Scribd
Upload
4 views

1.Time SeriesForecasting (1)

The document discusses time series forecasting, explaining various patterns such as horizontal, trend, seasonal, and cyclical patterns that can be identified in time series data. It provides a practical example of forecasting using Mean Squared Error (MSE) calculations with two methods: the naive method using the most recent value and the average of all available data. The conclusion indicates that using the average provides a better forecast due to a lower MSE.

Uploaded by

amishav2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

1.Time SeriesForecasting (1)

The document discusses time series forecasting, explaining various patterns such as horizontal, trend, seasonal, and cyclical patterns that can be identified in time series data. It provides a practical example of forecasting using Mean Squared Error (MSE) calculations with two methods: the naive method using the most recent value and the average of all available data. The conclusion indicates that using the average provides a better forecast due to a lower MSE.

Uploaded by

amishav2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

HDSC 601 Statistical Learning for Data Science DBIT, KURLA

DON BOSCO INSTITUTE OF TECHNOLOGY


(Engineering College)
Statistical Learning for Data Science
Module 6 : Time series Forecasting
a time series is a sequence of observations on a variable measured at successive points
in time or over successive periods of time. the measurements may be taken every hour,
day, week, month, or year, or at any other regular interval. 1 the pattern of the data
is an important factor in understanding how the time series has behaved in the past. if
such behavior can be expected to continue in the future, we can use the past pattern
to guide us in selecting an appropriate forecasting method. to identify the underlying
pattern in the data, a useful first step is to construct a time series plot. a time series plot
is a graphical presentation of the relationship between time and the time series variable;
time is on the horizontal axis and the time series values are shown on the vertical axis.
let us review some of the common types of data patterns that can be identified when
examining a time series plot.

Horizontal Pattern
A horizontal pattern exists when the data fluctuate around a constant mean.

The term stationary time series is used to denote a time series whose statistical
properties are independent of time.

Trend pattern
Although time series data generally exhibit random fluctuations, a time series may also
show gradual shifts or movements to relatively higher or lower values over a longer period
of time. if a time series plot exhibits this type of behavior, we say that a trend pattern
exists.
A trend is usually the result of long-term factors such as population increases or de-
creases, changing demographic characteristics of the population, technology, and/or con-
sumer preferences.

Seasonal Patterns
the trend of a time series can be identified by analyzing multiyear movements in histor-
ical data. Seasonal patterns are recognized by seeing the same repeating patterns over
successive periods of time.
For example, a manufacturer of swimming pools expects low sales activity in the fall and
winter months, with peak sales in the spring and summer months.

Manufacturers of snow removal equipment and heavy clothing, however, expect just
the opposite yearly pattern.
The pattern for a time series plot that exhibits a repeating pattern over a one-year pe-
riod due to seasonal influences is called a seasonal pattern. While we generally think of
seasonal movement in a time series as occurring within one year, time series data can
also exhibit seasonal patterns of less than one year in duration. For example, daily traffic
volume shows within-the-day “seasonal” behavior, with peak levels occurring during rush
hours, moderate flow during the rest of the day and early evening, and light flow from
midnight to early morning.

Revathy S Jan 2023 1


DBIT, KURLA HDSC 601 Statistical Learning for Data Science

Cyclical pattern
A cyclical pattern exists if the time series plot shows an alternating sequence of points
below and above the trend line lasting more than one year.
Many economic time series exhibit cyclical behavior with regular runs of observations
below and above the trend line. often, the cyclical component of a time series is due
to multiyear business cycles. For ex- ample, periods of moderate inflation followed by
periods of rapid inflation can lead to time series that alternate below and above a generally
increasing trend line (e.g., a time series for housing costs).

Forecasting

Consider the following time series data.

Month 1 2 3 4 5 6 7

Value 24 13 20 12 19 23 15
(i) Compute MSE (Mean Squared error) using the most recent value as the forecast for
the next period. ((naive method)What is the forecast for month 8?
(ii) Compute MSE using the average of all the data available as the forecast for the next
period. What is the forecast for month 8?
(iii) Which method appears to provide the better forecast

Solution: (i) MSE Computation using the most recent value:

Month Value Forecast Error Squared


Value Error

1 24
2 13 24 -11 121
3 20 13 7 49
4 12 20 -8 64
5 19 12 7 49
6 23 19 4 16
7 15 23 -8 64
Total = 363
363
Hence MSE (Mean Squared error) is = = 60.5
6
The forecast for Week 8 is = 15, the value of week 7.
(ii) MSE Computation using average of all the data available:

2 Revathy S Jan 2023


HDSC 601 Statistical Learning for Data Science DBIT, KURLA

Month Value Forecast Error Squared


Value Error

1 24
2 13 24 -11 121
24 + 13
3 20 = 18.5 1.5 2.25
2
24 + 13 + 20
4 12 = 19 -7 49
3
24 + 13 + 20 + 12
5 19 = 17.25 1.75 3.0625
4
24 + 13 + 20 + 12 + 19
6 23 = 17.6 5.4 29.16
5
24 + 13 + 20 + 12 + 19 + 23
7 15 = 18.5 -3.5 12.25
6
Total = 216.7225
216.7225
Hence MSE (Mean Squared error) is = = 36.12
6
24 + 13 + 20 + 12 + 19 + 23 + 15 126
The forecast for Week 8 is = = = 18, the average
7 7
of the values upto week 7.
(iii) For this problem, MSE Computation using average of all the data available appears
to provide the better forecast as the MSE is less in this case, in comparison.

Revathy S Jan 2023 3

You might also like