Data Mining Assignment

The analyst wants to determine if there is a pattern in the Price Company's quarterly earnings per share from 2016 to 2019. The data is provided in a table. The document asks to forecast the quarterly earnings using four naive models and evaluate the forecasts using mean squared error to determine the best model. Naive models 1, 2 and 3 are outlined and calculations provided to forecast earnings and calculate the mean squared error for each model.

Uploaded by

Musa Khan

Available Formats

Download as DOCX, PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

28 views

Data Mining Assignment

Uploaded by

Musa Khan

Available Formats

Download as DOCX, PDF, TXT or read online on Scribd

You are on page 1/ 4

Lahore School of Economics

BSc III
Time Series Analysis and Forecasting Spring 2021

Name:Aneeza Shabbir_ Section:_______________

Date:______________ Score:________________

Assignment No.4

An analyst would like to determine whether there is a pattern to earnings per share for the Price
Company, which operates a wholesale/retail cash-and-carry business in several states under the
name Price Club. The data are shown in the following table.

Quarterly Earnings per Share for the Price Company: 2016-

2019

Calendar 1st 2nd 3rd 4th

2016 .86 .51 .47 .63
2017 .94 .56 .50 .65
2018 .95 .42 .57 .60
2019 .93 .38 .37 .57

a. Find the forecast values of the quarterly earnings per share of the Price Club for each
quarter using the following naïve models:

i. Y^ t +1=Y t
ii.
Y^ t +1=Y t +(Y t −Y t −1)

Y^ t +1=Y t ( )
Yt
Y t−1
iii. ^
Y t +1=Y t −3
( Y t −Y t −4 )
iv. Y^ t +1=Y t −3+
4

b. Evaluate these forecasts using MSE. Which one is the best?

Ans:
(a) (i)

Y^ t +1=Y t

Year quarter t Yt Ŷt+1 e=Yt-Ŷ e^2

2016 1 1 0.86
2 2 0.51 0.86 -0.35 0.123
3 3 0.47 0.51 -0.04 0.002
4 4 0.63 0.47 0.16 0.026
2017 1 5 0.94 0.63 0.31 0.096
2 6 0.56 0.94 -0.38 0.144
3 7 0.5 0.56 -0.06 0.004
4 8 0.65 0.5 0.15 0.023
2018 1 9 0.95 0.65 0.3 0.090
2 10 0.42 0.95 -0.53 0.281
3 11 0.57 0.42 0.15 0.023
4 12 0.6 0.57 0.03 0.001
2019 1 13 0.93 0.6 0.33 0.109
2 14 0.38 0.93 -0.55 0.303
3 15 0.37 0.38 -0.01 0.000
4 16 0.57 0.37 0.2 0.040
sum 1.262
MSE 0.084
(ii)

Y^ t +1=Y t +(Y t −Y t −1)

Year quarter t Yt Ŷt+1 e=Yt-Ŷ e^2

2016 1 1 0.86
2 2 0.51
3 3 0.47 0.16 0.31 0.096
4 4 0.63 0.43 0.2 0.040
2017 1 5 0.94 0.79 0.15 0.023
2 6 0.56 1.25 -0.69 0.476
3 7 0.5 0.18 0.32 0.102
4 8 0.65 0.44 0.21 0.044
2018 1 9 0.95 0.8 0.15 0.023
2 10 0.42 1.25 -0.83 0.689
3 11 0.57 -0.11 0.68 0.462
4 12 0.6 0.72 -0.12 0.014
2019 1 13 0.93 0.63 0.3 0.090
2 14 0.38 1.26 -0.88 0.774
3 15 0.37 -0.17 0.54 0.292
4 16 0.57 0.36 0.21 0.044
sum 3.170
MSE 0.226
Y^ t +1=Y t
( )
Yt
Y t−1

Year quarter t Yt Ŷt+1 e=Yt-Ŷ e^2

2016 1 1 0.86
2 2 0.51
3 3 0.47 0.30 0.17 0.028
4 4 0.63 0.43 0.20 0.039
2017 1 5 0.94 0.84 0.10 0.009
2 6 0.56 1.40 -0.84 0.710
3 7 0.5 0.33 0.17 0.028
4 8 0.65 0.45 0.20 0.041
2018 1 9 0.95 0.85 0.11 0.011
2 10 0.42 1.39 -0.97 0.938
3 11 0.57 0.19 0.38 0.148
4 12 0.6 0.77 -0.17 0.030
2019 1 13 0.93 0.63 0.30 0.089
2 14 0.38 1.44 -1.06 1.127
3 15 0.37 0.16 0.21 0.046
4 16 0.57 0.36 0.21 0.044
sum 3.288
MSE 0.235