1.

Class intervals: different between upper-class limit and lower-class limit.

Class intervals= 4

(Example: 19-15=4)

2.

Age Frequency
15-19 6
20-24 16
25-29 9
30-34 1
35-39 10
40-44 4
45-49 0
50-54 3
55-59 0
60-64 1

3.

Positive skewness. The graph is skewed to right.

Histogram
18
16
14
12
Frequency

10
8
6
4
2
0
15-19 20-24 25-29 30-34 35-39 40-44 45-49 50-54 55-59 60-64
Age

4.
 Mean Median Mode
Month 1085 18.5 5
=21.7
50
Age 1494 27 24
=29.88
50
Hours/week 1361 25 42
=27.22
50
Blip 496.45 10.105 10.32
=9.929
50

5 (a)

Sample Variance, S² (Data from Excel) = 4.8904

∑ ( x )2
2
∑x −
Sample Variance, S² (calculation) = n
n−1

( 496.45 )2
5168.88−
= 50
50−1
= 4.8904

x̄ −µ
2
Test statistic (t)= s
√( )
n
9.929−9.5
= 4.8904
√( )
50
0.429
=
0.3127
= 1.372

H₀: µ= 9.5 H₁: µ≠ 9.5

P=p(t¿ -1.372) P=p(t¿ 1.372)

P value: (1-0.9147)= 0.0853

= 0.0853 x 2= 0.1706
Since the P value is 0.1706, which greater than the significant level of 95% (0.05), the test is not
significant and we cannot reject the null hypothesis.

Hence, the trade unions claim that the number of items processed average 9.5 minutes can be
accepted.

5 (b)

H₀: µ= 10 H₁: µ¿ 10

Sample Variance, S²: 4.8904

x̄ −µ
2
Test Statistic (t): s
√( )
n
9.929−10
= 4.8904
√( )
50
−0.071
=
0.3127
= -0.2271

P= p(t←0.2271)

P value: 1- 0.5910= 0.409

Since the P value is 0.409, which greater than the significant level of 95% (0.025), the test is not
significant and we cannot reject the null hypothesis.

Hence, the supermarket state that the target of an average of 10 items per minute is not being
achieved can be accepted.

6 (a)

SUMMARY OUTPUT

Regression Statistics
Multiple R 0.71742204
R Square 0.51469439
Adjusted R Square 0.48304402
Standard Error 1.58999897
Observations 50
 ANOVA
  df SS MS F Significanc
eF
Regression 3 123.334801 41.11160034 16.261878 2.4139E-07
Residual 46 116.292449 2.528096717
Total 49 239.62725      

  Coefficient Standard t Stat P-value Lower 95% Upper 95% Lower Upper
s Error 95.0% 95.0%
Intercept 8.2263026 0.8557000 9.613535493 1.404E-12 6.5038677 9.9487374 6.5038677 9.9487374
1 3 8 3 8 3
X Variable 1 0.0784443 0.0135741 5.778944467 6.2027E-07 0.0511209 0.1057677 0.0511209 0.1057677
6 7 8 4 8 4
X Variable 2 0.0165910 0.0235788 0.703639881 0.4852036 -0.0308708 0.0640528 -0.0308708 0.0640528
3 7 8 4 4
X Variable 3 -0.0181956 0.0162141 -1.122210172 0.2675967 -0.050833 0.0144416 -0.050833 0.0144416
1 3 7 7

y= 8.2263+ 0.017x₁+ 0.078x₂- 0.018x₃

6 (b)

r² is the coefficient of determination.

It measures the proportion of change in one variable that is explained by variations in the value of
the other variable.

The data will lie more closely to the least square line when the value is nearer to 1.

In this case, the value of the coefficient of determination is 0.5147. This means that there are
approximately 51.47% of the variation in y (blips) can be explained by x (age, month of work and
hours per week) during two hours test.

6 (c)(i)

H₀: β₁= 0 H₁: β₁≠0

Test statistic (t)= 0.7036

P= p (t¿ -0.7036) P= p (t¿ 0.7036)

P value: 1-0.758= 0.242

0.242 x2= 0.484

Since the P value is 0.484, which greater than the significant level of 95% (0.05), the test is not
significant and we cannot reject the null hypothesis.

Hence, the result shows that the age is not a significant variable when the confidence level is 95%.

When the significant value of 99% (0.01) occurred, the test is still not significant and we still cannot
reject the null hypothesis because of the P value still greater than the significant level of 99%.

Hence, the result shows that the age is not a significant variable when the confidence level is 99%.

6 (c)(ii)

H₀: β₂= 0 H₁: β₂≠ 0

Test statistic (t)= 5.7789

P value: 0.00000062

Since the P value is 0.00000062, which smaller than the significant level of 95% (0.05), the test is
significant and we can reject the null hypothesis.

Hence, the result shows that the month of work is a significant variable when the confidence level is
95%.

When the significant value of 99% (0.01) occurred, the test is still significant and we still can reject
the null hypothesis because of the P value still smaller than the significant level of 99%.

Hence, the result shows that the month of work is a significant variable when the confidence level is
99%.

6 (c)(iii)

H₀: β₃= 0 H₁: β₃≠ 0

Test statistic (t)= -1.1222

P= p (t¿ -1.1222) P= p (t¿ 1.1222)

P value: 1-0.8686= 0.1314

0.1314 x2= 0.2628

Since the P value is 0.2628, which greater than the significant level of 95% (0.05), the test is not
significant and we cannot reject the null hypothesis.

Hence, the result shows that the hours per week is not a significant variable when the confidence
level is 95%.
When the significant value of 99% (0.01) occurred, the test is still not significant and we still cannot
reject the null hypothesis because of the P value still greater than the significant level of 99%.

Hence, the result shows that the hours per week is not a significant variable when the confidence
level is 99%.

6 (c)(iv)

β₀ is an interception point between the dependent variable (blips) and the independent variable
(age, month of work and hours per week). This interception point help to predict the value of the
dependent variable when all the independent variable are equal to 0.

H₀: β₀= 0 H₁: β₀≠ 0

Test statistic (t)= 9.6135

P value: 1.404 x 10−12

Since the P value is 1.404 x 10−12, which lower than the significant level of 95% (0.05), the test is
significant and we can reject the null hypothesis.

Hence, the result shows that the interception point is a significant variable when the confidence
level is 95%.

When the significant value of 99% (0.01) occurred, the test is still significant and we still can reject
the null hypothesis because of the P value still lower than the significant level of 99%.

Hence, the result shows that the interception point is a significant variable when the confidence
level is 99%.

7 (a)

The independent variable that is not significant at 95% meaning that the P-value of the independent
value is greater than the significant level at 95% (0.05).

Based on the data provided, all the data are insignificant at 95% (0.05), which are the age (p-value=
0.484) and the hours per week (p-value= 0.2628) except the month of work. It is because the P-value
of the month of work is 0.00000062, which is smaller than the significant level at 95% (0.05).

7 (b)
Based on the data provided, we can drop two insignificant variables, which are the age and the
hours per week. We keep the month of work as the significant variable and use it to re-estimate the
equation.

SUMMARY OUTPUT

Regression Statistics
Multiple R 0.70386092
R Square 0.4954202
Adjusted R Square 0.48490812
Standard Error 1.58712968
Observations 50

ANOVA
  df SS MS F Significan
ce F
Regressi 1 118.71617 118.7161 47.128 1.1842E-
on 99 8 6594 08
Residual 48 120.91107 2.518980
01 63
Total 49 239.62725      

  Coefficie Standard t Stat P- Lower Upper Lower Upper

nts Error value 95% 95% 95.0% 95.0%
Intercept 8.093481 0.3490952 23.18416 1.0137 7.391578 8.7953 7.3915 8.7953
45 6 31 E-27 39 8452 7839 8452
X 0.084586 0.0123212 6.865031 1.1842 0.059812 0.1093 0.0598 0.1093
Variable 11 99 64 E-08 48 5974 1248 5974
1

Based on the data given, the re-estimated equation that dropping the insignificant variables (the age
and the hours/week) is:

y= 8.0935+ 0.0846x₁

Where y= blips, x₁= the month of work

7 (c)

The value of R² now decreased from 0.5146 to 0.4954, which decreased around 1.92%. This shows
that the drop in insignificant variables decreased the fitness of the data to the least square line, the
relationship between x and y become weaker. Approximate only 49.54% of y can be explained by x,
which harder to predict the value between the blips and the month of work relationship.