chapter – 4 volatility of aggregate market...

109

CHAPTER – 4

VOLATILITY OF AGGREGATE MARKET INDICES

Introduction

During the last decade the world financial market experienced a rapid growth

of emerging stock markets. Studies related to these markets show that equities from

emerging stock markets have different characteristics than equities from developed

stock markets. Four distinguishing features of emerging market returns are higher

sample average return, low correlations with developed market returns, more

predictable returns and higher volatility. Because of the current international status

and growth rate of emerging markets, many researchers focus on the volatility of

these markets. For example, Choudhry (1996) studies volatility, risk premia and the

persistence of volatility in six emerging markets; Argantina, Greece, India, Mexico,

Thailand and Zimbabwe, before and after the 1987 stock market crash. Santis and

Imrohoroglu (1997) study the dynamics of expected stock returns and volatility in

emerging financial markets. They find clustering, predictability and persistence in

conditional volatility in these markets. Bekaert and Harvey (1997) analyze the reasons

that volatility is different across emerging markets, particularly with respect to the

timing of capital market reforms. They find that capital market liberalizations often

increase the correlation between local market returns and the world market but do not

drive up local market volatility. More recently Aggarwal, Inclan and Leal (1999)

examine global and local events that cause large shifts in the volatility of emerging

stock markets.

Different statistical models such as the rolling standard deviations, parametric

ARCH or stochastic-volatility models have been used in these studies. In this chapter,

traditional method of volatility estimation by computing the monthly standard

deviations based on daily return observation to analyze the time-varying volatility of

aggregate market indices of Indian Stock Exchange is applied. The objective is to

determine whether Indian Stock Exchange is characterized by high volatility. It is to

examine when large changes in the volatility of Indian Stock Exchange returns occur

and what events (political, social, and economic) took place around the period of

increased volatility.

110

4.1 DATA AND VOLATILITY MEASUREMENT

The behavior of stock volatility is analyzed using eleven daily aggregate indices:

• BSE500,

• BSE200,

• BSE100,

• SENSEX,

• Consumer Durable Sector Index (CD),

• Consumer Goods Sector Index (CG),

• Auto Sector Index,

• FMCG Sector,

• Healthcare Sector Index,

• IT sector Stocks, Metal Sector and

• Oil and Gas Sector Index.

SENSEX is composed of 30 companies and it is the main index of the Indian

Stock Exchange others indices are the sector indices of Indian Stock Exchange. The

data is obtained from the Capitaline database and Bombay stock Exchange. The data

for period January 3, 2000 to December 30, 2009 is used. Throughout this paper,

stock market returns are defined as continuously compounded returns at time t

calculated as the natural log difference in the closing market index between two dates.

French, Schwert and Stambaugh (1987) and Schwert (1989) method is used to

calculate monthly standard deviation of stock return as a measure of volatility. To

estimate the monthly standard deviation of stock returns using the daily returns to

Eleven market indices. The estimator of the variance of the monthly return is the sum

of the squared daily returns after subtracting the average daily return in the month:

Formula

∑−

−

=1

1`~

2

1

2 1 tN

iit

tt r

Nσ

111

Where there are Nt daily returns rit in month t. Using non-overlapping samples

of daily data to estimate the monthly variance creates estimation error that is

uncorrelated through time.

4.2 GRAPHICAL ANALYSIS ON BEHAVIOR OF AGGREGATE MARKET

INDICES

Figure 4.1:

Volatility of Sensex Index (Monthly: January 2001 – December 2000)

0.00

1.00

2.00

3.00

4.00

5.00

6.00

Jan‐00

Jun‐00

Nov‐00

Apr‐01

Sep‐01

Feb‐02

Jul‐0

2

Dec‐02

May‐03

Oct‐03

Mar‐04

Aug

‐04

Jan‐05

Jun‐05

Nov‐05

Apr‐06

Sep‐06

Feb‐07

Jul‐0

7

Dec‐07

May‐08

Oct‐08

Mar‐09

Aug

‐09

Sensex

112

Figure 4.2:

Volatility of BSE 200 Index (Monthly: January 2001 – December 2000)

Figure 4.3:

Volatility of BSE 500 index (Monthly: January 2001 – December 2000)

0.00

1.00

2.00

3.00

4.00

5.00

6.00

Jan‐00

Jul‐0

0

Jan‐01

Jul‐0

1

Jan‐02

Jul‐0

2

Jan‐03

Jul‐0

3

Jan‐04

Jul‐0

4

Jan‐05

Jul‐0

5

Jan‐06

Jul‐0

6

Jan‐07

Jul‐0

7

Jan‐08

Jul‐0

8

Jan‐09

Jul‐0

9

BSE 200

0.00

1.00

2.00

3.00

4.00

5.00

6.00

Jan‐00

Jul‐0

0

Jan‐01

Jul‐0

1

Jan‐02

Jul‐0

2

Jan‐03

Jul‐0

3

Jan‐04

Jul‐0

4

Jan‐05

Jul‐0

5

Jan‐06

Jul‐0

6

Jan‐07

Jul‐0

7

Jan‐08

Jul‐0

8

Jan‐09

Jul‐0

9

BSE 500

113

Figure 4.4 :

Volatility of BSE 100 index (Monthly: January 2001 – December 2000)

Figure 4.5:

Volatility of Auto Sector Index (Monthly: January 2000 – December 2009)

0.00

1.00

2.00

3.00

4.00

5.00

6.00

Jan‐00

Jun‐00

Nov‐00

Apr‐01

Sep‐01

Feb‐02

Jul‐0

2

Dec‐02

May‐03

Oct‐03

Mar‐04

Aug

‐04

Jan‐05

Jun‐05

Nov‐05

Apr‐06

Sep‐06

Feb‐07

Jul‐0

7

Dec‐07

May‐08

Oct‐08

Mar‐09

Aug

‐09

BSE 100

0.00

0.50

1.00

1.50

2.00

2.50

3.00

3.50

4.00

4.50

5.00

Jan‐00

Jun‐00

Nov‐00

Apr‐01

Sep‐01

Feb‐02

Jul‐0

2

Dec‐02

May‐03

Oct‐03

Mar‐04

Aug

‐04

Jan‐05

Jun‐05

Nov‐05

Apr‐06

Sep‐06

Feb‐07

Jul‐0

7

Dec‐07

May‐08

Oct‐08

Mar‐09

Aug

‐09

Auto

114

Figure 4.6:

Volatility of Consumer Durable Sector Index (Monthly: January 2000 –

December 2009)

Figure 4.7:

Volatility of Consumer Goods Sector Index

(Monthly: January 2000 – December 2009)

0.00

1.00

2.00

3.00

4.00

5.00

6.00

7.00

Jan‐00

Jul‐0

0

Jan‐01

Jul‐0

1

Jan‐02

Jul‐0

2

Jan‐03

Jul‐0

3

Jan‐04

Jul‐0

4

Jan‐05

Jul‐0

5

Jan‐06

Jul‐0

6

Jan‐07

Jul‐0

7

Jan‐08

Jul‐0

8

Jan‐09

Jul‐0

9

Consumer Durables

0.00

1.00

2.00

3.00

4.00

5.00

6.00

Jan‐00

Jul‐0

0

Jan‐01

Jul‐0

1

Jan‐02

Jul‐0

2

Jan‐03

Jul‐0

3

Jan‐04

Jul‐0

4

Jan‐05

Jul‐0

5

Jan‐06

Jul‐0

6

Jan‐07

Jul‐0

7

Jan‐08

Jul‐0

8

Jan‐09

Jul‐0

9

Consumer Goods

115

Figure 4.8:

Volatility of FMCG Sector Index (Monthly: January 2000 – December 2009)

Figure 4.9:

Volatility of Health Care Sector Index


0.00

0.50

1.00

1.50

2.00

2.50

3.00

3.50

4.00FMCG

0.00

0.50

1.00

1.50

2.00

2.50

3.00

3.50

4.00 Health Care

116

Figure 4.10:

Volatility of Metal Sector Index (Monthly: January 2000 – December 2009)

Figure 4.11:

Volatility of Oil & Gas Sector Index


0.00

1.00

2.00

3.00

4.00

5.00

6.00

7.00

8.00

Jan‐00

Jun‐00

Nov‐00

Apr‐01

Sep‐01

Feb‐02

Jul‐0

2

Dec‐02

May‐03

Oct‐03

Mar‐04

Aug

‐04

Jan‐05

Jun‐05

Nov‐05

Apr‐06

Sep‐06

Feb‐07

Jul‐0

7

Dec‐07

May‐08

Oct‐08

Mar‐09

Aug

‐09

Metal

0.00

1.00

2.00

3.00

4.00

5.00

6.00

7.00Oil & Gas

117

4.3 INTERPRETATION

In figure 5.1 to 5.11 plots the volatility of various Market Index and Sector

indices. All plots appear to capture important political and economic events of India.

First consider the volatility of Market index. Figure 5.1 - Figure 5.4 shows a huge

spike in January 2000 as well as higher levels of volatility in March 2004, May 2006

and between January 2007 - May 2009. In general, Figure 5.1 – Figure 5.4 shows an

upward trend in volatility. The average of monthly standard deviation for the period

January 2000- December 2009 is as follows

Table 4.1:

Average Volatility (Monthly: January 2001 – December 2000)

Sensex BSE

100

BSE

200

BSE

500

Auto

Sector

Consumer

Durables

Consumer

Goods FMCG

Health

Care Metal

Oil

&

Gas

1.59 1.62 1.60 1.57 1.56 1.93 1.81 1.45 1.31 2.20 1.88

The increased volatility during 2000 - 2001 was due to dot com bust.

Beginning of year 2000, the market was bolstered by a positive investment

environment supported by the IMF-backed disinflation program, with 5.6% GDP

increase year-to- year, high confidence due to financial sector reforms, new license

policy, FEMA, FERA and a decline in interest rates and inflation. Positive news

included a new law snowing international arbitration between the government and

foreign investors, and new measures to prevent insider trading. Despite these reforms,

investor confidence declined and share prices plunged because of political turmoil.

After a period of robust global growth and favorable economic conditions in

2006, global financial markets entered a turbulent phase because of the subprime

crisis which started in mid-2007. Non-performing housing loans, declining global

equity prices and the rising cost of default protection on corporate bonds forced some

major banks in the US incurred losses. Alongside, the tightening of banking credit

standards in major industrial economies has reinforced worries of an impending credit

crunch. The impact has been compounded by the volatility in international food and

118

oil prices. These effects have impacted global economic growth in the current year as

well as next.

The increased FII flows till 2007-08 reversed its trend in 2008-09. The

judgment about excess volatility of capital flows will depend not merely on the

quantity of the flow, but to some extent on the quality in terms of components of the

capital flow i.e., whether capital flows are of enduring nature or temporary. Strategic

management of the capital account would warrant preparedness for all situations.

The financial crisis has also started directly affecting Indian Industries. For the

past few years, the two most preferred method of raising money by the companies

were Stock Markets and external borrowings (ECB) on low interest rates. Stock

Markets are bleeding everyday and it is not possible to raise money there. Regarding

external borrowing from world markets, this option has also become difficult. In the

last fiscal year alone, India borrowed $29 billion from foreign lenders and attracted

$34 billion of foreign direct investment. A global recession has hurt external demand.

International lenders who have become extremely risk aversive can limit access to

international capital. If that happens, both India’s financial markets and the real

economy will be hurt in the process.

One positive point in favor of India is the fact that Indian Banks were more or

less insulated from the ill-effects of sub-prime crises. A glance at Indian banks’

balance sheets would show that their exposure to complex instruments like CDOs is

almost nil. In India, major banking operations are with the Public Sector Banks who

exercise extreme cautions in disbursing loans to needy people/companies. Though

there have been a presence of big US/European Banks in India and even some Indian

banks (like ICICI) have some foreign subsidiary’s with effluent in the sub-prime

losses, its effect is miniscule as compare to the overall size of Indian banking

industry. However, a global depression is likely to result in a fall in demand and

adversely Indian Exports. In 2007-08, India sold 13.5% of its goods to foreign buyers.

A fall in demand is likely to affect the growth rate this year.

Lack of business optimism, shortage of cash, fall in demands, decline in

growth rate and uncertainties in the market are some of the most visible aspects of an

119

economic depression. What started as a small matter of sub-prime loan defaulters has

now become a subject of global discussion and has engulfed the global economic

scenario.

Indian companies have major outsourcing deals from the US. India's exports to

the US have also grown substantially over the years. The India economy has lost

between 1 to 2 percentage points in GDP growth due to crash. Indian companies with

big tickets deals in the US have seen their profit margins shrinking. The worries for

exporters were rupee strengthens further against the dollar. But experts note that the

long-term prospects for India as stable. A weak dollar could bring more foreign

money to Indian markets. Oil may get cheaper brining down inflation. A recession

could bring down oil prices to $70.

The whole of Asia would be hit by a recession as it depends on the US

economy. Even though domestic demand and diversification of trade in the Asian

region will partly counter any drop in the US demand, many economies simply can't

escape a downturn in the world's largest economy. The US economy accounts for 30

per cent of the world's GDP. The US recession had a dual impact on the outsourcing

industry. Appreciating rupee along with poor performance of US companies (law

firms, investment banks and media houses) affect the bottom line of the outsourcing

industry. Small BPOs, which are operating at a net margin of 7-8 percent, have found

it difficult to survive.

The US economy contracts much more than anticipated, the whole world's

GDP growth-which is estimated at 3.7 per cent by the IMF-will contract, and India

would be no exception. IT and IT-enabled services, textiles, jewellery, handicrafts and

leather segments suffered losses because of their trade link. The IT sector was the

worst hit as 75 per cent of its revenues come from the US. Low demand for services

forced most Indian Fortune 500 companies to slash their IT budgets.

US companies in health care, financial services and all consumers demand

driven firms had to cut down on their spending. Among other sectors, manufacturing

and financial institutions are moderately vulnerable. The service sector took a serious

120

hit; India had to revise its GDP to about 8 to 8.5 per cent or even less. Recession

seriously affects the portfolio and fixed investment flows.

4.4 RESULTS AND DISCUSSION ON CYCLICAL BEHVIOUR OF

AGGREGATE MARKET INDICES

This section discusses the result of the data analysis keeping in view the

objective of the study. The main focus is to investigate the level of long – run

relationship and the integration that exists between market index and sector based

indices. The statistical and econometric methods applied to investigate are follows:

• Descriptive Statistics of daily returns.

• Correlation Test

• Unit root test

• Johansen Co-integration Analysis (Bilateral and Multilateral) and

Dickey fuller test

• Granger Causality Test

121

Table - 4.2:

Descriptive Statistics of Daily Prices of Market Index and Sector Indices

Indices AUTO Return

BSE 100

Return

BSE 200 Return

BSE 500 Return

CD Return

CG Return

FMCG Return

HC Return

IT Return

Metal Return

Oil Return

Sensex Return

Mean 0.08 0.06 0.07 0.07 0.06 0.12 0.05 0.04 0.06 0.12 0.10 0.06

Median 0.14 0.19 0.19 0.21 0.11 0.16 0.05 0.10 0.05 0.18 0.12 0.14

Maximum 11.21 16.75 16.31 15.74 13.29 21.90 8.76 8.06 15.61 16.10 19.11 17.34

Minimum -10.43 -11.25 -11.87 -11.70 -11.01 -14.58 -10.55 -8.31 -19.99 -13.30 -14.97 -11.14

Std. Dev. 1.70 1.84 1.81 1.79 2.14 2.06 1.58 1.46 2.64 2.46 2.10 1.79

Skewness -0.27 -0.15 -0.25 -0.32 -0.14 0.22 -0.04 -0.36 -0.08 -0.21 -0.10 0.02

Kurtosis 6.04 8.65 8.84 8.68 6.71 11.07 6.47 7.19 8.46 6.61 10.15 9.40

Jarque-Bera 989.79 3323.51 3572.74 3394.52 1441.83 6793.95 1249.91 1879.91 2978.58 1375.08 5314.48 4253.98

Sum 204.48 160.86 164.37 167.05 147.97 299.52 117.84 106.99 142.03 299.04 250.15 157.63

Sum Sq. Dev. 7247.72 8442.24 8167.17 7953.84 11393.21 10541.64 6212.07 5298.07 16621.07 15063.66 10958.74 7947.84

Observations 2495.00 2494.00 2494.00 2494.00 2494.00 2494.00 2494.00 2494.00 2392.00 2495.00 2495.00 2494.00

122

Table - 4.3:

Descriptive Statistics of Daily returns of Market Index and Sector Indices

Indices AUTO Return

BSE 100

Return

BSE 200 Return

BSE 500 Return

CD Return

CG Return

FMCG Return

HC Return

IT Return

Metal Return

Oil Return

Sensex Return

Mean 0.08 0.06 0.07 0.07 0.06 0.12 0.05 0.04 0.06 0.12 0.10 0.06

Median 0.14 0.19 0.19 0.21 0.11 0.16 0.05 0.10 0.05 0.18 0.12 0.14

Maximum 11.21 16.75 16.31 15.74 13.29 21.90 8.76 8.06 15.61 16.10 19.11 17.34

Minimum -10.43 -11.25 -11.87 -11.70 -11.01 -14.58 -10.55 -8.31 -19.99 -13.30 -14.97 -11.14

Std. Dev. 1.70 1.84 1.81 1.79 2.14 2.06 1.58 1.46 2.64 2.46 2.10 1.79

Skewness -0.27 -0.15 -0.25 -0.32 -0.14 0.22 -0.04 -0.36 -0.08 -0.21 -0.10 0.02

Kurtosis 6.04 8.65 8.84 8.68 6.71 11.07 6.47 7.19 8.46 6.61 10.15 9.40

Jarque-Bera 989.79 3323.51 3572.74 3394.52 1441.83 6793.95 1249.91 1879.91 2978.58 1375.08 5314.48 4253.98

Sum 204.48 160.86 164.37 167.05 147.97 299.52 117.84 106.99 142.03 299.04 250.15 157.63

Sum Sq. Dev. 7247.72 8442.24 8167.17 7953.84 11393.21 10541.64 6212.07 5298.07 16621.07 15063.66 10958.74 7947.84

Observations 2495.00 2494.00 2494.00 2494.00 2494.00 2494.00 2494.00 2494.00 2392.00 2495.00 2495.00 2494.00

123

4.4.1 DESCRIPTIVE STATISTICS

Table 4.3 and 4.4 Provides descriptive statistics of daily Index value and daily

returns on index respectively four market indices and eight sector indices are included

in the study from January 1, 2000 to December 31, 2009. Daily returns are calculates

as log of price relative.

It is evident from the table that there is significant positive mean return for all

the indices. The highest mean return for all the indices. The highest mean return is

found in consumer goods sector and metal with 0.12 percent. Mean returns of market

is 0.06 percent and returns in health care sector with 0.04 percent. The volatility of a

measured by standard deviation less volatility is found in health care sector 1.58

followed by FMCG with 1.58. Highest volatility is found in IT sector 2.64 followed

by metal with 2.46 all market indices have almost same level of volatility between

1.79-1.84.

Sensex return is skewed2 to the right while the rest are skewed to the left and

all other indices are skewed right indicating that distribution is spread to the low-

value end i.e. excess tail is on left-hand side. Kurtosis3 measures the peakedness of the

return, the coefficient of kurtosis are high for all selected indices inferring it is more

close bunched around the mode since coefficient of kurtosis is greater than 3 it is

mores peaked than the normal curve. Jarque-Bera (JB)4 is a test statistic for testing

whether the series is normally distributed. The test statistic measures the difference of

the skewness and kurtosis of the series with those from the normal distribution. Jarque

- Bera statistics is high in all the indices, which means that the null-hypothesis of

normal distribution of return in selected indices rejected.

1 |

2 ∑ Where S is estimator of standard Deviation.

3 ∑

4 Where K is Kurtosis coefficient, S is the skewness and k is the number

of the estimated co-efficient used to create the series.

124

Figure 4.12:

Index price series of selected indices from 2000 - 2009

Figure shows the long-run stock price variations in each of selected indices.

The market crashed in 2001 and started picking up from 2004. Between 2006 - 07

market was at all time high reaching 23,000 marks. In 2008 again market crashed

owing the downturn in world market.

A complement to standard descriptive statistics is displayed along with the

histogram. All of the statistics are calculated using the observations in the current

sample Histogram is used to study the distribution of indices. It includes mean,

median, standard deviation, maximum, minimum value, skewness and kurtosis.

0

4,000

8,000

12,000

16,000

20,000

24,000

00 01 02 03 04 05 06 07 08 09

AUTO BANK BSE100BSE200 BSE500 CDCG FMCG HCIT

125

Figure 4.13:

Distribution of Sensex from January 2000 to December 2009

The above histogram shows the historical distribution of the Sensex. Mean of

stock price indices from 2000 to 2009 is 8301.74; median and standard deviation are

6227.80 and 4976.31 respectively. It is skewed to right with a value of 0.672.

Figure 4.14:

Stock Price Movement, Trend and cycle of Sensex

This figure shows indices movements, trends and cycles which are indicated

with two scales; top panel shows trend and cycles. Bottom panel indicates stock price

volatility.

0

100

200

300

400

500

2500 5000 7500 10000 12500 15000 17500 20000

Series: SENSEXSample 1/03/2000 12/31/2009Observations 2495

Mean 8301.749Median 6227.830Maximum 20873.33Minimum 2600.120Std. Dev. 4976.311Skewness 0.672417Kurtosis 2.109829

Jarque-Bera 270.3937Probability 0.000000

-3,000

-2,000

-1,000

0

1,000

2,000

3,000

0

5,000

10,000

15,000

20,000

25,000

00 01 02 03 04 05 06 07 08 09

SENSEX Trend Cycle

Hodrick-Prescott Filter (lambda=6812100)

126

Figure 4.15:

Distribution of BSE 200 from January 2000 to December 2009

The above histogram shows the historical distribution of the BSE 200 Index

Mean of stock price indices from 2000 to 2009 is 1015.79; median and standard

deviation are 829.34 and 623.10 respectively. It is skewed to right with a value of

0.672.

Figure 4.16:

Stock Price Movement, Trend and cycle of BSE 200

0

100

200

300

400

500

400 800 1200 1600 2000 2400 2800

Series: BSE200Sample 1/03/2000 12/31/2009Observations 2495



-400

-200

0

200

400

600

0

500

1,000

1,500

2,000

2,500

3,000

00 01 02 03 04 05 06 07 08 09

BSE200 Trend Cycle


127

Figure 4.17:





0.672.

Figure 4.18:


0

100

200

300

400

500

600

1000 2000 3000 4000 5000 6000 7000 8000 9000




-1,500

-1,000

-500

0

500

1,000

1,500

2,000

0

2,000

4,000

6,000

8,000

10,000

00 01 02 03 04 05 06 07 08 09

BSE500 Trend Cycle


128

Figure 4.19:





0.696.

Figure 4.20:


0

100

200

300

400

500

600

2000 4000 6000 8000 10000 12000




-2,000

-1,000

0

1,000

2,000

0

2,000

4,000

6,000

8,000

10,000

12,000

00 01 02 03 04 05 06 07 08 09

BSE100 Trend Cycle


129

Figure 4.21:

Distribution Consumer durable from January 2000 to December 2009

The above histogram shows the historical distribution of the Consumer

Durable Index Mean of stock price indices from 2000 to 2009 is 2022.19; median and

standard deviation are 1497.4 and 1404.57 respectively. It is skewed to right with a

value of 0.8161.

Figure 4.22:

Stock Price Movement, Trend and cycle of Consumer Durable

0

100

200

300

400

500

1000 2000 3000 4000 5000 6000 7000

Series: CDSample 1/03/2000 12/31/2009Observations 2495



-2,000

-1,000

0

1,000

2,000

0

2,000

4,000

6,000

8,000

00 01 02 03 04 05 06 07 08 09

CD Trend Cycle


130

Figure 4.23:

Distribution Consumer Goods from January 2000 to December 2009

The above histogram shows the historical distribution of the Consumer Goods

Index Mean of stock price indices from 2000 to 2009 is 5297.24; median and standard


0.956.

Figure 4.24:

Stock Price Movement, Trend and cycle of Consumer Goods

0

100

200

300

400

500

600

700

800

900

0 4000 8000 12000 16000 20000

Series: CGSample 1/03/2000 12/31/2009Observations 2495



-4,000

-2,000

0

2,000

4,000

6,000

0

5,000

10,000

15,000

20,000

25,000

00 01 02 03 04 05 06 07 08 09

CG Trend Cycle


131

Figure 4.25:

Distribution FMCG from January 2000 to December 2009

The above histogram shows the historical distribution of the FMCG Index



1.952.

Figure 4.26:

Stock Price Movement, Trend and cycle of FMCG

0

100

200

300

400

500

800 1200 1600 2000 2400 2800

Series: FMCGSample 1/03/2000 12/31/2009Observations 2495



-1,000

-500

0

500

1,000

0

2,000

4,000

6,000

8,000

00 01 02 03 04 05 06 07 08 09

AUTO Trend Cycle


132

Figure 4.27:

Distribution Health Care from January 2000 to December 2009

The above histogram shows the historical distribution of the Health Care

Index Mean of stock price indices from 2000 to 2009 is 2553.395; median and

standard deviation are 2574.4 and 1092.90 respectively. It is skewed to right with a

value of 1.69.

Figure 4.28:

Stock Price Movement, Trend and cycle of Health care

0

100

200

300

400

500

1000 1500 2000 2500 3000 3500 4000 4500 5000

Series: HCSample 1/03/2000 12/31/2009Observations 2495



-800

-400

0

400

800

0

1,000

2,000

3,000

4,000

5,000

6,000

00 01 02 03 04 05 06 07 08 09

HC Trend Cycle


133

Figure 4.29:

Distribution Information Technology from January 2000 to December 2009

The above histogram shows the historical distribution of the Information

Technology Index Mean of stock price indices from 2000 to 2009 is 2553.395;

median and standard deviation are 2574.4 and 1092.90 respectively. It is skewed to

right with a value of 1.69.

Figure 4.30:

Stock Price Movement, Trend and cycle of Information Technology

0

50

100

150

200

250

300

1000 2000 3000 4000 5000

Series: ITSample 1/03/2000 12/31/2009Observations 2393



-1,200

-800

-400

0

400

800

0

1,000

2,000

3,000

4,000

5,000

6,000

00 01 02 03 04 05 06 07 08 09

IT Trend Cycle


134

Figure 4.31:

Distribution Metal from January 2000 to December 2009

The above histogram shows the historical distribution of the Metal Index



0.883.

Figure 4.32:

Stock Price Movement, Trend and cycle of Metal Index

0

100

200

300

400

500

600

2500 5000 7500 10000 12500 15000 17500 20000

Series: METALSample 1/03/2000 12/31/2009Observations 2496



-800

-400

0

400

800

0

1,000

2,000

3,000

4,000

5,000

6,000

00 01 02 03 04 05 06 07 08 09

HC Trend Cycle


135

Figure 4.33:

Distribution Oil & Gas Index from January 2000 to December 2009

The above histogram shows the historical distribution of the oil Index Mean of

stock price indices from 2000 to 2009 is 4322.191; median and standard deviation are

3100.62 and 3408.07 respectively. It is skewed to right with a value of 0.825.

Figure 4.34:

Stock Price Movement, Trend and cycle of Oil & Gas Index

0

100

200

300

400

500

2000 4000 6000 8000 10000 12000 14000

Series: OILSample 1/03/2000 12/31/2009Observations 2496



-3,000

-2,000

-1,000

0

1,000

2,000

3,000

0

4,000

8,000

12,000

16,000

00 01 02 03 04 05 06 07 08 09

OIL Trend Cycle


136

Figure 4.35:

Distribution Transport Index from January 2000 to December 2009

The above histogram shows the historical distribution of the Transport Mean

of stock price indices from 2000 to 2009 is 2831.990; median and standard deviation

are 2552.056 and 1836.15 respectively. It is skewed to right with a value of 0.381.

Figure 4.36: Stock Price Movement, Trend and cycle of Transport Index

0

100

200

300

400

500

1000 2000 3000 4000 5000 6000 7000

Series: AUTOSample 1/03/2000 12/31/2009Observations 2496



-1,000

-500

0

500

1,000

0

2,000

4,000

6,000

8,000

00 01 02 03 04 05 06 07 08 09

AUTO Trend Cycle


137

Table 4.4:

Correlation Matrix for Indices based on return

Auto

Return

BSE100

Return

BSE200

Return

BSE500

Return

CD

Return

CG

Return

FMCG

Return

HC

Return

IT

Return

Metal

Return

Oil

Return

BSE100 RETURN 0.25

BSE200 RETURN 0.27 1.00

BSE500 RETURN 0.28 0.99 1.00

CD RETURN 0.28 0.71 0.73 0.74

CG RETURN 0.29 0.82 0.83 0.83 0.68

FMCG RETURN 0.20 0.67 0.67 0.66 0.50 0.54

HC RETURN 0.29 0.73 0.75 0.75 0.63 0.66 0.58

IT RETURN -0.02 0.002 0.004 0.004 -0.003 0.02 0.01 -0.02

METAL

RETURN 0.71 0.23 0.25 0.26 0.26 0.27 0.17 0.25 -0.02

OIL RETURN 0.67 0.25 0.28 0.29 0.25 0.28 0.17 0.24 -0.02 0.72

SENSEX

RETURN 0.24 0.97 0.97 0.96 0.67 0.81 0.71 0.72 -0.003 0.20 0.22

138

Table 4.5:

Correlation Matrix for Indices based on index value

AUTO BSE100 BSE200 BSE500 CD CG FMCG HC IT METAL OIL

BSE100 0.91

BSE200 0.92 1.00

BSE500 0.93 1.00 1.00

CD 0.92 0.97 0.98 0.98

CG 0.88 0.99 0.99 0.98 0.96

FMCG 0.87 0.93 0.92 0.92 0.88 0.90

HC 0.96 0.93 0.94 0.94 0.91 0.89 0.89

IT 0.84 0.74 0.74 0.74 0.74 0.67 0.77 0.77

METAL 0.89 0.97 0.97 0.98 0.95 0.97 0.86 0.92 0.65

OIL 0.85 0.97 0.97 0.97 0.91 0.98 0.91 0.90 0.63 0.96

SENSEX 0.92 1.00 1.00 1.00 0.97 0.99 0.93 0.93 0.75 0.96 0.97

139

4.4.2 CORRELATION

Correlation test, preliminarily indication of relationship, is correlation between

market indices and sector indices. Table 4.5 and table 4.6 give the correlation

coefficient (two –tailed) for 12 bilateral pairs of selected indices.

It is observed that there is high positive correlation between BSE 100, BSE

200 BSE 500 and consumer durables r =0.83. There is perfect positive correlation

between all the market indices. r = 1. The return of IT sector does not have

relationship with the returns of other sector return as r =0. The return on IT sector is

not even selected to the return on market indices. The return of Consumer Durable,

Consumer Goods, FMCG, and Health Care has high positive relationship with market.

Whereas metal, oil, auto show less positive association. Correlation of Index

movement of market and other sector are highly positive correlated with r-value

ranging from 0.67 to 1.

4.4.3 UNIT ROOT TEST:

Hypothesis 1

H0: Unit root exits, the time series is non-stationary and the series I (1).

H1: Unit root does not exist, the time series is stationary and the series is I (0).

140

Table 4.6:

Augmented Dickey-Fuller Test (ADF) finding for level for various sectors and Markets

AUTO CD CG FMCG HC IT METAL OIL SENSEX BSE100 BSE200 BSE500

ADF t-value 0.68 -0.84 -0.39 0.09 0.27 -0.73 -0.23 -0.45 -0.25 -0.26 -0.26 -0.27

Critical Value of t (1%) -3.43 -3.43 -3.43 -3.43 -3.43 -3.43 -3.43 -3.43 -3.43 -3.43 -3.43 -3.43


Lag Length 1 2 1 0 1 0 1 1 1 1 1 1

H0 Accepted

Data Character Non - Stationary

Table 4.7:

Augmented Dickey-Fuller Test (ADF) finding for first difference for various sectors and Market

AUTO CD CG FMCG HC IT METAL OIL SENSEX BSE100 BSE200 BSE500

ADF t-value -43.3973 -31.1905 -42.8617 -48.1133 -45.1722 -36.0576 -44.1143 -45.6556 -46.0577 -44.9237 -44.4629 -43.91764



Lag Length 0 1 0 0 0 1 0 0 0 0 0 0

H0 Rejected

Data Character Integrated of order one I (1)

141

Table results of the unit root test bases on ADF t - statistical are presented in

the table. The critical values of the tests are obtained from the table values. Tables by

Mackinnon (1996) one - side value are used. Lag length is chosen automatically based

on SIC, MAXLAG.

Table 4.7 shows that the null hypotheses of unit root is not be rejected at 5

percent and I percent confidence levels in all of selected market and sector indices. As

illustrated in the table, ADF t- values for all indices are higher than the critical values,

implying that the series are non-stationary.

The null hypothesis of the unit root at first difference is rejected for all indices

as shows in table 4.8. Statistics of the ADF lie to the left of the critical values

implying that the series are stationary at first difference level. The result for all the

indices are consistent there is a possibility that co-integration among the series exist.

4.4.4 BI-LATERAL CO-INTEGRATION

Johannes co integration test is performed for each of 58 bilateral pairs

identifies with in the group of selected indices for each pair, co integration rack of a

and I are examined by comparing the trace statistic to corresponding critical values at

5% and 1% if the trace value is higher than critical values, then co integration exist at

that level and vice versa the null hypothesis in the test holds that r = 0 (No co-

integration exists) while the alterative holds. That r = 1 ( co-integration exists) failure

to reject the null hypothesis implies that variables are not co-integrated, where as

positive rejection implies that there is at least on co-integrated equation. The result

of the Johansen co-integration test for each of the 58 bilateral pair of the selected

indices is summarized in Tables 4.9.

HYPOTHESIS -2

H0: No bi-variate co integration exists.

H1: Bi-variate co –integration exists.

The result of Johansen co-integration test indicates that integration among

selected stock indices is minimal. Out of 58 bilateral pairs of 11 stock indices, one

pair is found to be co-integrated i.e., the market index Sensex and Information

142

Technology stock. The selected market indices and sector indices are not co-

integrated because; the trace statistics are less than the Critical value at both 5% and

1%. Only in case of integration between Sensex and IT sector exist as the trace

statistics so null hypothesis is accepted. Table 4.9 shows that no co-integration exist

between all other pairs

4.4.5 MULTILATERAL CO INTEGRATION:

The Johansen co –integration test is performed for twelve set of selected

market indices to investigate integration of these indices as group analysis using the

Multiple Equation, is based on VAR model, the VAR model of order 2, is chosen

acceding to AIC contain 12x1 vector that contain Logarithms of share price index of

12 indices. The multivariate approach examines co integrating vector in the stochastic

matrix possible number of matrix. A sequence of hypotheses test using maximum

likelihood method, establishing the greatest possible number of vector within the

system.

The analysis of Johansen multivariate approach is to test null hypothesis of r

co integrated vectors against the alternative that r+1 co integrated vectors are present

where r is the number of hypothesized co integration equations. The Null hypotheses

assume that for each row of numbers: zero at most one, at most two so on till at most

eleven. The alternative hypotheses states one, two, three, four to eleven co –

integration equation respectively for each row. As long as trace statistics exceeds

critical values at 5% or 1%, the alternative accepted. The results of test are present in

Table 4.10.

HYPOTHESIS -3

H0: r =0 NO multilateral co-integration exists.

H1: r =1 Multilateral co-integration exists.

As illustrated in the table, the trace statistics indicate three co integration

vector at 5% and 1% significance level among the indices selected. Since trace

statistics 417.68 exceeds the 5% and 1% critical values, it is possible to reject the null

hypothesis of no co integration vector, indicating that there are three co-integration

equations. For the fourth null hypothesis, the trace statistics of 189.91 is less than the

143

5% and 1% critical values, which implies that the hypothesis cannot be rejected,

indicating that there is at most one co integrating vector.

Findings of multilateral co-integration indicate that the level of integration

with respect to the group of twelve selected indices is low because only three co-

integrated vector is found. The result of the Johansen multivariate test on the group of

twelve selected indices has supported the proposition of integration across all twelve

indices on bilateral basis because only one pair is found to be integrated.

4.4.6 GRANGER CAUALITY TEST:

The finding of co-integration testing do not indicate the direction of

relationship among selected market indices, Granger causality test is performed to

examine the casual relationship among these indices. If two variables are co-

integrated, Granger causality must exist at least in one direction. The Granger

causality approach seeks to determine how much of a current variable Y, can be

explained by past values of Y and lagged values of another variable X. There are four

possible patterns of the test. There can be unconditional causality from X to Y. There

can be unconditional causality occurs from Y to X, There can be bidirectional

causality. NO causality exists between X and Y.

HYPOTHESIS -3

H0: No Causality exists between Sensex and Sector Indices.

H1: Causality exists between Sensex and Sector Indices.

The Granger causality test is applied to log values for the twelve selected

indices Table 4.10 presents the output of the test, which includes calculated F-

statistics and the probability for each pair of the market index and sector indices. If

the probability of non – causality is less than 0.25, the hypothesis of non – causality is

rejected implying that the casual relationship exists. Findings of Granger causality test

show clearly that the causality in terms of co – dependencies on each other’s lagged

indices runs from Sensex i.e. market index and other selected sector indices. As

illustrated in Table 4.10, the probability of accepting the null hypothesis that Sensex

returns does not cause Auto sector return is 0%, which means the auto return is

affected by Sensex return by 100 percent. Likewise the Consumer Durable sector

144

return is also affected by market return by 99 percent. Consumer Goods sector return

is affected by 95 percent by Sensex return, FMCG returns are affected by 80 percent,

Health-Care returns are affected by 88 percent. IT sector returns are affected by 93

percent and Metal sector and Oil sector returns are affected by market return by 100

percent. The causality test indicates that market returns are independent variable.

The result suggests a Granger causality running from only Market to other

sector indices.

Table 4.8:

Result of Granger Causality among Sensex and sectoral indices

Null Hypothesis: Obs F-Statistic Prob.

SENSEXRETURN does not Granger Cause

AUTORETURN

2492 725.61 0.00

AUTORETURN does not Granger Cause

SENSEXRETURN

0.0733 0.9293

SENSEXRETURN does not Granger Cause CDRETURN 2492 6.25156 0.002

CDRETURN does not Granger Cause SENSEXRETURN 2.39797 0.0911

SENSEXRETURN does not Granger Cause CGRETURN 2492 3.10794 0.0449

CGRETURN does not Granger Cause SENSEXRETURN 3.6097 0.0272

SENSEXRETURN does not Granger Cause

FMCGRETURN

2492 1.63498 0.1952

FMCGRETURN does not Granger Cause

SENSEXRETURN

8.83762 0.0001

SENSEXRETURN does not Granger Cause HCRETURN 2492 2.14256 0.1176

HCRETURN does not Granger Cause SENSEXRETURN 3.74642 0.0237

SENSEXRETURN does not Granger Cause ITRETURN 2390 2.61673 0.0733

ITRETURN does not Granger Cause SENSEXRETURN 0.97827 0.3761

SENSEXRETURN does not Granger Cause 2492 833.871 0.00

145

METALRETURN

METALRETURN does not Granger Cause

SENSEXRETURN

1.39489 0.2481

SENSEXRETURN does not Granger Cause OILRETURN 2492 855.885 0.00

OILRETURN does not Granger Cause SENSEXRETURN 1.28192 0.2777

Table 4.9 : Result of Granger Causality among sector indices

Null Hypothesis: Obs F-Statistic Prob.

CDRETURN does not Granger Cause AUTORETURN 2492 359.494 0.00

AUTORETURN does not Granger Cause CDRETURN 2.08396 0.1247

CGRETURN does not Granger Cause AUTORETURN 2492 546.032 0.00

AUTORETURN does not Granger Cause CGRETURN 0.27629 0.7586


AUTORETURN

2492 292.131 0.00


FMCGRETURN

0.25547 0.7746

HCRETURN does not Granger Cause AUTORETURN 2492 360.544 0.00

AUTORETURN does not Granger Cause HCRETURN 1.67095 0.1883

ITRETURN does not Granger Cause AUTORETURN 2390 0.97494 0.3774

AUTORETURN does not Granger Cause ITRETURN 0.23355 0.7917


AUTORETURN

2493 0.12164 0.8855


METALRETURN

0.82028 0.4404

OILRETURN does not Granger Cause AUTORETURN 2493 1.09045 0.3362

AUTORETURN does not Granger Cause OILRETURN 0.14123 0.8683

CGRETURN does not Granger Cause CDRETURN 2492 4.09746 0.0167

146

CDRETURN does not Granger Cause CGRETURN 1.58077 0.206

FMCGRETURN does not Granger Cause CDRETURN 2492 1.50075 0.2232

CDRETURN does not Granger Cause FMCGRETURN 0.27633 0.7586

HCRETURN does not Granger Cause CDRETURN 2492 0.49898 0.6072

CDRETURN does not Granger Cause HCRETURN 1.37733 0.2524

ITRETURN does not Granger Cause CDRETURN 2390 1.45214 0.2343

CDRETURN does not Granger Cause ITRETURN 1.24222 0.2889

METALRETURN does not Granger Cause CDRETURN

2492 3.61147 0.0272

CDRETURN does not Granger Cause

METALRETURN

403.567 0.00

OILRETURN does not Granger Cause CDRETURN 2492 0.20403 0.8155

CDRETURN does not Granger Cause OILRETURN 293.752 0.00

FMCGRETURN does not Granger Cause CGRETURN 2492 0.2359 0.7899

CGRETURN does not Granger Cause FMCGRETURN 0.62657 0.5345

HCRETURN does not Granger Cause CGRETURN 2492 1.88165 0.1526

CGRETURN does not Granger Cause HCRETURN 1.08498 0.3381

ITRETURN does not Granger Cause CGRETURN 2390 2.05256 0.1286

CGRETURN does not Granger Cause ITRETURN 0.82704 0.4375


CGRETURN

2492 1.07709 0.3407

CGRETURN does not Granger Cause

METALRETURN

631.156 0.00

OILRETURN does not Granger Cause CGRETURN 2492 0.23459 0.7909

CGRETURN does not Granger Cause OILRETURN 602.876 0.00

HCRETURN does not Granger Cause FMCGRETURN 2492 2.64317 0.0713

FMCGRETURN does not Granger Cause HCRETURN 0.59633 0.5509

147

ITRETURN does not Granger Cause FMCGRETURN 2390 2.54759 0.0785

FMCGRETURN does not Granger Cause ITRETURN 2.62875 0.0724


FMCGRETURN

2492 1.39495 0.248


METALRETURN

269.625 0.00

OILRETURN does not Granger Cause FMCGRETURN 2492 0.22548 0.7981

FMCGRETURN does not Granger Cause OILRETURN 231.722 0.00

ITRETURN does not Granger Cause HCRETURN 2390 1.44078 0.2369

HCRETURN does not Granger Cause ITRETURN 1.17794 0.3081


HCRETURN

2492 1.71617 0.18

HCRETURN does not Granger Cause

METALRETURN

365.142 0.00

OILRETURN does not Granger Cause HCRETURN 2492 0.29825 0.7421

HCRETURN does not Granger Cause OILRETURN 331.696 0.00

METALRETURN does not Granger Cause ITRETURN 2390 0.13544 0.8733

ITRETURN does not Granger Cause METALRETURN 2.42631 0.0886

OILRETURN does not Granger Cause ITRETURN 2390 0.29464 0.7448

ITRETURN does not Granger Cause OILRETURN 0.89417 0.4091

OILRETURN does not Granger Cause

METALRETURN

2493 0.91852 0.3992


OILRETURN

0.26808 0.7649

148

ANNEXURES

A. UNIT ROOT TEST

A.1 Augmented Dickey-Fuller Test (ADF) finding for level for Sensex

Null Hypothesis : SENSEX has a unit root

Exogenous : Constant

Lag Length : 1 (Automatic based on SIC, MAXLAG=26)

t-Statistic Prob.*

Augmented Dickey-Fuller test statistic -0.246341 0.9301 Test critical values: 1% level -3.432779

5% level -2.862499 10% level -2.567326

*MacKinnon (1996) one-sided p-values.

Augmented Dickey-Fuller Test Equation

Dependent Variable : D(SENSEX)

Method : Least Squares

Included observations : 2493 after adjustments

Variable Coefficient Std. Error t-Statistic Prob.

SENSEX(-1) -0.000184 0.000746 -0.246341 0.8054 D(SENSEX(-1)) 0.080315 0.019988 4.018268 0.0001

C 5.942866 7.216082 0.823558 0.4103

R-squared 0.006447 Mean dependent var 4.802968 Adjusted R-squared 0.005649 S.D. dependent var 185.7091 S.E. of regression 185.1838 Akaike info criterion 13.28178 Sum squared resid 85389631 Schwarz criterion 13.28878 Log likelihood -16552.73 Hannan-Quinn criter. 13.28432 F-statistic 8.079010 Durbin-Watson stat 1.995923 Prob(F-statistic) 0.000318

149

A.2 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 Null Hypothesis : BSE100 has a unit root



t-Statistic

Augmented Dickey-Fuller test statistic -0.262998 Test critical values: 1% level -3.432779

5% level -2.862499 10% level -2.567326


Augmented Dickey-Fuller Test Equation Dependent Variable : D(BSE100) Method : Least Squares Included observations : 2493 after adjustments


BSE100(-1) -0.000197 0.000747 -0.262998 0.7926 D(BSE100(-1)) 0.105175 0.019939 5.274832 0.0000

C 3.111944 3.771574 0.825105 0.4094


150

A.3 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 200

Null Hypothesis : BSE200 has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567326


Augmented Dickey-Fuller Test Equation

Dependent Variable : D(BSE200)

Method : Least Squares



BSE200(-1) -0.000188 0.000731 -0.257712 0.7967 D(BSE200(-1)) 0.115304 0.019917 5.789086 0.0000

C 0.732965 0.870166 0.842328 0.3997

R-squared 0.013282 Mean dependent var 0.612651 Adjusted R-squared 0.012489 S.D. dependent var 22.85366 S.E. of regression 22.71050 Akaike info criterion 9.084735 Sum squared resid 1284260. Schwarz criterion 9.091740 Log likelihood -11321.12 Hannan-Quinn criter. 9.087278 F-statistic 16.75825 Durbin-Watson stat 1.998760 Prob(F-statistic) 0.000000

151

A.4 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 500

Null Hypothesis : BSE500 has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567326

*MacKinnon (1996) one-sided p-values. Augmented Dickey-Fuller Test Equation Dependent Variable : D(BSE500) Method : Least Squares Included observations : 2493 after adjustments


BSE500(-1) -0.000188 0.000703 -0.267002 0.7895 D(BSE500(-1)) 0.127447 0.019887 6.408498 0.0000

C 2.301722 2.648018 0.869224 0.3848


152

A.5 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO

Null Hypothesis : AUTO has a unit root



t-Statistic Prob.*

Augmented Dickey-Fuller test statistic 0.676033 0.9917 Test critical values: 1% level -3.432778

5% level -2.862499 10% level -2.567325

*MacKinnon (1996) one-sided p-values. Augmented Dickey-Fuller Test Equation Dependent Variable : D(AUTO) Method : Least Squares Included observations : 2494 after adjustments


AUTO(-1) 0.000423 0.000626 0.676033 0.4991 D(AUTO(-1)) 0.138164 0.019871 6.952960 0.0000

C 0.890916 2.109838 0.422268 0.6729


153

A.6 Augmented Dickey-Fuller Test (ADF) finding for level for CD

Null Hypothesis : CD has a unit root



t-Statistic Prob.*


5% level -2.862500 10% level -2.567326

*MacKinnon (1996) one-sided p-values. Augmented Dickey-Fuller Test Equation Dependent Variable : D(CD) Method : Least Squares Included observations : 2492 after adjustments


CD(-1) -0.000638 0.000763 -0.835411 0.4036 D(CD(-1)) 0.115019 0.020015 5.746612 0.0000 D(CD(-2)) 0.058511 0.020021 2.922428 0.0035

C 2.064826 1.878281 1.099316 0.2717


154

A.7 Augmented Dickey-Fuller Test (ADF) finding for level for CG

Null Hypothesis : CG has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567326

*MacKinnon (1996) one-sided p-values. Augmented Dickey-Fuller Test Equation Dependent Variable : D(CG) Method : Least Squares Included observations : 2493 after adjustments


CG(-1) -0.000259 0.000667 -0.387570 0.6984 D(CG(-1)) 0.151161 0.019822 7.626011 0.0000

C 5.784982 4.924732 1.174679 0.2402


155

A.8 Augmented Dickey-Fuller Test (ADF) finding for level for FMCG

Null Hypothesis : FMCG has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567325

*MacKinnon (1996) one-sided p-values. Augmented Dickey-Fuller Test Equation Dependent Variable : D(FMCG) Method : Least Squares Included observations : 2494 after adjustments


FMCG(-1) 7.99E-05 0.000866 0.092255 0.9265 C 0.534381 1.345243 0.397238 0.6912

R-squared 0.000003 Mean dependent var 0.649178 Adjusted R-squared -0.000398 S.D. dependent var 25.52226 S.E. of regression 25.52734 Akaike info criterion 9.318178 Sum squared resid 1623899. Schwarz criterion 9.322847 Log likelihood -11617.77 Hannan-Quinn criter. 9.319873 F-statistic 0.008511 Durbin-Watson stat 1.925414 Prob(F-statistic) 0.926503

156

A.9 Augmented Dickey-Fuller Test (ADF) finding for level for HC

Null Hypothesis : HC has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567326

*MacKinnon (1996) one-sided p-values. Augmented Dickey-Fuller Test Equation Dependent Variable : D(HC) Method : Least Squares Included observations : 2493 after adjustments


HC(-1) 0.000198 0.000718 0.275249 0.7831 D(HC(-1)) 0.099340 0.019958 4.977513 0.0000

C 0.480584 1.993099 0.241124 0.8095


157

A.10 Augmented Dickey-Fuller Test (ADF) finding for level for IT

Null Hypothesis : IT has a unit root



t-Statistic Prob.*


5% level -2.862548 10% level -2.567352

*MacKinnon (1996) one-sided p-values. Augmented Dickey-Fuller Test Equation Dependent Variable : D(IT) Method : Least Squares Included observations : 2392 after adjustments


IT(-1) -0.000833 0.001141 -0.729941 0.4655 C 3.344804 3.562361 0.938929 0.3479

R-squared 0.000223 Mean dependent var 0.961777 Adjusted R-squared -0.000195 S.D. dependent var 69.71500 S.E. of regression 69.72181 Akaike info criterion 11.32774 Sum squared resid 11618102 Schwarz criterion 11.33257 Log likelihood -13545.98 Hannan-Quinn criter. 11.32950 F-statistic 0.532814 Durbin-Watson stat 1.945916 Prob(F-statistic) 0.465498

158

A.11 Augmented Dickey-Fuller Test (ADF) finding for level for METAL

Null Hypothesis : METAL has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567325


Augmented Dickey-Fuller Test Equation Dependent Variable : D(METAL) Method : Least Squares Included observations : 2494 after adjustments


METAL(-1) -0.000199 0.000868 -0.229864 0.8182 D(METAL(-1)) 0.123210 0.019903 6.190406 0.0000

C 6.672609 6.663511 1.001365 0.3167

R-squared 0.015152 Mean dependent var 6.233011 Adjusted R-squared 0.014361 S.D. dependent var 207.1684 S.E. of regression 205.6755 Akaike info criterion 13.49168 Sum squared resid 1.05E+08 Schwarz criterion 13.49868 Log likelihood -16821.12 Hannan-Quinn criter. 13.49422 F-statistic 19.16157 Durbin-Watson stat 2.005255 Prob(F-statistic) 0.000000

159

A.12 Augmented Dickey-Fuller Test (ADF) finding for level for OIL

Null Hypothesis : OIL has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567325


Augmented Dickey-Fuller Test Equation Dependent Variable : D(OIL) Method : Least Squares Included observations : 2494 after adjustments


OIL(-1) -0.000352 0.000776 -0.453757 0.6500 D(OIL(-1)) 0.089237 0.019968 4.468887 0.0000

C 4.807142 4.264700 1.127193 0.2598


160

A.13 Augmented Dickey-Fuller Test (ADF) finding for first difference for various

sectors and Market Indices

Null Hypothesis : D(OIL) has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567325


Augmented Dickey-Fuller Test Equation Dependent Variable : D(OIL,2) Method : Least Squares Included observations : 2494 after adjustments


D(OIL(-1)) -0.911054 0.019955 -45.65555 0.0000 C 3.287712 2.640576 1.245074 0.2132


161

A.14 Augmented Dickey-Fuller Test (ADF) finding for level for D(SENSEX)

Null Hypothesis : D(SENSEX) has a unit root Exogenous : Constant Lag Length : 0 (Automatic based on SIC, MAXLAG=26)

t-Statistic Prob.*


5% level -2.862499 10% level -2.567326


Augmented Dickey-Fuller Test Equation Dependent Variable : D(SENSEX,2) Method : Least Squares Included observations : 2493 after adjustments


D(SENSEX(-1)) -0.919855 0.019972 -46.05774 0.0000 C 4.418199 3.709411 1.191078 0.2337


162

A.15 Augmented Dickey-Fuller Test (ADF) finding for level for D (BSE100)

Null Hypothesis : D(BSE100) has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567326


Augmented Dickey-Fuller Test Equation Dependent Variable : D(BSE100,2) Method : Least Squares Included observations : 2493 after adjustments


D(BSE100(-1)) -0.895010 0.019923 -44.92372 0.0000 C 2.265252 1.964413 1.153145 0.2490

R-squared 0.447567 Mean dependent var -0.017196 Adjusted R-squared 0.447345 S.D. dependent var 131.8929 S.E. of regression 98.05023 Akaike info criterion 12.00964 Sum squared resid 23948094 Schwarz criterion 12.01431 Log likelihood -14968.01 Hannan-Quinn criter. 12.01133 F-statistic 2018.140 Durbin-Watson stat 1.998008 Prob(F-statistic) 0.000000

163





t-Statistic Prob.*


5% level -2.862499 10% level -2.567326




D(BSE200(-1)) -0.884876 0.019901 -44.46291 0.0000 C 0.541815 0.454927 1.190993 0.2338

R-squared 0.442474 Mean dependent var -0.002659 Adjusted R-squared 0.442250 S.D. dependent var 30.40364 S.E. of regression 22.70625 Akaike info criterion 9.083959 Sum squared resid 1284294. Schwarz criterion 9.088629 Log likelihood -11321.16 Hannan-Quinn criter. 9.085655 F-statistic 1976.950 Durbin-Watson stat 1.998724 Prob(F-statistic) 0.000000

164





t-Statistic Prob.*


5% level -2.862499 10% level -2.567326




D(BSE500(-1)) -0.872733 0.019872 -43.91764 0.0000 C 1.703976 1.413981 1.205092 0.2283


165

A.18 Augmented Dickey-Fuller Test (ADF) finding for level for D (AUTO)

Null Hypothesis : D(AUTO) has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567325


Augmented Dickey-Fuller Test Equation Dependent Variable : D(AUTO,2) Method : Least Squares Included observations : 2494 after adjustments


D(AUTO(-1)) -0.861155 0.019844 -43.39729 0.0000 C 2.087631 1.147830 1.818762 0.0691


166

A.19 Augmented Dickey-Fuller Test (ADF) finding for level for D (CD)

Null Hypothesis : D(CD) has a unit root



t-Statistic Prob.*


5% level -2.862500 10% level -2.567326


Augmented Dickey-Fuller Test Equation Dependent Variable : D(CD,2) Method : Least Squares Included observations : 2492 after adjustments


D(CD(-1)) -0.827314 0.026525 -31.19047 0.0000 D(CD(-1),2) -0.058049 0.020012 -2.900636 0.0038

C 0.776178 1.071633 0.724294 0.4690


167

A.20 Augmented Dickey-Fuller Test (ADF) finding for level for D (CG)

Null Hypothesis : D(CG) has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567326


Augmented Dickey-Fuller Test Equation Dependent Variable : D(CG,2) Method : Least Squares Included observations : 2493 after adjustments


D(CG(-1)) -0.849069 0.019810 -42.86167 0.0000 C 4.416541 3.432526 1.286674 0.1983


168

A.21 Augmented Dickey-Fuller Test (ADF) finding for level for D (FMCG)

Null Hypothesis : D(FMCG) has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567326


Augmented Dickey-Fuller Test Equation Dependent Variable : D(FMCG,2) Method : Least Squares Included observations : 2493 after adjustments


D(FMCG(-1)) -0.963002 0.020015 -48.11331 0.0000 C 0.638873 0.510996 1.250250 0.2113


169

A.22 Augmented Dickey-Fuller Test (ADF) finding for level for D (HC)

Null Hypothesis : D(HC) has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567326


Augmented Dickey-Fuller Test Equation Dependent Variable : D(HC,2) Method : Least Squares Included observations : 2493 after adjustments


D(HC(-1)) -0.900407 0.019933 -45.17219 0.0000 C 0.984972 0.783725 1.256783 0.2089

R-squared 0.450296 Mean dependent var -0.018853 Adjusted R-squared 0.450075 S.D. dependent var 52.74707 S.E. of regression 39.11561 Akaike info criterion 10.17172 Sum squared resid 3811307. Schwarz criterion 10.17639 Log likelihood -12677.05 Hannan-Quinn criter. 10.17342 F-statistic 2040.527 Durbin-Watson stat 1.999390 Prob(F-statistic) 0.000000

170

A.23 Augmented Dickey-Fuller Test (ADF) finding for level for D (IT)

Null Hypothesis : D(IT) has a unit root



t-Statistic Prob.*


5% level -2.862549 10% level -2.567352


Augmented Dickey-Fuller Test Equation Dependent Variable : D(IT,2) Method : Least Squares Included observations : 2390 after adjustments


D(IT(-1)) -1.026969 0.028481 -36.05757 0.0000 D(IT(-1),2) 0.049158 0.020372 2.413034 0.0159

C 0.817797 1.420243 0.575814 0.5648


171

A.24 Augmented Dickey-Fuller Test (ADF) finding for level for D (METAL)

Null Hypothesis : D(METAL) has a unit root



t-Statistic Prob.*


5% level -2.862499 10% level -2.567325


Augmented Dickey-Fuller Test Equation Dependent Variable : D(METAL,2) Method : Least Squares Included observations : 2494 after adjustments


D(METAL(-1)) -0.876993 0.019880 -44.11426 0.0000 C 5.468827 4.119523 1.327539 0.1845

R-squared 0.438494 Mean dependent var 0.020493 Adjusted R-squared 0.438269 S.D. dependent var 274.3694 S.E. of regression 205.6364 Akaike info criterion 13.49090 Sum squared resid 1.05E+08 Schwarz criterion 13.49557 Log likelihood -16821.15 Hannan-Quinn criter. 13.49259 F-statistic 1946.068 Durbin-Watson stat 2.005197 Prob(F-statistic) 0.000000

172

B. CO INTEGRATION TEST

B.1 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO BSE 100


Trend assumption : Linear deterministic trend

Series : AUTO BSE100

Lags interval (in first differences) : 1 to 4

Unrestricted Co-integration Rank Test (Trace)

Hypothesized Trace 0.05 No. of CE(s) Eigen Value Statistic Critical Value Prob.**

None 0.003608 9.031268 15.49471 0.3625 At most 1 1.26E-05 0.031254 3.841466 0.8596

Trace test indicates no Co-integration at the 0.05 level * denotes rejection of the hypothesis at the 0.05 level **MacKinnon-Haug-Michelis (1999) p-values








None 0.003686 9.205608 15.49471 0.3467 At most 1 4.56E-06 0.011348 3.841466 0.9149


173








None 0.003917 9.788101 15.49471 0.2974 At most 1 5.91E-06 0.014715 3.841466 0.9033


B.4 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO CD



Series : AUTO CD




None 0.005704 14.24408 15.49471 0.0765 At most 1 7.39E-08 0.000184 3.841466 0.9909


174

B.5 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO CG



Series : AUTO CG




None 0.002748 6.886288 15.49471 0.5909 At most 1 1.39E-05 0.034655 3.841466 0.8523


B.6 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO FMCG



Series : AUTO FMCG




None 0.001730 4.684591 15.49471 0.8413 At most 1 0.000150 0.372729 3.841466 0.5415


175

B.7 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO HC



Series : AUTO HC




None 0.005904 14.75048 15.49471 0.0645 At most 1 2.44E-06 0.006064 3.841466 0.9372


B.8 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO IT



Series : AUTO IT




None 0.004848 11.64069 15.49471 0.1750 At most 1 1.46E-05 0.034747 3.841466 0.8521


176

B.9 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO METAL



Series : AUTO METAL




None 0.003886 9.812805 15.49471 0.2954 At most 1 4.59E-05 0.114437 3.841466 0.7351


B.10 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO OIL



Series : AUTO OIL




None 0.001697 4.399484 15.49471 0.8688 At most 1 6.80E-05 0.169279 3.841466 0.6807


177

B.11 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO SENSEX



Series : AUTO SENSEX




None 0.003436 8.589130 15.49471 0.4047 At most 1 7.97E-06 0.019846 3.841466 0.8879


B.12 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 BSE 200



Series : BSE100 BSE200




None 0.002005 5.459749 15.49471 0.7582 At most 1 0.000186 0.462648 3.841466 0.4964


178








None 0.002002 5.273521 15.49471 0.7791 At most 1 0.000114 0.283071 3.841466 0.5947


B.14 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 CD



Series : BSE100 CD




None 0.002386 5.978005 15.49471 0.6981 At most 1 1.20E-05 0.029885 3.841466 0.8627


179

B.15 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 CG



Series : BSE100 CG




None 0.004216 10.58412 15.49471 0.2384 At most 1 2.57E-05 0.063887 3.841466 0.8004


B.16 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 FMCG



Series : BSE100 FMCG




None 0.002298 5.742757 15.49471 0.7257 At most 1 5.96E-06 0.014853 3.841466 0.9028


180

B.17 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 HC



Series : BSE100 HC




None 0.002057 5.162101 15.49471 0.7914 At most 1 1.40E-05 0.034747 3.841466 0.8521


B.18 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 IT



Series : BSE100 IT




None 0.006233 15.19399 15.49471 0.0555 At most 1 0.000110 0.261871 3.841466 0.6088


181

B.19 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 METAL



Series : BSE100 METAL




None 0.002308 5.901797 15.49471 0.7071 At most 1 5.94E-05 0.147939 3.841466 0.7005


B.20 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 OIL



Series : BSE100 OIL




None 0.002192 5.479834 15.49471 0.7559 At most 1 5.86E-06 0.014601 3.841466 0.9037


182

B.21 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 100 SENSEX



Series : BSE100 SENSEX




None 0.005340 13.39093 15.49471 0.1012 At most 1 2.39E-05 0.059568 3.841466 0.8072




Trend assumption : Linear deterministic

trend





None 0.001846 4.611611 15.49471 0.8486 At most 1 4.03E-06 0.010024 3.841466 0.9199


183




Series : BSE200 CD




None 0.002392 5.976656 15.49471 0.6983 At most 1 5.18E-06 0.012886 3.841466 0.9094





Series : BSE200 CG




None 0.003843 9.642141 15.49471 0.3093 At most 1 2.23E-05 0.055569 3.841466 0.8136


184








None 0.002097 5.234457 15.49471 0.7834 At most 1 2.77E-06 0.006903 3.841466 0.9332





Series : BSE200 HC




None 0.002211 5.536414 15.49471 0.7495 At most 1 9.62E-06 0.023944 3.841466 0.8770


185




Series : BSE200 IT




None 0.005846 14.20479 15.49471 0.0775 At most 1 8.57E-05 0.204727 3.841466 0.6509









None 0.002574 6.687429 15.49471 0.6142 At most 1 0.000108 0.269478 3.841466 0.6037


186




Series : BSE200 OIL




None 0.002052 5.135241 15.49471 0.7943 At most 1 8.62E-06 0.021466 3.841466 0.8834









None 0.002937 7.332604 15.49471 0.5393 At most 1 3.67E-06 0.009130 3.841466 0.9235


187




Series : BSE500 CD




None 0.002620 6.553788 15.49471 0.6300 At most 1 8.28E-06 0.020607 3.841466 0.8858





Series : BSE500 CG




None 0.003782 9.501757 15.49471 0.3210 At most 1 2.67E-05 0.066413 3.841466 0.7966


188

B.33 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 500 FMCG







None 0.001964 4.896783 15.49471 0.8197 At most 1 8.51E-07 0.002118 3.841466 0.9596





Series : BSE500 HC




None 0.002164 5.414415 15.49471 0.7633 At most 1 7.97E-06 0.019849 3.841466 0.8879


189




Series : BSE500 IT




None 0.005927 14.42130 15.49471 0.0721 At most 1 9.42E-05 0.224859 3.841466 0.6354


B.36 Augmented Dickey-Fuller Test (ADF) finding for level for BSE 500 METAL







None 0.002183 5.814795 15.49471 0.7173 At most 1 0.000150 0.373800 3.841466 0.5409


190




Series : BSE500 OIL




None 0.001833 4.610884 15.49471 0.8487 At most 1 1.67E-05 0.041644 3.841466 0.8383









None 0.003088 7.706553 15.49471 0.4973 At most 1 2.34E-06 0.005832 3.841466 0.9384


191

B.39 Augmented Dickey-Fuller Test (ADF) finding for level for SENSEX CD



Series : SENSEX CD




None 0.002844 7.101850 15.49471 0.5658 At most 1 3.80E-06 0.009451 3.841466 0.9222


B.40 Augmented Dickey-Fuller Test (ADF) finding for level for SENSEX CG



Series : SENSEX CG




None 0.003961 9.902092 15.49471 0.2883 At most 1 7.88E-06 0.019610 3.841466 0.8885


192

B.41 Augmented Dickey-Fuller Test (ADF) finding for level for SENSEX FMCG



Series : SENSEX FMCG




None 0.002290 5.729782 15.49471 0.7272 At most 1 8.91E-06 0.022198 3.841466 0.8815


B.42 Augmented Dickey-Fuller Test (ADF) finding for level for SENSEX HC



Series : SENSEX HC




None 0.001965 4.941628 15.49471 0.8150 At most 1 1.80E-05 0.044852 3.841466 0.8322


193

B.43 Augmented Dickey-Fuller Test (ADF) finding for level for SENSEX IT



Series : SENSEX IT




None * 0.006466 15.71532 15.49471 0.0463 At most 1 9.35E-05 0.223376 3.841466 0.6365

Trace test indicates 1 cointegrating eqn(s) at the 0.05 level * denotes rejection of the hypothesis at the 0.05 level **MacKinnon-Haug-Michelis (1999) p-values

B.44 Augmented Dickey-Fuller Test (ADF) finding for level for SENSEX METAL



Series : SENSEX METAL




None 0.002276 5.906957 15.49471 0.7065 At most 1 9.40E-05 0.234142 3.841466 0.6285


194

B.45 Augmented Dickey-Fuller Test (ADF) finding for level for SENSEX OIL



Series : SENSEX OIL



Hypothesized Trace 0.05 No. of CE(s) Eigen value Statistic Critical Value Prob.**

None 0.002255 5.634215 15.49471 0.7383 At most 1 4.70E-06 0.011714 3.841466 0.9136


B.46 Augmented Dickey-Fuller Test (ADF) finding for level for CD CG



Series : CD CG




None 0.003297 8.381798 15.49471 0.4255 At most 1 6.40E-05 0.159419 3.841466 0.6897


195

B.47 Augmented Dickey-Fuller Test (ADF) finding for level for FMCG CD



Series : FMCG CD




None 0.001665 4.219045 15.49471 0.8851 At most 1 2.82E-05 0.070214 3.841466 0.7910


B.48 Augmented Dickey-Fuller Test (ADF) finding for level for CD HC



Series : CD HC




None 0.001760 4.418608 15.49471 0.8670 At most 1 1.27E-05 0.031623 3.841466 0.8588


196

B.49 Augmented Dickey-Fuller Test (ADF) finding for level for CD IT



Series : CD IT




None 0.005803 14.70690 15.49471 0.0655 At most 1 0.000338 0.807907 3.841466 0.3687


B.50 Augmented Dickey-Fuller Test (ADF) finding for level for CD METAL



Series : CD METAL




None 0.001127 2.853244 15.49471 0.9731 At most 1 1.80E-05 0.044706 3.841466 0.8325


197

B.51 Augmented Dickey-Fuller Test (ADF) finding for level for CD OIL



Series : CD OIL




None 0.001830 4.751111 15.49471 0.8347 At most 1 7.68E-05 0.191199 3.841466 0.6619


B.52 Augmented Dickey-Fuller Test (ADF) finding for level for CD FMCG



Series : CG FMCG




None 0.002666 6.658643 15.49471 0.6176 At most 1 4.23E-06 0.010544 3.841466 0.9179


198

B.53 Augmented Dickey-Fuller Test (ADF) finding for level for CD HC



Series : CG HC




None 0.001968 4.920088 15.49471 0.8172 At most 1 6.43E-06 0.016003 3.841466 0.8992


B.54 Augmented Dickey-Fuller Test (ADF) finding for level for CG IT



Series : CG IT




None 0.004218 10.15712 15.49471 0.2689 At most 1 2.65E-05 0.063314 3.841466 0.8013


199

B.55 Augmented Dickey-Fuller Test (ADF) finding for level for CG METAL



Series : CG METAL




None 0.002968 7.709080 15.49471 0.4970 At most 1 0.000124 0.308220 3.841466 0.5788


B.56 Augmented Dickey-Fuller Test (ADF) finding for level for CG OIL



Series : CG OIL




None 0.004668 11.72541 15.49471 0.1706 At most 1 3.02E-05 0.075303 3.841466 0.7838


200

B.57 Augmented Dickey-Fuller Test (ADF) finding for level for FMCG HC



Series : FMCG HC




None 0.001894 4.845169 15.49471 0.8250 At most 1 5.05E-05 0.125825 3.841466 0.7228


B.58 Augmented Dickey-Fuller Test (ADF) finding for level for FMCG IT



Series : FMCG IT




None 0.003383 8.165541 15.49471 0.4479 At most 1 3.10E-05 0.073974 3.841466 0.7856


201

B.59 Augmented Dickey-Fuller Test (ADF) finding for level for FMCG MENTAL



Series : FMCG METAL




None 0.002234 5.653407 15.49471 0.7360 At most 1 3.38E-05 0.084203 3.841466 0.7717


B.60 Augmented Dickey-Fuller Test (ADF) finding for level for FMCG OIL



Series : FMCG OIL




None 0.002555 6.380006 15.49471 0.6506 At most 1 4.33E-06 0.010791 3.841466 0.9170


202

B.61 Augmented Dickey-Fuller Test (ADF) finding for level for HC IT



Series : HC IT




None 0.002838 6.834076 15.49471 0.5970 At most 1 1.94E-05 0.046430 3.841466 0.8294


B.62 Augmented Dickey-Fuller Test (ADF) finding for level for HC MENTAL



Series : HC METAL




None 0.003310 8.267709 15.49471 0.4372 At most 1 4.73E-06 0.011772 3.841466 0.9134


203

B.63 Augmented Dickey-Fuller Test (ADF) finding for level for HC OIL



Series : HC OIL




None 0.002002 4.988903 15.49471 0.8100 At most 1 9.01E-09 2.24E-05 3.841466 0.9985


B.64 Augmented Dickey-Fuller Test (ADF) finding for level for IT METAL


Trend assumption : Linear deterministic

trend

Series : IT METAL




None 0.004148 10.15946 15.49471 0.2687 At most 1 9.73E-05 0.232430 3.841466 0.6297


204

B.65 Augmented Dickey-Fuller Test (ADF) finding for level for IT OIL



Series : IT OIL




None 0.003492 8.378462 15.49471 0.4258 At most 1 1.09E-05 0.026105 3.841466 0.8716


B.66 Augmented Dickey-Fuller Test (ADF) finding for level for OIL METAL



Series : OIL METAL




None 0.002139 5.392584 15.49471 0.7658 At most 1 2.40E-05 0.059769 3.841466 0.8068


205

C. MULTILATERAL CO-INTEGRATION: C.1 Augmented Dickey-Fuller Test (ADF) finding for level for OIL METAL IT

SENSEX HC FMCG CG CD BSE500 BSE200 BSE100 AUTO



Series : OIL METAL IT SENSEX HC FMCG

CG CD BSE500 BSE200 BSE100 AUTO




None * 0.039478 417.6811 334.9837 0.0000 At most 1 * 0.031411 321.4965 285.1425 0.0006 At most 2 * 0.022921 245.2836 239.2354 0.0260 At most 3 0.019541 189.9102 197.3709 0.1100 At most 4 0.017068 142.7832 159.5297 0.2805 At most 5 0.012202 101.6739 125.6154 0.5487 At most 6 0.010394 72.35678 95.75366 0.6406 At most 7 0.008466 47.40551 69.81889 0.7454 At most 8 0.005260 27.10295 47.85613 0.8503 At most 9 0.003398 14.50918 29.79707 0.8109 At most 10 0.002471 6.379869 15.49471 0.6506 At most 11 0.000198 0.472348 3.841466 0.4919


206

C.2 Augmented Dickey-Fuller Test (ADF) finding for level for AUTO BSE100

BSE200 BSE500 CD CG FMCG HC IT METAL OIL SENSEX



Series : AUTO BSE100 BSE200 BSE500 CD CG

FMCG HC IT METAL OIL SENSEX




None * 0.039478 417.6811 351.2421 0.0000 At most 1 * 0.031411 321.4965 300.2879 0.0006 At most 2 0.022921 245.2836 253.2348 0.0260 At most 3 0.019541 189.9102 210.0548 0.1100 At most 4 0.017068 142.7832 171.0905 0.2805 At most 5 0.012202 101.6739 135.9732 0.5487 At most 6 0.010394 72.35678 104.9615 0.6406 At most 7 0.008466 47.40551 77.81884 0.7454 At most 8 0.005260 27.10295 54.68150 0.8503 At most 9 0.003398 14.50918 35.45817 0.8109 At most 10 0.002471 6.379869 19.93711 0.6506 At most 11 0.000198 0.472348 6.634897 0.4919


chapter – 4 volatility of aggregate market...

Documents