You are on page 1of 10

TIARA RANTIKA SARI

20170410370
IMABS
Number 3 page 143

1. Analysis of paired samples statistics


Based on the output we can see the summary of the statistic showed that the selling before bonus
and the selling after bonus. The average selling before bonus is 21.150 and the average selling
after bonus is 20.761
2. Analysis of paired samples correlation
Based on the output part we can see the correlation between the two variables. The correlation
number that is shown is 0.955 with significant level that is low and far below the required level
of significance 5%
It shows that the correlation between the selling before bonus and the selling after bonus is very
tight and significant

3. Analysis of paired samples correlation


Hypothesis
Ho : µ before ≥ µ after : The average of selling before bonus is more than the average of selling
after bonus
Ha : µ before ≤ µ after : The average of selling before bonus is less than the average of selling
after bonus

Based on the result of test seems the level of significant/probability that is shown is very low
(0,000), low below the required level of significance 5%. The decision that we take is H o rejected
and it means the average of selling before bonus is less than the average of selling after bonus.

Number 4 page 143

Hypothesis :
Ho = μ1 = μ2 = μ3: there is no difference in average productivity between the three
machines
Ha = one or more machines have different productivity averages with other machines
1. Anaylisis of descriptive

This output shows the descriptive statistic of the three samples. For example, one average
production machine is 49.00 units per day, minimum 46 units and maximum 53 units.
The average two-machine production is 56.00 units per day product, minimum 52 units
and maximum 61 units. the average production machine is 51.00 units per day, minimum
49 units and maximum 54 units.

2. Analysis test of homogeneity of variances


This analysis aims to test whether or not the assumption anova is whether the variance of
the three samples is the same
Criteria used:
If the probability> 0.05 receive Ho (the third variance of the identic population)
If the probability <0.05 reject Ho (the third variance of different populations)
Since the probability is 0.286> 0.05 then Ho is accepted, means the variance of all three
samples is equal

3. Analysis of ANOVA
After the third variance of the sample is the same, anova test is performed to determine
whether the three samples have the same mean.
Hypothesis:
Ho = μ1 = μ2 = μ3: there is no difference in average productivity between the three
machines
Ha = one or more machines have different productivity averages with other machines
To decide it can be seen from F arithmetic 8.298 compared with F table or by comparing
the probability of 0.005 with a significant level of 0.05. Based on the probability
significance of 0.005 less than 0.05 is significant. From these results can be concluded
that there are differences in productivity between the three machines.
4. Anaylisis of post hoc test
Post hoc tests show which machines are different and which machines are no different
from using the tukey test and bonferroni test.
For example we use the first line of tukey-HSD test results that test the difference of
machine 1 and machine 2
The mean difference value (group average 1-group average) is indicated at -7000 range
of mean differences ranging from -2.28 to -11.72.
The significance test of the mean difference can be seen from the significance of the
mean difference. For the first row because the probability is 0.005 <0.05 means
significant means the productivity of machine 1 with machine 2 is significantly different.
Further significance significance test results can be easily done by observing the presence
or absence of a * sign. The * indicates that the probability of difference between the two
machines is significant.
5. Analysis of Homogeneous Subsets
In contrast to the Tukey and Bonferoni tests, Homogeneous Subsets are used to find
which machines have significantly different mean differences. The test results show that
the three machines are divided into two subsets. Subset 1 shows only the 1 machine
coming in, this means that machine 1 is different from other machines. Subset 2 shows
that the group containing machines 2 and 3. This shows machines 2 and 3 do not differ
significantly. This can be compared by looking at the mean of the machine at the output
in the first and the test results of Tukey and Bonferoni. Tukey and Bonferoni test results
with Homogeneous Subsets always complement each other.

Number 2 Page 180


1. Analysize of paired samples statistics
Based on output it seems that summary of the statistic showed that toefl test score before
following course and toefl test score after following course. The average toefl test score before
following course is 410,11 and The average toefl test score after following course is 439,89.

2. Analysize of paired samples correlation


Based the output part seems the correlation between the two variables. The correlation number
that is shown is 0.293 with significant level that is low and far below the required level of
significance 5%.
It shows that the correlation between that toefl test score before following course and
toefl test score after following course is very tight and significant
3. Analysize of paired samples correlation
Hypothesis
Ho : µ before ≥ µ after : The average toefl test score before following course is
more than The average toefl test score after following course
Ha : µ before ≤ µ after : The average toefl test score before following course is
less than The average toefl test score after following course
Based on the result of test seems the level of significant/probability that is shown is very low
(0,006) , low below the required level of significance 5%. The decision that we take is Ho is
rejected and it means the The average toefl test score before following course is less than The
average toefl test score after following course.
Number 1 page 282
1. Analysis of variables entered
Base on the model, Employee performance is dependent variable and the organization
culture, the leader style, motivation is independent variable

2. Analysis of Model Summary


The number of R is 0,436 or 43,6% show that 43,6% of the employee performance can be
explained by the variable of organization’s culture, leadership style,motivation.
Standart Error of Estimated (SEE) is 2,364. The lower the SEE will make the regreation
model more accurate to predict dependent variable.

3. Analysis ANOVA
Based on the ANOVA tast or F Test is obteined F as 5,411 with significant level 0,006. It
means the probability (0,003) is lower compared significant level as 0,05. It can be said
that the orgaisation’s culture, leadership style, motivation effect on employee
performance

4. Analysis Coefficients

The regression equation is


Y = 10,840 + 0,116x1 + 0,122x2 + 0,462x3
Explanation
Y = employee’s performance
X1 = leadership style
X2 = motivation
X3 = organizational culture
The constant value of 10,840 state that if X=0 then each value of 10,480 coefficient
regression. Coefficient 0.116 states that any increase (+) leadership style of 1 then it will
raise employee performance of 0.116.
Regression coefficient 0,112 states that every increase (+) motivation equal to 1 hence
will raise employee performance equal to 0,112.
The regression coefficient 0,462 states that every increase (+) organizational culture
equal to 1 hence will raise employee performance equal to 0,462.
For T test to test the significance of constants and dependent variable (employee performance)

Hypothesis
Ho : There is no significant effect between independent variable to Dependent
variable
Ha : There is significant effect between independent variable to dependent variable

Base on thr probability then


If the probability is> 0.05 then Ho is acceptable
If the probability <0,05 then H¬o is rejected

The Decition

3 variabel x

X1 = leadership style
Ho: there is no influence between leadership style towards employee performance
Ha : there is influence between leadership style towards employee performance
It is seen that the significance column for leadership style is 0,558 or the probability is
bigger than the significant level that is set that is 0,05 then leadership does not influence
significantly to employee performance so Ho accepted and Ha rejected

X2 = motivation
Ho: there is no influence between motivation towards employee performance
Ha : there is influence between motivation towards employee performance
It is seen that the significance column for leadership style is 0.480 or the probability is
smaller than the significance level that is set is 0,05 then the motivation has significant
effect to employee performance so Ho is rejected and Ha accepted

X3= organizational culture


Ho: there is no influence between organizational culture towards employee performance
Ha : there is influence between organizational culture towards employee performance
It is seen that the significance column for leadership style is 0.019 or the probability is
smaller than the significance level that set 0,05 then organizational culture significantly
influence to employee performance so Ho is rejected and Ha accepted

You might also like