Top Banner
IBS Statistics Year 1 Dr. Ning DING [email protected] I.007
34

Lesson05

Dec 03, 2014

Download

Technology

Ning Ding

Statistics for International Business School, Hanze University of Applied Science, Groningen, The Netherlands
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Lesson05

IBS Statistics Year 1

Dr. Ning DING [email protected]

Page 2: Lesson05

What we are going to learn?

• Review

• Chapter 16: – Define the components of a time series– Compute a moving average– Determine a linear trend equation

Page 3: Lesson05

Chapter 12: Sim Reg & Corr

Exercise

Ŷ = -1.8182 + 0.1329XŶ = -1.8182 + 0.1329X Sample Exam P.4

Page 4: Lesson05

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

a

r2

SD

Ŷ = -1.8182 + 0.1329XŶ = -1.8182 + 0.1329X

98.87%

increase

Page 5: Lesson05

Review Chapter 1

Nominal: gender Ordinal: ranking Interval: temperature, IQ Ratio: age in years

Qualitative:

gender, eye color,

Quantitative:

income, distance

Discrete counting or Continuous measuringDiscrete counting or Continuous measuring

true zero

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 6: Lesson05

Review Chapter 2Bar Chart

Pie Chart

Qualitative DataQualitative Data

Histogram

Polygon

Cumulative Frequency

Distribution

Quantitative DataQuantitative Data

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 7: Lesson05

Review Chapter 3

MeanMean

Median

Ungrouped Data Grouped Data

1 2 2 3 4

(1+2+2+3+4)/5

Classes f 10 up to 20 220 up to 30 130 up to 40 4

2 *15=301 *25=254 *35=140

2 *15=301 *25=254 *35=140

10-<20 220-<30 330-<40 7

L=(N+1)/2(7+1)/2=4

30 40

3 74 5 6

32.5

10-<20 220 -<30 130-<40 4

1957 =24.86ModeMode

Central TendencyCentral Tendency

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 8: Lesson05

Ungrouped Data

1 2 2 3 410 up to 20 220 up to 30 130 up to 40 4

DispersionDispersion

RangeRange

VarianceVariance

Standard DeviationStandard Deviation

4-1=3

Nμ)-Σ(X

=σ2

2

1-n)X-Σ(X

=s2

2

2σ=σ 2s=s

Grouped Data

1957 =24.86

Review Chapter 3

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 9: Lesson05

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

The distribution is skewed to __________because the mean is __________the median.

P42 Example Ch2

the right larger than

Interquartile Range

Mean =23.06

Review Chapter 4

Page 10: Lesson05

Review Chapter 12

Strong & Positivecorrelation

Strong & Negativecorrelation

Moderate & Positivecorrelation

Moderate & Negativecorrelation

Nocorrelation

r = 0.9 r = -0.9 r = 0.6 r = -0.6r = 0

Ŷ = a + bX

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 11: Lesson05

Standard Error

X Axis: Independent Variable

Y A

xis: Dependent V

ariable

r2 = 1 r = -1Standard Error = 0

r2 = 0.24 r = -0.49Standard Error = 2.5

Standard Error

1 2 3 4 5 6 7

7

6

5

4

3.

2

1

Individual values are more scattered from the regression line.

Ŷ = a + bX

Review Chapter 12

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 12: Lesson05

Least Square Regression Equation Ŷ = a + bX

Review Chapter 12

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 13: Lesson05

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Sample Exam P.4

Ŷ = -1.8182 + 0.1329XŶ = -1.8182 + 0.1329X

Page 14: Lesson05

The graph is positive.

There is a strong determination.

r =0.8619 so 86.19% of the variation in Y is explained by the variation in X.

It is a srong positive correlation.

r2=1.05 r = √ 1.05 = 1.025 = $1.025

X

X

X

X

X

Review Chapter 12

•Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 15: Lesson05

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Chapter 16: Time Series & Forecasting

Page 16: Lesson05

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Components of a Time Series

Time series:a collection of data recorded over a period of time (weekly, monthly, quarterly),

an analysis of history, that can be used by management to make current decisions and plans based on long-term forecasting.

– Secular Trend

– Linear– Nonlinear

– Cyclical variation– Rises and Falls over periods longer than one year

– Seasonal variation– Patterns of change within a year, typically repeating themselves

– Residual variation

S

C

S

R

Page 17: Lesson05

Secular Trend:The smooth long-term direction of a time series.

• Review

•Chapter 16: –Define the components of a time series

–Compute a moving average

–Determine a linear trend equation

Components of a Time Series

Page 18: Lesson05

Cyclical Variation:The rise and fall of a time series over periods longer

than one year.

• Review

•Chapter 16: –Define the components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 19: Lesson05

Seasonal Variation:Patterns of change in a time series within a year. These

patterns tend to repeat themselves each year.

• Review

•Chapter 16: –Define the components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 20: Lesson05

Irregular Variation:• Episodic – unpredictable but identifiable• Residual – also called chance fluctuation and

unidentifiable

• Review

•Chapter 16: –Define the components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 21: Lesson05

• Useful in smoothing time series to see its trend

• Basic method used in measuring seasonal fluctuation

Moving Average:

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 22: Lesson05

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

1+2+3+4+5+4+3=22 / 7 = 3.143

Seven-Year Moving Total Moving Average

2+3+4+5+4+3+2=23 / 7 = 3.2863+4+5+4+3+2+3=24 / 7 = 3.429

Page 23: Lesson05

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Moving Average:

Page 24: Lesson05

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 25: Lesson05

Linear TrendThe long term trend of many business series often approximates a straight line

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 26: Lesson05

• Use the least squares method in Simple Linear Regression (Chapter 12) to find the best linear relationship between 2 variables

• Code time (t) and use it as the independent variable

• E.g. let t be 1 for the first year, 2 for the second, and so on (if data are annual)

Ŷ = a + bX Ŷ = a + btŶ = a + bt

Linear Trend

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 27: Lesson05

Linear Trend• Code time (t) and use it as the independent variable• E.g. let t be 1 for the first year, 2 for the second, and

so on (if data are annual)

YearSales

($ mil.)

2005 7

2006 10

2007 9

2008 11

2009 13

Example:The sales of Jensen Foods, a small grocery chain located

in southwest Texas, since 2005 are:

Year tSales

($ mil.)

2005 1 7

2006 2 10

2007 3 9

2008 4 11

2009 5 13

Ŷ = a + btŶ = a + btxn-x

y xn-xy=b

22 a = Y - bX

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 28: Lesson05

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Year tSales

($ mil.)

2005 1 7

2006 2 10

2007 3 9

2008 4 11

2009 5 13

Ŷ = 6.1 + 1.3tŶ = 6.1 + 1.3t9*555

10*3*5163

-

-=b = 1.3

a = 10 -1.3*3 = 6.1

Ŷ = a + btŶ = a + btxn-x

y xn-xy=b

22 a = Y - bX

Linear Trend

Step 1 Step 2

Step 3

Step 4

Step 5

Page 29: Lesson05

Example:The sales of Jensen Foods, a small grocery chain located

in southwest Texas, since 2005 are:

Ŷ = 6.1 + 1.3tŶ = 6.1 + 1.3t

? 2011 ? Ŷ = 6.1 + 1.3*7 = 15.2Ŷ = 6.1 + 1.3*7 = 15.2$ millions

Linear Trend

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 30: Lesson05

• The amounts spent in vending machines in the United States, in billions of dollars, for the years 1999 through 2005 are given below. Determine the least-squares trend equation and estimate vending sales for 2007.

Exercise

P152 N6 Ch16

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Page 31: Lesson05

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

Ŷ = a + btŶ = a + bt

xn-x

y xn-xy=b

22

a = Y - bX

16*7140

67.22*4*71.683

-

-=b = 1.73

a = 22.67 -1.73*4 = 15.75

P152 N6 Ch16

Exercise

Page 32: Lesson05

• Review

•Chapter 16: –Define the

components of a time series

–Compute a moving average

–Determine a linear trend equation

P152 N6 Ch16

Ŷ = 15.75 + 1.73tŶ = 15.75 + 1.73t

16*7140

67.22*4*71.683

-

-=b

= 1.73 a = 22.67 -1.73*4 = 15.75

2006 8 Ŷ2007 9

Ŷ = 15.75 + 1.73*9 = $31.32 billions Ŷ = 15.75 + 1.73*9 = $31.32 billions

Exercise

Page 33: Lesson05

Ŷ = a + btŶ = a + bt xn-x

y xn-xy=b

22

a = Y - bX

P152 N6 Ch16

HintStep 1

Step 2

Step 3

Step 4

Code the year

Calculate X*Y, X2

Step 5

Ŷ = ? + ?*tŶ = ? + ?*t

What is the b?

What is the a?

Formulate the least square equation

Page 34: Lesson05

What we have learnt?

•Review

•Chapter 16: –Define the components of a time series–Compute a moving average–Determine a linear trend equation