1 2
Hawaii Idaho Illinois Indiana Iowa Kansas Kentucky Louisiana

Maine Maryland
3 3 1 3 3 3 3 1 3 1
pg. 24
Massachusetts Michigan Minnesota Mississippi Missouri Montana Nebraska
Nevada New Hampshire New Jersey
2 1 3 1 2 3 3 1 3 2
New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon
Pennsylvania Rhode Island South Carolina
1 1 1 3 3 2 2 3 2 1
South Dakota Tennessee Texas Utah Vermont Virginia Washington West

Virginia Wisconsin Wyoming
3 2 2 3 3 2 2 3 3 2
Warning message:
In pf(beale, pp, df2) : NaNs produced
> md<-kmeans(dt,3)
> clusplot(dt,md$cluster,shade = T)
Warning messages:
1: In doTryCatch(return(expr), name, parentenv, handler) :
display list redraw incomplete
invalid graphics state
pg. 25
display list redraw incomplete
pg. 26
EXP 11
> #exp 11
> #ABA DISCRIMINATE ANALYSIS CHATURVEDA
> library(MASS, lib.loc = "C:/Program Files/R/R-4.1.1/library")
> dt<-USArrests
> head(dt)
Murder Assault UrbanPop Rape
Alabama 13.2 236 58 21.2
Alaska 10.0 263 48 44.5
Arizona 8.1 294 80 31.0
Arkansas 8.8 190 50 19.5
California 9.0 276 91 40.6
Colorado 7.9 204 78 38.7
> md<-lda(Murder~.,data = dt)
> md
Call:
lda(Murder ~ ., data = dt)
Prior probabilities of groups:
0.8 2.1 2.2 2.6 2.7 3.2 3.3 3.4 3.8 4 4.3
0.02 0.04 0.04 0.04 0.02 0.02 0.02 0.02 0.02 0.02 0.02
4.4 4.9 5.3 5.7 5.9 6 6.3 6.6 6.8 7.2 7.3
0.02 0.02 0.02 0.02 0.02 0.04 0.02 0.02 0.02 0.02 0.02
7.4 7.9 8.1 8.5 8.8 9 9.7 10 10.4 11.1 11.3
0.02 0.02 0.02 0.02 0.02 0.04 0.02 0.02 0.02 0.02 0.02
11.4 12.1 12.2 12.7 13 13.2 14.4 15.4 16.1 17.4
0.02 0.02 0.02 0.02 0.02 0.04 0.02 0.04 0.02 0.02
Group means:
Assault UrbanPop Rape
0.8 45.0 44.0 7.30
pg. 27
2.1 70.0 53.5 8.65
2.2 52.0 44.5 11.25
2.6 86.5 60.0 12.50
2.7 72.0 66.0 14.90
3.2 120.0 80.0 22.90
3.3 110.0 77.0 11.10
3.4 174.0 87.0 8.30
3.8 86.0 45.0 12.80
4 145.0 73.0 26.20
4.3 102.0 62.0 16.50
4.4 149.0 85.0 16.30
4.9 159.0 67.0 29.30
5.3 46.0 83.0 20.20
5.7 81.0 39.0 9.30
5.9 238.0 72.0 15.80
6 112.0 59.5 17.20
6.3 106.0 72.0 14.90
6.6 151.0 68.0 20.00
6.8 161.0 60.0 15.60
7.2 113.0 65.0 21.00
7.3 120.0 75.0 21.40
7.4 159.0 89.0 18.80
7.9 204.0 78.0 38.70
8.1 294.0 80.0 31.00
8.5 156.0 63.0 20.70
8.8 190.0 50.0 19.50
9 227.0 80.5 34.40
9.7 109.0 52.0 16.30
10 263.0 48.0 44.50
10.4 249.0 83.0 24.00
11.1 254.0 86.0 26.10
pg. 28
11.3 300.0 67.0 27.80
11.4 285.0 70.0 32.10
12.1 255.0 74.0 35.10
12.2 252.0 81.0 46.00
12.7 201.0 80.0 25.50
13 337.0 45.0 16.10
13.2 212.0 58.5 24.05
14.4 279.0 48.0 22.50
15.4 292.0 73.0 27.05
16.1 259.0 44.0 17.10
17.4 211.0 60.0 25.80
Coefficients of linear discriminants:
LD1 LD2 LD3
Assault 0.02038940 -0.02821854 -0.001846574
UrbanPop 0.04847377 0.03946608 -0.095054873
Rape -0.34985475 0.03364126 0.018963587
Proportion of trace:
LD1 LD2 LD3
0.4704 0.3804 0.1491
> summary(md)
Length Class Mode
prior 43 -none- numeric
counts 43 -none- numeric
means 129 -none- numeric
scaling 9 -none- numeric
lev 43 -none- character
svd 3 -none- numeric
N 1 -none- numeric
call 3 -none- call
terms 3 terms call
xlevels 0 -none- list
pg. 29
> partimat(Murder~.,data =dt)
pg. 30

ABA

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

ABA

Uploaded by

Copyright:

Available Formats

EXP 1

'data.frame': 10 obs. of 4 variables:

$ name: chr "ramu" "raju" "ravi" "vamsi" ...

'data.frame': 10 obs. of 4 variables:

$ name: chr "ramu" "raju" "ravi" "vamsi" ...

$ gd : Factor w/ 2 levels "0","1": 2 2 2 2 1 2 1 2 2 1

'data.frame': 10 obs. of 4 variables:

$ name: chr "ramu" "raju" "ravi" "vamsi" ...

$ gd : Factor w/ 2 levels "0","1": 2 2 2 2 1 2 1 2 2 1

> #ABA-K.CHATURVEDA REDDY

Chi-squared test for given probabilities

[1] 0.4666667 0.3333333 0.2000000

Chi-squared test for given probabilities

Chi-squared test for given probabilities

X-squared = 33.333, df = 2, p-value = 5.778e-08

> #NH:the distribution of observed data is same as expecte

> #AH: the distribution of observed data is not same as expecte

> #ABA-Correlation Analysis -K.Chaturveda reddy

> #multi-variant correlation

corrplot 0.92 loaded

package ‘corrplot’ was built under R version 4.1.2

> corrplot(dt11,method = 'number')

> #ABA-K.CHATURVEDA REDDY

> #simple liner regression

> dt<-lm(mpg~hp,data = mtcars)

lm(formula = mpg ~ hp, data = mtcars)

lm(formula = mpg ~ hp, data = mtcars)

Min 1Q Median 3Q Max

-5.7121 -2.1122 -0.8854 1.5819 8.2360

Estimate Std. Error t value Pr(>|t|)

(Intercept) 30.09886 1.63392 18.421 < 2e-16 ***

hp -0.06823 0.01012 -6.742 1.79e-07 ***

Residual standard error: 3.863 on 30 degrees of freedom

F-statistic: 45.46 on 1 and 30 DF, p-value: 1.788e-07

> #multiple liner regression

> dt<-lm(mpg~.,data = mtcars)

lm(formula = mpg ~ ., data = mtcars)

(Intercept) cyl disp hp drat

12.30337 -0.11144 0.01334 -0.02148 0.78711

-3.71530 0.82104 0.31776 2.52023 0.65541

lm(formula = mpg ~ ., data = mtcars)

Min 1Q Median 3Q Max

-3.4506 -1.6044 -0.1196 1.2193 4.6271

Estimate Std. Error t value Pr(>|t|)

(Intercept) 12.30337 18.71788 0.657 0.5181

cyl -0.11144 1.04502 -0.107 0.9161

hp -0.02148 0.02177 -0.987 0.3350

drat 0.78711 1.63537 0.481 0.6353

wt -3.71530 1.89441 -1.961 0.0633 .

qsec 0.82104 0.73084 1.123 0.2739

vs 0.31776 2.10451 0.151 0.8814

am 2.52023 2.05665 1.225 0.2340

gear 0.65541 1.49326 0.439 0.6652

carb -0.19942 0.82875 -0.241 0.8122

Residual standard error: 2.65 on 21 degrees of freedom

Multiple R-squared: 0.869, Adjusted R-squared: 0.8066

F-statistic: 13.93 on 10 and 21 DF, p-value: 3.793e-07

> #ABA LOGISTIC REGRESSION

> #binomial logistic regression

'data.frame': 32 obs. of 11 variables:

$ cyl : num 6 6 4 6 8 6 8 4 4 6 ...

$ disp: num 160 160 108 258 360 ...

$ hp : num 110 110 93 110 175 105 245 62 95 123 ...

$ wt : num 2.62 2.88 2.32 3.21 3.44 ...