ASSIGNMENT FOR WEEK 2

Ravi Nayak (2241973)

University Canada West

Operations Management (OPMT 620) HBD Winter 24-56

Aida Esmaeilidouki

January 23, 2023

2nd Answer:
- Weights are
W1: 0.3
W2: 0.4
W3: 0.3

Period 1: 6 x 0.3 = 1.8

Period 2: 12 x 04 = 4.8 + 1.8 = 6.6
Period 3: 14 x 0.3 = 4.2 + 4.8 + 1.8 = 11.4

Utilizing the given values:

Period 4 Forecast = (0.3 x 14) + (0.4 × 12) + (0.3 x 6)) = 10.8
Period 5 Forecast = ((0.3 × 18) + (0.4 × 14) + (0.3 × 12)) = 14.6
Period 6 Forecast = ((0.3 × 22) + (0.4 × 18) + (0.3 × 14)) = 18
Period 7 Forecast = (0.3 × 25) + (0.4 × 22) + (0.3 × 18)) = 21.7

3rd Answer:
Forecast (t+1) = α × Actual t + (1 – 0.40) Forecast_(t)
Period 1: Actual: 63 Forecast: 60 (initial forecast value)
Period 1:
Actual: 63
Forecast: 60 (initial forecast value)

- Period 2: Actual: 52 Forecast:

0.40 × 63+ (1 − 0.40) × 60 = 25.2 +36= 61.2

- Period 3: Actual: 56 Forecast:

0.40 × 52 + (1 − 0.40) × 61.2 = 20.8 +36.72 = 57.52

- Step 4
Period 4: Actual: 62 Forecast:
0.40 x 56+ (0.40) x 57.52 = 22.4 +34.512=56.912

Period Actual Forecast

1 63 60
2 52 61.2
3 56 57.52
4 62 56.912
4th Answer: Let us calculate the exponential smoothing forecast:

Week Demand Forecast

1 830 830
2 765 830
3 630 784.5
4 640 676.35
5 650.91

Explanation:
At+1 = αAt + (1 - α)Ft

Period 3:
Forecast for period 3 = 0.7 × 765 + (1 - 0.7) × 830
= 784.50
Period 4:
Forecast for period 4 = 0.7 × 630 + (1 - 0.7) × 784.50
= 676.35
Period 5:
Forecast for period 5 = 0.7 × 640 + (1 - 0.7) × 676.35
= 650.91

We get the same forecast value for the second week if we use exponential smoothing
approach or naive approach. We use the naive approach to forecast demand for 2nd week.

5th Answer:
First let's calculate the demand using the trend equation for quarterly 2, where t = 15.
yt = 124 + 7.5t
yt = 124 + 7.5 × 15
yt = 124+ 112.5
yt = 236.5

Now, we will use the seasonal index for quarter 2 (Q2), which is 1.10, to adjust the
demand for seasonality.

Adjusted demand for Q2 = yt × seasonal index

Adjusted demand for Q2 = 236.5 × 1.10
Adjusted demand for Q2 = 260.15

Thus, the predicted demand for the loveseat in quarter 2 is approximately 260 units
6th Answer:
MAD = sum of (A - F) Error/N
= 93/8
MAD=11.63

MSE= sum of Forecast Error^2/N

1,757/8
MSE= 219.63

MAPE = sum of ((Error/actual) * 100)/N

39.21/8
МАРЕ=4.90%

In the given table, the last row indicates the sum of the columns so simply take the value
from that row and divide by 8 to find MAD, MSE and MAPE

For Standard deviation=

First we need to find the average error
E bar = sum of error/N
43/8
= -5.37
 Std dev = (sum of (Forecast Error-E bar)^2/(n-1))^0.5
Std deviation: (1525.88/8 – 1)0.5
= 14.76

7th Answer:
Forecast Error

Months Actual Sales Forecast Demand Forecast Error (Actual-Forecast)

1 215 n/a n/a
2 235 255 -20
3 200 203 -3
4 305 325 -20
5 310 320 -10
For 1 month there is no forecast demand

Square each forecast error to obtain the squared errors

Months Forecast Error (Actual – Forecast) Squared errors
2 -20 400
3 -3 9
4 -20 400
5 -10 100
 Sum Up all forecast errors and squared errors

Sum of Forecast Errors: -20 + ( -3 ) + ( -20 ) + (-10) = -53

The sum of Squared Errors: 400+9+400+100 = 909

MAD = Sum of Forecast Errors/Number of Data Points

= -53/5
MAD= -10.6

MSE= Sum of Squared Errors/Number of Data Points

= 909/5
MSE= 181.8

By Control Chart we can identify any patterns that may require adjustments in the
forecasting process to improve accuracy.

8th Answer:

Week Number
1 232
2 250
3 270
4 262
5 320
6 352
7 375
8 385
9 420
10 465
11 485
12 498
13 520
14 555
 Chart Title
600

f(x) = 25.7604395604396 x + 191.725274725275

500

400

300

200

100

0
0 2 4 6 8 10 12 14 16

SUMMARY OUTPUT

Regression Statistics
Multiple R 0.993598
R Square 0.987236
Adjusted R
Square 0.986172
Standard
Error 12.75367
Observations 14

ANOVA
Significanc
df SS MS F eF
Regression 1 150969.1 150969.1 928.1491 9.81E-13
Residual 12 1951.873 162.656
Total 13 152920.9

Coefficient Standard Upper Lower Upper

s Error t Stat P-value Lower 95% 95% 95.0% 95.0%
Intercept 191.7253 7.199684 26.62968 4.82E-12 176.0385 207.412 176.0385 207.412
X Variable 1 25.76044 0.84556 30.46554 9.81E-13 23.91812 27.60276 23.91812 27.60276

Prediction for Week 15 and 16

The equation we have
regression line equation is Y = 25.76x +191.73

Week 15
Y = 191.73 x 15 + 25.76
 = 2,875 + 25.760
= 2,901.71

Week 16
Y= 191.73 x 16 +25.76
= 3067.68 + 25.76
= 3093.44

9th Answer:
Explanation:
Option C )Simple linear regression analysis assumes that predictions have to simplest be
made within the variety of determined values of the predictor variable. This way that the
relationship between the predictor variable and the reaction variable is believed to be
linear and valid most effective inside the range of statistics that changed into used to
create the regression model. Extrapolating past this variety may additionally result in
unreliable predictions due to the fact the model's assumptions may additionally now not
keep actual.
Incorrect options:
A)
This choice is wrong due to the fact easy linear regression objectives to decrease the sum
of squared deviations (also called residuals) of the facts points from the regression line,
no longer maximize them.
B)
This alternative is wrong because the assumptions of easy linear regression encompass
the assumption that the deviations across the regression line are normally distributed.
This assumption is important for undertaking speculation assessments and building
confidence intervals.
D)
This option is incorrect because simple linear regression assumes that predictions should
simplest be made within the range of found values of the predictor variable, as cited in
the right option. Extrapolating beyond this range is not dependable.
This choice is wrong because simple linear regression assumes that variations around the
regression line are random and observe an everyday distribution. This assumption is
crucial for making legitimate inferences and undertaking statistical tests.

10th Answer:
a) True
b) False
c) False