DSIMGTS

Time Series Analysis and Forecasting

Introduction
•Forecasting methods can be classified as qualitative or quantitative
•Qualitative methods generally involve the use of expert judgment to develop forecasts
•Quantitative forecasting methods can be used when:
•Past information about the variable being forecast is available
•The information can be quantified
•It is reasonable to assume that past is prologue

Time Series Patterns

•Time series: 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, year, or any other regular
interval. The pattern of the data is important to understand the series’ past behavior
•If the behavior of the time series data of the past is expected to continue in the future, we can
use it to guide us in selecting an appropriate forecasting method

Horizontal Pattern
•Exists when the data fluctuate randomly around a constant mean
over time
•Stationary time series: denotes a time series whose statistical
properties are independent of time
•The process generating the data has a constant mean
•The variability of the time series is constant over time
•A time series plot for a stationary time series will always exhibit a
horizontal pattern with random fluctuations

Trend Pattern
•A trend pattern is gradual shifts or movements to relatively
higher or lower values over a longer period of time
•A trend is usually the result of long-term factors such as:
 •Population increases or decreases
•Shifting demographic characteristics of the population
•Improving technology
•Changes in the competitive landscape
•Changes in consumer preferences

Seasonal Pattern
•Seasonal patterns are recurring patterns over successive periods of time
•Time series plot not only exhibits a seasonal pattern over a one-year
period but also for less than one year in duration

Trend and Seasonal Pattern

•Some time series include both a trend and a seasonal pattern

Cyclical Pattern
•A cyclical pattern exists if the time series plot shows an alternating sequence of points below
and above the trendline that lasts for more than one year
•Cyclical effects are often combined with long-term trend effects and referred to as trend-cycle
effects

Forecast Accuracy
•Naïve forecasting method: Using the most recent data to predict future data
•The key concept associated with measuring forecast accuracy is forecast error
•Measures to determine how well a par[cular forecasting method is able to reproduce the time
series data that are already available
•Forecast error = Difference between the actual and forecasted values for period t.

•Mean forecast error = Mean of the

forecasted errors
 •Mean absolute error (MAE) = Measure of forecast accuracy that avoids the problem of
positive and negative forecast errors offsetting one another.

•Mean squared error (MSE) = measure that avoids the problem of positive and negative
errors offsetting each other is obtained by computing the average of the squared
forecast errors.

•Mean absolute percentage error (MAPE) = Average of the absolute value of percentage
forecast errors.

Moving Averages
•Moving averages method: Uses the average of the most recent k data values in the time
series as the forecast for the next period

Exponential Smoothing
•Exponential smoothing uses a weighted average of past time series
values as a forecast
•Smoothing constant (α )is the weight given to the actual value in period
t; weight given to the forecast in period t is 1 –α.
- Forecast Accuracy
•If the time series contains substantial random variability, a small value of
the smoothing constant is preferred and vice-versa
•Choose the value of “a” that minimizes the MSE
Using Regression Analysis for Forecasting
Linear Trend Projection
•Regression analysis can be used to forecast a time series with a linear trend
•Simple linear regression analysis yields the linear relationship between the independent
variable and the dependent variable that minimizes the MSE
•Use this approach to find a best-fitting line to a set of data that exhibit a linear trend
•The variable to be forecasted (y, the actual value of the time series period t) is the dependent
variable
•Trend variable (time period t) is the independent variable

•Equation for the trendline:

Seasonality Without Trend

•We can model a time series with a seasonal pattern by treating the season as a dummy
variable

Seasonality with Trend

•The time series contains both seasonal effects and a linear trend
•The time series plot corresponding to this data indicates that there is both linear trend and
seasonal pattern

Using Regression Analysis as a Causal Forecasting Method

•The relationship of the variable to be forecast with other variables may also be used to develop
a forecasting model
•Advertising expenditures when sales is to be forecast
•The mortgage rate when new housing construction is to be forecast

•Causal models: Models that include only variables that are believed to cause
changes in the variable to be forecast
The barometric method is based on the approach of developing an index of relevant economic
indicators and forecasting the future trends by analyzing the movements in these indicators.

1. Leading Series: The leading series is comprised of indicators which move up or down
ahead of some other series
2. Coincidental Series: The coincidental series include indicators which move up and
down simultaneously with the general level of economic activities.
3. Lagging Series: A series consisting of those indicators, which after some time-lag
follows the change.

Linear Regression
Introduction
•Managerial decisions are often based on the relationship between two or more variables
•Sometimes a manager will rely on intuition to judge how two variables are related
•If data can be obtained, a statistical procedure called regression analysis can be used to develop
an equation showing how the variables are related

•Dependent variable or response: Variable being predicted

•Independent variables or predictor variables: Variables being used to predict the value of the
dependent variable
•Linear regression: A regression analysis involving one independent variable and one
dependent variable
•Simple linear regression: A regression analysis for which any one unit change in the
independent variable, x, is assumed to result in the same change in the dependent variable, y
•Multiple linear regression: Regression analysis involving two or more independent variables
The Simple Linear Regression Model
Regression Model
•The equation that describes how y is related to x and an error term
•Parameters: The characteristics of the population, β0 and β1
•Random variable: Error term, ε
•The error term accounts for the variability in y that cannot be explained by the linear
relationship between x and y
•The parameter values are usually not known and must be estimated using sample data
Least Squares Method
•Least squares method: A procedure for using sample data to find the estimated regression
equation
•Determine the values of b0and b1
•Interpretation of b0 and b1:
•The slope b1 is the estimated change in the mean of the dependent variable y that is
associated with a one unit increase in the independent variable x
•The y-intercept b0 is the estimated value of the dependent variable y when the
independent variable x is equal to 0
•Residual: The error made using the regression model to estimate the mean value of
the dependent variable for the ith observation
•We are finding the regression that minimizes the sum of squared errors
•Experimental region: The range of values of the independent variables in the data
used to estimate the model
•The regression model is valid only over this region
•Extrapolation: Prediction of the value of the dependent variable outside the
experimental region
•It is risky
Integer Linear Optimization Models
Introduction
•Integer linear programs: Problems that are modeled as linear programs with the additional
requirement that one or more variables must be integer
•The objective is to provide an applications-oriented introduction to integer linear programming

Types of Integer Linear Optimization Models

•All-integer linear program:If all variables are required to be integer
•Mixed-integer linear program:If some, but not necessarily all, variables are required to be
integer
•Binary integer linear program: The integer variables may take on only the values 0 or 1
•LP Relaxation (linear programming relaxation) of the integer linear program: The linear
program that results from dropping the integer requirements
•The region bounded by the dashed lines is known as the convex hull of the set of feasible
integer solutions
Applications Involving Binary Variables
Capital Budgeting
•Capital budgeting problem: A binary integer programming problem that involves choosing
which possible projects or activities provide the best investment return
•In a capital budgeting problem, the objective function is to maximize the net present value of
the capital budgeting projects

•In many applications, the cost of production has two components:

•A setup cost, which is a fixed cost
•A variable cost, which is directly related to the production quantity

•Fixed-cost problem:A binary mixed-integer programming problem in which the binary

variables represent whether an activity, such as a production run, is undertaken (variable = 1) or
not (variable = 0)
•Location problem:A binary integer programming problem in which the objective is to select
the best locations to meet a stated objective
•Variations of this problem are known as covering problems

Spreadsheet Models
Introduction
•Spreadsheet models are mathematical and logic-based models
•Referred to as what-if models
•Total cost of manufacturing a product is the sum of two costs:
•Fixed cost: Portion of the total cost that does not depend on the production quantity and
remains the same no matter how much is produced
•Variable cost: Portion of the total cost that is dependent on and
varies with the production quantity

•Make-versus-buy decision: comparing the costs of manufacturing in-

house to the costs of outsourcing production to another firm
Influence Diagrams
•An influence diagram is a visual representation that shows which entities influence others in a
model

What-If Analysis
Data Tables
•Data Table: Excel tool which quantifies the impact of changing the value of a specific input on
an output of interest
•One-way data table: summarizes a single input’s impact on the output
•Two-way data table:summarizes two inputs’ impact on the output

Goal Seek
•Goal Seek: Excel tool that allows the user to determine the value of an input cell that will cause
the value of a related output cell to equal some specified value (the goal)

SUM and SUMPRODUCT

•SUM: Function that adds up all of the numbers in a range of cells
•SUMPRODUCT: Function that returns the sum of the products of elements in a set of arrays

IF and COUNTIF
• =IF(condition, result if condition is true, result if condition is false)
• =COUNTIF(range, condition)•Counts the number of components having a positive order
quantity

VLOOKUP
•This function allows the user to pull a subset of data from a larger table of data based on some
criterion
•General form =VLOOKUP(value, table, index, range)

Auditing Spreadsheet Models

•Excel contains a variety of tools to assist you in the development and debugging of
spreadsheet models
•These tools are found in the Formula Auditing group of the Formulas Tab

Trace Precedents and Dependents

•Trace Precedents button: After selecting cells, this button creates arrows pointing to the
selected cell from cells that are part of the formula in that cell
•Trace Dependents button: Shows arrows pointing from the selected cell to cells that depend on
the selected cell

Show Formulas
•To see the formulas in a worksheet, simply click on any cell in the worksheet and then click on
Show Formulas—you will see the formulas residing in that worksheet
•To revert to hiding the formulas, click again on the Show Formulas button
Evaluate Formulas
•The Evaluate Formulas button allows you to investigate the calculations of a cell in great detail
•Provides an excellent means of identifying the exact location of an error in a formula

Error Checking
•The Error Checking button provides an automatic means of checking for mathematical errors
within formulas of a worksheet
•Clicking on the Error Checking button causes Excel to check every formula in the sheet for
calculation errors
•If an error is found, the Error Checking dialog box appears

Watch Window
•The Watch Window, located in the Formula Auditing group, allows the user to observe the
values of cells included in the Watch Window box list
•Useful for large models when not all of the model is observable on the screen or when multiple
worksheets are used

Linear Optimization Models

Introduction
•Optimization problems:
 •Can be used to support and improve managerial decision making
•Maximize or minimize some function, called the objective function, and have a set of
restrictions known as constraints
•Can be linear or nonlinear
•Linear optimization models are also known as linear programs
•Linear programming:
•A problem-solving approach developed to help managers make better decisions
•Numerous applications in today’s competitive business environment

A Simple Maximization Problem

•Problem formulation or modeling: Process of translating the verbal statement of a problem
into a mathematical statement (or model)
•Describe the objective
•Describe each constraint
•Define the decision variables
•This is a linear programming model (or linear program) because the objective function and all
constraint functions are linear functions of the decision variables
•Linear function: Mathematical function in which each variable appears in a separate term and
is raised to the first power
•To find the optimal solution to the problem is modeled as a linear program:
•The optimal solution must have the highest objective function value
•The optimal solution must be a feasible solution—a setting of the decision variables
that satisfies all of the constraints of the problem
•Search over the feasible region—a set of all possible solutions
•Find the solution that gives the best objective function value
• Extreme points of the feasible region are the optimal solution
•Extreme points are found where constraints intersect on the boundary of the feasible region
•A binding constraint is one that holds as an equality at the optimal solution
•The slack value for each less-than-or-equal-to constraint indicates the difference between the
left-hand and right-hand values for a constraint
•By adding a nonnegative slack variable, we can make the constraint equality
•A surplus variable tells how much over the right-hand side the left-hand side of a greater-
than-or-equal-to constraint is for a solution

Sensitivity Analysis
•Sensitivity analysis: The study of how the changes in the input parameters of an optimization
model affect the optimal solution
•The shadow price for a constraint is the change in the optimal objective function value if the
right-hand side of that constraint is increased by one
 DSIMGTS
TEST YOURSELF
A. IDENTIFICATION

1. a variable used to categorize observations of data -- used when modeling a time series with a
seasonal pattern
2. exists if the time series plot shows an alternating sequence of points below and above the
trend line lasting more than one year
3. the variable that is being predicted or explained in a regression analysis exponential
smoothing
4. a forecasting method that uses a weighted average of past time series values as the forecast
5. the difference between the actual time series value and the forecast
6. a variable used to predict or explain values of the dependent variable in regression analysis
7. the average of the absolute values of the forecast errors
8. the average of the sum of squared forecast errors
9. a forecasting method that uses the average of the (k) most recent data values in the time
series as the forecast for the next period
10. a procedure for estimating values of a dependent variable given the values of one or more
independent variables in a manner that minimizes the sum of the squared errors
11. an equation or formula that simplifies reality and helps us to understand underlying patterns
and relationships
12. an equation of a straight line through the data
13. the relationship between two quantitative variables
14. the predicted value
15. the difference between the observed value and its associated predicted value
16. how far off the model's prediction is at that point
17. a sequence of observations on a variable measured at successive points in time or over
successive periods of time
18. a procedure for using sample data to find the estimated regression equation
19. one that holds as an equality at the optimal solution
20. comparing the costs of manufacturing in-house to the costs of outsourcing production to
another firm
ANSWER KEY
1. CATEGORICAL VARIABLE
2. CYCLICAL PATTERN
3. DEPENDENT VARIABLE
4. EXPONENTIAL SMOOTHING
5. FORECAST ERROR
6. INDEPENDENT VARIABLE
7. MEAN ABSOLUTE ERROR
8. MEAN SQUARED ERROR
9. MOVING AVERAGES
10. REGRESSION ANALYSIS
11. MODEL
12. LINEAR MODEL
13. LINEAR REGRESSION
14. Y-HAT
15. RESIDUAL
16. RESIDUAL VALUE
17. TIME SERIES
18. LEAST SQUARES METHOD
19. BINDING CONSTRAINT
20. MAKE-VERSUS-BUY DECISION