+ All Categories
Home > Documents > Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

Date post: 22-Dec-2015
Category:
Upload: erica-obrien
View: 212 times
Download: 0 times
Share this document with a friend
Popular Tags:
27
Quantitative Business Methods for Decision Making Estimation and Estimation and Testing of Testing of Hypotheses Hypotheses
Transcript
Page 1: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

Quantitative Business Methods for Decision Making

Estimation and Estimation and Testing of Testing of

HypothesesHypotheses

Page 2: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 2

Lecture OutlinesLecture Outlines

Estimation Confidence interval for estimating

means Confidence interval for predicting a

new observation Confidence interval for estimating

proportions

Page 3: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 3

Lecture Outlines (con’t)Lecture Outlines (con’t)

Hypothesis Testing Null and alternative hypotheses Decision rules (Tests) and their level of

significance Type I and Type II errors Tests of hypotheses for comparing

means Tests of hypotheses for comparing

proportions

Page 4: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 4

Estimating a Population MeanEstimating a Population Mean

Population mean is estimated by , the sample mean

Standard error of , i.e.

will decrease as n gets large.

x

n

ss

x

x

Page 5: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 5

Confidence Interval for Confidence Interval for Estimating if is Estimating if is

knownknown

With a 95% degree of confidence is estimated within ( )

written as Or more accurately

by

nx

x2

X

x2X

x2

X

x96.1 X

Page 6: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 6

Confidence Interval for if Confidence Interval for if is not known is not known

Use instead of ,

remember , and

“t” is 95th% percentile of the t distribution with (n-1) degrees of

freedom.

x96.1 x

xtsx

nx

n

s

xs

Page 7: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 7

An IllustrationAn Illustration

Suppose n= 26. Then degrees of freedom (d.f.) = n-1 = 25.

A two-sided degree of C.I. is computed

by But, for a one-sided 95% C.I. , t = 1.711

instead of 2.064

%95

x2.064sx

Page 8: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 8

Assumptions and Sample Size Assumptions and Sample Size forfor

Estimation of the meanEstimation of the mean

The population should be normally (at least close to) distributed. If skew, then median is an appropriate measure of the center than themean.To estimate mean with a specified margin oferror (m.e.), take a random sample of size n

large size. 2

22

..em

zn

Page 9: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 9

Prediction Interval for a Prediction Interval for a New Observation on XNew Observation on X

n

11ts x

Prediction Interval for a new observation is given by

Page 10: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 10

Confidence Interval for a Confidence Interval for a Population ProportionPopulation Proportion

Let denote the proportion of items in a

population having a certain propertyAn estimate of is the binomial proportion: , What is ?

For a C.I. for , use

ptsp

n

Xp

X

Page 11: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 11

Confidence Intervals for Confidence Intervals for the Proportion (con’t)the Proportion (con’t)

For estimating ,“t” is the percentile of the

t-distribution with (equivalently, percentile of the standard normal distribution), and s.e. of p is

df

n

pp )1(sp

Page 12: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 12

Hypotheses Testing Hypotheses Testing

The hypothesis testing is a methodology for proving or disproving researcher’s prior

beliefs. Statements that express prior beliefs are framed as alternative hypotheses. Complementary statement to an alternative hypothesis is called null hypothesis.

Page 13: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 13

Null and AlternativeNull and Alternative

Ha: Researcher’s belief that are to be tested (alternate hypothesis)

H0: Complement of Ha (Null hypothesis)

Page 14: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 14

Statistical Decision

A decision will be either: Reject H0 (Ha is proved)

orDo not reject H0 (Ha is not proved)

Page 15: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 15

Hypothesis Testing Methodology Hypothesis Testing Methodology for the meanfor the mean

Depending upon what an investigator believes a priori, an alternative hypothesis is formulated to be one of the followings:1.

2.

3.

0a :H

0a :H

0a :H

one-sided

Page 16: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 16

A Test StatisticA Test Statistic

Regardless of what an alternative hypothesis

about the mean is formulated, the decision

rule is defined by a t- statistic:

x

0

S

Xt

Page 17: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 17

Decision Rules for Testing Decision Rules for Testing Hypotheses About the MeanHypotheses About the Mean

Hypotheses Decision Rule

1. Ho: = o At level of significance, reject Ho in favor of Ha if

Ha: o either t-statistic 2t or -

2t

2. Ho: o At level of significance, reject Ho in favor of Ha if

Ha: o t-statistic t

3. Ho: o At level of significance, reject Ho in favor of Ha if

Ha: o t-statistic -t

Page 18: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 18

Type I and Type II ErrorsType I and Type II ErrorsDecision taken is

Accept H0 Accept H1

----------------------------------------------------------------------- Suppose correct Type I Error H0 is true decision (wrong decision)------------------------------------------------------------------------ Suppose Type II Error correct H1 is true (wrong decision) decision

Type I error : reject H0 if H0 is true.

Type II error : Do not reject H0 when H0 is false.

Page 19: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 19

Comparing Two MeansComparing Two Means

The reference number is a specified amount for comparing the

difference between two means. There are two distinct practical

situations resulting in samples on X and Y.

X population Y population X ,

X Y , Y

Consider

1. H0: X - Y = 2. H0: X - Y 3. H0: X - Y

Ha: X - Y , Ha: X - Y , Ha: X - Y .

Page 20: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 20

Two Sampling Designs Two Sampling Designs

•Paired Sample•Two independent Samples

Page 21: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 21

Paired SamplePaired Sample Two variables X and Y are observed for

each unit in the sample to measure the same aspect but under two different conditions.

Thus, for n randomly selected units, a sample of n pairs (X, Y) is observed.

Compute differences: X1-Y1= d1, X2-Y2= d2, etc. and then mean

Compute Sd of differences

dd

Page 22: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 22

Paired Samples (con’t)Paired Samples (con’t)

Compute

t-statistic:

dS

d statistic-t

n

sdd

S

Page 23: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 23

Paired Samples (con’t)Paired Samples (con’t)

•Reject H0 if absolute value of t-statistic is more than the desired percentile of the t-distribution.

•Alternatively, find the p value of the t-statistics and reject H0 if the p value is less than the desired significance level.

Page 24: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 24

Two Independent Two Independent (Unpaired) Samples(Unpaired) Samples

Populations of variables X and Y (for example, males salary X and females salary Y). Take samples independently on X and

Y. Compute Compute pooled standard deviation

yx S,Y,S,X

2

S1S1nS

21

2y2

2x1

nn

n

Page 25: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 25

Unpaired Samples Unpaired Samples (con’t)(con’t)

Compute

Finally, compute t-statistic=

Use p value to reach a decision

21

x n

1

n

1SSX of SE

yY

y

xS

YX

Page 26: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 26

Comparing ProportionsComparing Proportions

To estimate in a 95% C.I., compute,

21

2

22

1

1121

1196.1

n

pp

n

pppp

21 and

Page 27: Quantitative Business Methods for Decision Making Estimation and Testing of Hypotheses.

403.6 27

Comparing Two Comparing Two ProportionsProportions

For testing hypothesis about the difference , compute

and

t-statistic=

21

n

pnpnpnnn 2211

21 ,

n

pp

pp

)1(21


Recommended