In: Statistics and Probability
The CIO of an IT company would like to investigate how a software developer’s work experience (in number of years), professional certifications (number of certificates), and knowledge of various computer languages (number of programming languages) contribute to his/her work performance. The work performance is measured on the scale of 1 to 1000 so that the higher one’s score, the better his/her work performance. He collects data from 20 software developers in his company Years of experience Num of certificates Num of progLang Performance
Years of expiernce , number of certificates , number of prolong, performance
1 27 3 8 880
2 11 1 2 686
3 6 2 1 681
4 21 3 4 877
5 26 3 4 975
6 21 3 4 902
7 18 3 3 900
8 15 1 5 882
9 14 2 3 200
10 5 1 3 650
11 17 2 5 908
12 14 2 4 687
13 15 3 4 891
14 7 2 3 566
15 5 3 1 959
16 13 2 5 793
17 11 1 4 778
18 31 3 7 975
19 16 2 5 846
20 12 2 6 779.
Using the pivot table on this data what is the standard deviation for the performance of software developers who have. obtained 2 to certificates and know 3 programming languages?
a 117.4
b 67.3
c 56.9
d 258.80
we would like to create a regression model that would describe how performance depends on work experience, professional , certifications, and knowledge of varies computer languages.
what is the respond (or dependent) variable in this regression model
a performance
b employee id
c knowledge of computer languages
d work experience
e professional certifications
What is the value of r-squared of this regression model?
a .28
b .53
c .45
d .76
e .37
Ans : a. 0.28
>
exp<-c(27,11,6,21,26,21,18,15,14,5,17,14,15,7,5,13,11,31,16,12)
> cert<-c(3,1,2,3,3,3,3,1,2,1,2,2,3,2,3,2,1,3,2,2)
> prolan<-c(8,2,1,4,4,4,3,5,3,3,5,4,4,3,1,5,4,7,5,6)
>
perfo<-c(880,686,681,877,975,902,900,882,200,650,908,687,891,566,959,793,778,975,846,779)
> dmat1<-cbind(exp,cert,prolan)
> mod1<-lm(perfo~dmat1)
> mod1
Call:
lm(formula = perfo ~ dmat1)
Coefficients:
(Intercept) dmat1exp dmat1cert dmat1prolan
490.170 3.862 78.903 16.815
> summary(mod1)
Call:
lm(formula = perfo ~ dmat1)
Residuals:
Min 1Q Median 3Q Max
-552.49 -9.27 18.97 59.99 196.00
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 490.170 143.128 3.425 0.00347 **
dmat1exp 3.862 9.811 0.394 0.69904
dmat1cert 78.903 66.548 1.186 0.25307
dmat1prolan 16.815 33.554 0.501 0.62311
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 167.9 on 16 degrees of freedom
Multiple R-squared: 0.2778, Adjusted
R-squared: 0.1424
F-statistic: 2.052 on 3 and 16 DF, p-value: 0.1471
So, we get r-squared value = 0.28