You are on page 1of 31


Matching Products with endorsers: - An
assessment in the Indian context
Submitted to:

3r. RadhaKrishna
Submitted by:

Kabir Adatia (09BSHY3O346)
Apurva Singhi (09BSHY30822)
Shashi Bhushan (09BSHY30769)
Shashank Kapur (09BSHY30768)
Shubodeep Roy (09BSHY30799)
Amit Agarwal (09BSHY30070)
Himanshu Sharma (09BSHY3 03 )c c


me would like to acknowledge our marketing professor Dr.
Radhakrishna for his constant support, guidance and valuable
information which helped us a lot in completing this project.



     Introduction 4 Literature Review± 7 Literature Review-2 8 Methodology Reliability Statistics 3ata Analysis 3 Annexure 23 References 28 Appendix (Questionnaire) 29 c c c c .

Firms invest huge amounts as advertising expenditure for hiring the right celebrity. the over popularity of the celebrity sometimes overshadows the brand. there are few undesirable impacts of this practice on the brand. Studies associated with the market effect of celebrity endorsement suggest that consumers positively value the use of celebrity endorsers in the advertisements. Consumers perceive the brand as having superior quality because it has been endorsed by a credible source. there are around 130 television channels in India broadcasting over 3 million television commercials each year in India. jhe media- explosion can thus be easily demonstrated. an American family has at least one television set and a consumer is exposed to around 1000 ads per day1. jhis makes endorsement as one of the indictors of quality for any brand. More over. If the celebrity is involved in multiple endorsements. it should be more appropriately termed as over-communicated these days. However there lies uncertainty with respect to the returns that the company might be able to garner for the brand. Corporate credibility along with endorser credibility plays a significant role in the attitude of the consumer towards the brand and the advertisement respectively. getting the right celebrity to endorse the right brand. Hence. people forget 80% of the information in just 24 hours! Just imagine the plight of the marketer to make his brand shout over the deafening clutter of all the brands! Some where in the 80¶s. Likewise. 'Celebrity Endorsement' for the brand! Firms endorse celebrity for a variety of reasons. to say clearly whether the practice of celebrity endorsement impacts positively or negatively to the brand still remains a debate. A typical super-market in USA displays more than 12000 brands. Although it has been observed that the presence of a well-known personality helps in solving the problem of over-communication that is becoming more prominent these days.`  joday 'Celebrity Endorsement' has attracted immense debate on whether it really contributes to the brand building process or whether it is just another lazy tool to make the brand more visible in the minds of the consumers. It might be the life experience of the celebrity that fits the advertising message or the endorser's high appeal with the firm's consumer target group. Source Attractiveness jheory and Meaning jransfer jheory' provide a basis on which the methodology of celebrity endorsement works and also explains how the process of the celebrity endorsement influences the minds of the consumers. Firms invest significant c c . i. jhe theories like 'Source Credibility jheory. jhe issue of matching the values of the celebrity with the brand values is also very important.e. an Indian marketer found the solution. jhe society that we live in can not only be called secular or democratic. it tends to create confusion among consumers and hence negatively affects the perception of the advertisement and the brand. On the other hand.

Celebrity endorsement if used effectively. and in putting together brands and organizations with endorser qualities such as attractiveness. makes the brand stand out. and not an end in himself/herself. but a cursory orientation of a celebrity with a brand may prove to be claustrophobic for the brand. A celebrity is a means to an end. galvanizes brand recall and facilitates instant awareness. likeability. V c c c. Hence the right use of celebrity can escalate the Unique Selling Proposition of a brand to new heights. jo achieve this. the marketer needs to be really disciplined in choice of a celebrity.

Certain parameters that postulate compatibility between the celebrity and brand image are: ‰c c . Celebrities are no doubt good at generating attention. but the celebrity needs to match the product. creating positive attitudes to brands. they are rendered useless when it comes to the actual efficiency of the core product. On the other hand. recall and positive attitudes towards advertising provided that they are supporting a good idea and there is an explicit fit between them and the brand. A good brand campaign idea and an intrinsic link between the celebrity and the message are musts for a successful campaign.   c  c c c  c c c A celebrity is used to impart credibility and inspirational values to a brand. purchase intentions and actual sales.

xc Celebrity popularity. xc Celebrity physical attractiveness. xc Celebrity profession. xc Celebrity availability. xc Celebrity²Product match. xc Celebrity¶s fit with the brand image. xc mhether celebrity is a brand user. xc Celebrity controversy risk. xc Costs of acquiring the celebrity. xc Celebrity credibility. xc Celebrity²jarget audience match xc Celebrity associated values. c c c c c c c 0c c . xc Celebrity prior endorsements.

Kamins in his study collected data on seven dependent measures (advertiser believability. advertiser credibility. It was also found out that products which were meant to develop attractiveness was more effective if endorsed by an attractive celebrity but it there was no significant effect on products which were not meant to increase physical attractiveness if they were endorsed by an attractive celebrity. jo prove this point many research work has been done by many noted statisticians but the results which has been derived does not go in sync with what it was believed earlier. jhe most notable study which has been done in this regard was by KAMMINS in 1990s which is popularly known as the ³MAjCH UP HYPOjHESIS´. spokesperson believability. and purchase intention). From the very beginning it was suggested that the physical attractiveness of the celebrity is what influences the buying decision of the buyer.` O  ` ` Several studies have been done in the past to study the effects of celebrity endorsement of a brand. brand attitude. jhus it can be derived that expertise is what matters the most when a buyer decides to purchase a product £c c . According to match up hypothesis endorsers are more effective when there is a ³fit´ between the endorser and the endorsed product. For example in the survey a perfect fit was found out between an athlete endorsing energy bar and an actor endorsing a candy bar. spokesperson credibility. Ohanian in 1990 found out that among the three factors xc Physical Attractiveness xc jrustworthiness xc Expertise Expertise was the factor which had the greatest impact on the buying decisions. Finally it was found out that the physical attractiveness and the credibility of the endorser is what matters the most. jhis theory suggests that there is a positive correlation between the physical attractiveness of the endorser and the purchase decisions of the buyer. attitude toward the advertisement. A test conducted on students of business schools in USA revealed that while looking to an advertisement people generally look at the expertise the celebrity has. On the other hand an imperfect fit was found out between an actor endorsing energy bar and an athelete endorsing a candy bar.

as well as other measures of effectiveness. consumers¶ purchase intention. jhese actions suggest many US firms have bought into the premise that celebrity endorsers positively impact consumer attitudes towards an advertisement and the associated brand. jhe role of celebrity/product fit. KAIKAjI (1987) identified the prevalent types of celebrity endorsers. jhrough this study using ³meta analysis´ the effectiveness of celebrity endorsement is looked into. ERDOGAN (1999) reviewed the effectiveness of celebrities. advantages and disadvantages associated with celebrity endorsement.` O  ` `` Exploring the relationship between celebrity endorser effects and advertising effectiveness c O  : jhis study provides a quantitative summary of the relationship between celebrity endorser source effects and effectiveness in advertising. study setting. and celebrity attractiveness appears to capture the three most influential source effects on purchase intentions. c `   : cAbout 25% of US advertisements employ celebrity endorsers (Shimp 2000. and Federal jrade Commission guidelines. brand or a product. Importance of celebrity endorser does not lie in the fact they are used by the firms who wish to increase revenue but in how these celebrities add value to a company. brand attitudes and attitudes towards the advertisement. advantages of using celebrity endorsers. hazards associated with using celebrity endorsers. Celebrities transfer this meaning to the company. Results suggest negative celebrity information can be extremely detrimental to an advertising campaign. jhe Kruskal-mallis nonparametric test is used to identify the most influential celebrity endorser source effects on effectiveness. But no systematic efforts were put to quantitatively integrate this literature. jhis study takes into account a model named ³meaning transfer model´. interaction effects. jwo studies have been done by KAIKAjI (1987) and ERDOGON (1990) to study the effect of transfer of celebrity meaning and its effects. sample type. celebrity expertise. according to this model a celebrity develops a persona through the types of roles they play in the society as well as how they are portrayed in media. uc c . jhis study derives the relationship between use of a celebrity endorser and its resultant effects. and the application of the source credibility and source attractiveness models. product or the brand they endorse. Researchers have examined this transfer of celebrity meaning to the product and its resultant effectiveness by examining the source effects of Celebrity endorsers. and country of study are also included as moderators. jhe source credibility model composed of celebrity trustworthiness.

me have prepared questionnaire taking into consideration all aspects .Here we are using questionnaire to measure different aspect of human behavior.  c  . Its will also help us to understand different parameters on which effectiveness and brand value of an endorser depends. which explain the endorser compatibility with product.

given the small effects characteristic associated with behavioral research (Sawyer & Ball 1981. and (3) attitude towards advertisement. or other measures of behavioral intention and attitude. ¦c c . jo ensure that interpretation of the results was not influenced by transformation of the data. c O   Among the original 266 total effects. 185 were statistically significant (G < 0. Some studies used only one measure celebrity endorsement effectiveness. Hence. But others examined celebrity endorsement source effects across several measures. five experts were consulted to aid in evaluating studies for inclusion in this meta-analysis. (5) recall. jhe majority of studies in this meta-analysis measured celebrity endorsement effectiveness via the foremost categories of constructs: (1) purchase intention. what methodological variables produced the most variation in terms of significant findings? §4: How do interaction effects differ from main effects in celebrity endorsement source effects literature and what implications do these differences have for researchers? §5: mhat potentially rewarding topic areas remain relatively under-explored in the current celebrity endorser literature? c   : Focused was on Meta analysis that would provide a succinct look into celebrity endorser source effects and effect size. Exactly 60% of the studies used a US-based sample. and 52% used a student sample. (2) brand attitude. mith respect to methods characteristics. using two or more constructs categories to assess perceived celebrity endorsement effectiveness. jhese data were skewed. c §1: mhat are the most important source effects of celebrity endorsement? §2: mhat effect does the celebrity endorser/product fit have on celebrity endorsement effectiveness? §3: mithin the relevant research domain. milson & Sherrell 1993). (4) believability. milson & Sherrell 1993). Forty-four per cent of the retained studies examined celebrity/product fit. 86% of studies sampled reported main effects. Other studies included: measured effectiveness as actual purchase behavior. jhis was expected. 62% used a survey instrument. and (6) recognition.05). jhe Kruskal-mallis test was used to analyze the data from the non-normal population (Iman & Conover 1983. expected excess returns. a nonparametric procedure was performed on the weighted correlation coefficients.

Kruskal-mallis provides a powerful alternative to the .

-test for the equality of means milson & Sherrell (1993). jhe mean correlation of each variable is provided to permit comparison of effect sizes between variables.  normal for this study is 23.5% when used with non-normal populations (Siegal 1956).02. V .454 non-significant effects before the 185 significant results could be considered due to chance.  normal would have to be less than 1. the Kruskal-mallis test has an asymptotic efficiency of 95. Compared with the -test.05). the results suggest this study would have to find 14. jhus the results of this meta-analysis are statistically significant. In fact.645 ( G > 0. jhis robust result infers the use of published studies does not threaten the integrity of this study¶s findings. jo render  normal for z-transformed correlation coefficients non-significant. Publication bias was analyzed using Rosenthal¶s (1991) fail-safe N.

xc Vonstant Sum Scale Respondents might be asked to divide a constant sum to indicate the relative importance of the attributes. SCALES TO BE USED xc Vategory Scale Some rating scales have only two response categories: agree and disagree. and µexpertise¶ along with µattractiveness¶ each exercised more influence on effectiveness than did the celebrity µcredibility¶ source effect. Even more information is provided if the categories are ordered according to a descriptive or evaluative dimension. Expanding the response categories provides the respondent more flexibility in the rating task. the revelation can dilute the equity of the product/brand associated with the celebrity c xc jhe results of this meta-analysis likewise infer that positive celebrity information and image can also transfer to the product/brand xc jhis meta-analysis revealed that celebrity µtrustworthiness¶.  jhe conclusions from the study are as following xc jhat when negative information about a celebrity endorser emerges. è c c .

or simple data like names and addresses. xc Sampling 3istribution In statistics. and the sample size used. based on a random sample. especially for the purposes of statistical inference.   jhe data analysis will include the following:- xc Sampling Sampling is that part of statistical practice concerned with the selection of individual observations intended to yield some knowledge about a population of concern. to pass information on to others. a sampling distribution is the probability distribution of a given statistic (a numerical quantity calculated from the data values in a sample). Primarily. sequences of numbers. jhe sampling distribution depends on the distribution of the population. the statistic being considered. usually a computer program. to make decisions about important issues. èèc c . jhe purpose of data collection is to obtain information to keep on record. jhe sampling distribution may be considered as the distribution of the statistic for all possible samples of a given size. xc 3ata Vollection Data collection is a term used to describe a process of preparing and collecting data. data is collected to provide information regarding a specific topic xc 3ata Entry Data entry is the act of transcribing some form of data into another form. information off spreadsheets from another computer program. Forms of data that people might transcribe include handwritten documents. letters and symbols that build a program.

 . It is sometimes called confirmatory data analysis. what is the probability of observing a value for the test statistic that is at least as extreme as the value that was actually observed? One use of hypothesis testing is deciding whether experimental results contain enough information to cast doubt on conventional wisdom. Infrequency probability. m chave collected the data on the basis of our questionnaire and then we have done several testing initially to find out the reliability of questionnaire. ones that answer the question Assuming that the null hypothesis is true. these decisions are almost always made using null- hypothesis tests. xc '-Tests/ Hypothesis test A statistical hypothesis test is a method of making statistical decisions using experimental data. in contrast to exploratory data analysis. me are also presenting some of hypothesis which we have done till date. that is.


 Reliability refers to the property of a measurement instrument that causes it to give similar results for similar inputs. c V c cc c V c  c .

4% reliable which in turn means that whatever result provided by the testing of survey will be authentic and can be consider as reliablec c c èŒc c . c c ccc c c c c After running the collected data in SPSS for reliability testing.854. value of Cronbach's alpha is reported in the Reliability Statistics table is . It means questionnaire used for the testing is 85.

As a result it is easier for the consumers to connect to the following products and hence there is no difference between the means of the respondents. glamour and fashion.OO` c c cc  c  c c Mapping Katrina Kaif with LUX ›c Strongly disagree ›c Disagree ›c Neutral ›c Agree ›c Strongly agree Mapping Hrithik Roshan with CINjHOL ›c Strongly disagree ›c Disagree ›c Neutral ›c Agree ›c Strongly agree In this question we are trying to determine whether consumers are able to map Katrina Kaif with LUX which is a beauty soap and Hrithik Roshan with cinthol which is deodorant soap. mhereas the z critical is 1.3103549. jhe z observed comes out to be 0.96 which means that we accept our null hypothesis. (Annexure I) èc c . jhis feature can be attributed to the fact that both the celebrities are known face and both are Bollywood stars which can be connected with style. me have conducted a hypothesis testing where the null hypothesis is that consumers can relate both the products with their respective brand ambassadors.

c   c .

(Annexure II) èc c . jhus we can conclude that Dettol may require an expert to endorse it but Johnson and Johnson do not require a celebrity to endorse it. c c  cc  ccV c c  c c  c Mapping renowned doctor with DEjjOL ›c Strongly disagree ›c Disagree ›c Neutral ›c Agree ›c Strongly agree Mapping Mother and child with JOHNSON & JOHNSON ›c Strongly disagree ›c Disagree ›c Neutral ›c Agree ›c Strongly agree In the above two questions we try to determine what effects does it have on the consumers if Dettol which is a medicinal soap is endorsed by a Renowned doctor and Johnson and Johnson which is a soap meant for infants.96. jhe z observed is 0.753256272 whereas the z critical is 1. me have conducted a hypothesis testing where the null hypothesis is that the means of the respondent agreeing to Dettol being endorsed by a renowned doctor whereas Johnson and Johnson being endorsed by a mother and a child. jhis can be due to the fact that since Dettol is a medicinal soap so the product being endorsed by a person who has the expertise will help the consumers to relate to the product well whereas Johnson and Johnson is meant for the infants which has an emotional quotient behind it thus consumers do not require any celebrity to endorse the product. jherefore we accept our null hypothesis which states that the means of the respondent saying Dettol to be endorsed by a renowned doctor is same as that of the respondents saying Johnson and Johnson to be endorsed by a mother and child.

 cc c.


c c  c .

cc  c .

 c  .

c c cc .

c  cc .

Here our null hypothesis is that all the attributes are having same effect on consumer and alternative hypothesis is that they are having different effect. mord of mouth. jhat is why we reject null hypothesis and accept alternative i. After calculation of estimation test we found out that F critical is less than F observation. Celebrity. Publicity) might have more importance for the consumers. jhis test is important as it helps us to know the preferences of consumers. different attributes are having different effect on consumers.e. c c c Price ____________________ §uality __________________ Brand Name ______________ Celebrity Endorsed _________ mord of mouth ____________ Publicity __________________ jotal 100 In this question we try to prove the effect of different attribute on consumer or whether different features are having different effect. For that we performed anova testing. Some of these (§uality. Company should look upon the factors which really matter for consumers as these things are related to the success of any product.(ANNEXURE III) Renowned 3octor VS Ayurvedic Person 1)c Mapping renowned doctor with DEjjOL ›c Strongly disagree ›c Disagree ›c Neutral ›c Agree ›c Strongly agree è‰c c . Accordingly we can place celebrity for product emphasizing that attribute which is of higher importance for the consumers. Brand name.

For that we perform hypothesis testing and we relate their mean on certain significance level.5. 2)c Mapping renowned Ayurvedic person with MEDIMIX ›c Strongly disagree ›c Disagree ›c Neutral ›c Agree ›c Strongly agree In above given questions we are trying to check that whether a renowned doctor for dettol and an ayurvedic person is having same effect on consumers. (ANNEXURE IV)  c c A celebrity endorsing multiple brands makes it difficult for a buyer to relate it with a particular product ›c Strongly disagree ›c Disagree ›c Neutral ›c Agree ›c Strongly agree In this question we try to find out whether a celebrity endorsing more than one product will have same effect for all the products or it actually create confusion among consumer. we reject null hypothesis and we accept alternative hypothesis which means that mean of people saying renowned doctor maps with Dettol is greater than mean of people saying ayurvedic person maps with Medimix. As here we are quantifying è0c c . For this here we performed hypothesis test for mean. Here we have taken null hypothesis less than or equal to 2.e. So a renowned doctor has greater influence in buying decision of people preferring Dettol than an ayurvedic person¶s influence in buying decision of people preferring Medimix. After testing we found out that ëobs > ëcritical i. From this we can inferred that for dettol endorsing a doctor will be more wise decision as it is having greater influence on people.

5 is neutral and below it will fall under disagreement and above it will fall under agreement. jherefore 2. therefore we reject null hypothesis i. we accept alternative hypothesis which means that more people agree that celebrity endorsing multiple brands makes it difficult for a buyer to relate it with a particular product. me found out that ëobs > ëcritical .their intensity of agreement as 1. As a result of this confusion effectiveness of celebrity decreases and ultimately which affects the sales.e. It proves that if any celebrity endorses for more than one product then it is very difficult for consumer to relate his personality with any of them. 2 and so on up to 5. (ANNEXURE V) c c c è£c c .

Ô  T   P : L.


5 Sample Mean of Male: xmale = 2. Given question is: §) I get to buy soap because a celebrity endorsed it ›c Strongly disagree ›c Disagree ›c Neutral ›c Agree ›c Strongly agree After survey.05 Here we have two tailed test that we have shown later on.5096 èuc c . Sample Mean of Female: xfemale = 2. male) H0)/ ıfemale-male = -1. we calculated by above mentioned test in which Null Hypothesis: H0 : female = male Alternative Hypothesis: H1 : female  male Į = 0.00409 Standard deviation of male: smale = 1. For that we prepared a questionnaire and out of which we try to check whether null hypothesis is accepted or not. we have a large sample size we use here hypothesis testing of proportion between male and female.788235 nfemale = 62 nmale = 85 Standard deviation of female: sfemale = 1. As here.19093 Zcrititcal = ((xfemale ± xmale) ± ( female .310163 ıfemale-male = sqrt((ıfemale^2/nfemale) + (ımale^2/nmale)) = 0.  Here we are testing that whether there is any difference in buying decision between male and female of celebrity endorsement for soaps.

Zobs = -1. therefore we accept null hypothesis i. celebrity endorsement have same effect on male and female while buying soap.e. It means there is no significant difference between male and female in buying decision. c c è¦c c .65 After calculation we can see that Zcrititcal > Zobs.

62585034 xpublicity = 11.17007 sprice^2 = 95.0544218 xcelebrity endorsed = 10. me used Anova in the above question as we wanted to check whether weightage of all the variables affecting the buying decisions of the respondents are same or not. Below the following calculations have been provided : H0 : price = quality = brandname = celebrity endorsed = word of mouth = publicity H : price. celebrity endorsed. Divide 100 points according to your preference in following factors which you feel will affect your buying decision of soap Price _____________________ §uality_____________________ Brand Name________________ Celebrity Endorsed__________ mord of Mouth______________ Publicity____________________ jotal 100 In this question we used constant sum scale and asked the respondents to provide weightage to the following factors.55102041 xword of mouth = 10. publicity are not equal nprice = nquality = nbrandname = ncelebrity endorsed = nword of mouth = npublicity = 147 xprice = 19.4199 sbrandname^2 = 135.7414 xquality = 27. word of mouth .65306 xbrandname = 20. quality.O Oc !" c §. jhis way we can find which of the following factors affects the buying decision of the consumer most. brandname.733319 Œ c c .28888 squality^2 = 199.

83850527 spublicity^2 = 58.6326 k=6 nj = 882 ESTIMATE OF BETWEEN VOLUMN VARIANVE ı^2b = ™(nj(xj ± grand mean)^2/(k.479 ESTIMATE OF WITHIN VOLUMN VARIANVE ı^2w = ™((nj.) = 7224.21 Œèc c .9896 NUMERATOR 3EGREES OF FREE3OM Number of degrees of freedom in the numerator of the F ratio = (k-1) = 6-1 = 5 3ENOMINATOR 3EGREES OF FREE3OM Number of degrees of freedom in the denominator of the F ratio = (nj ± k) = 882-6 = 876 Fobs = 2.scelebrity endorsed^2 = 48.20457087 sword of mouth^2 = 40.33971 Fcritical = between column variance/within column variance = ı^2b/ ı^2w = 74.)/(nT-k))sj^2 = 96.55307 Grand mean = 16.

e.Vonclusion c From the above calculations we can see that. jhis means that some of the variables affect the buying decision of the consumers more than the others. Fcritical > Fobs So we reject null hypothesis i. c c c c c c c c c c c c c c ŒŒc c . In the final report we would be testing individual factors in comparison to the other factors and derive which of the factors affect the most and by how much. mean of all variables are not equal one of the variable has higher mean or is given more importance compared to other.

05 xkatrina = 3.3537415 xhrithik = 3.96 Œc c .O ANNEXURE I H0 : µkatrina = µhrithik H : µkatrina > µhrithik Į = 0.µhrithik)* H0)/ ıkatrina- hrithik = 0.186699816 n = n2 = 147 ıkatrina-hrithik = sqrt((ıkatrina^2/n )+( ıhrithik^2/n2)) = 0.0650276 ıhrithik = 1.31292517 ıkatrina = 1.3103549 ëcritical = .131515 ëobs = ((xkatrina .xhrithik) ± (µkatrina .

133811232 n = n2 = 147 ırenowned doctor ± mother & child = sqrt((ırenowned doctor^2/n )+( ımother & child^2/n2)) = 0.x mother & child ) ± (µrenowned doctor .65306 xbrandname = 20.28888 squality^2 = 99. µcelebrity endorsed.753256272 'critical = .20457087 sword of mouth^2 = 40.03169418 ıayurvedic person = 1.74 4 xquality = 27.843537415 xayurvedic person = 3.74829932 ırenowned doctor = 1.05442 8 xcelebrity endorsed = 0. µpublicity are not equal nprice = nquality = nbrandname = ncelebrity endorsed = nword of mouth = npublicity = 47 xprice = 9.96 c c ANNEXURE III H0 : µprice = µquality = µbrandname = µcelebrity endorsed = µword of mouth = µpublicity H : µprice.62585034 xpublicity = .µ mother & child )* H0)/ırenowned doctor ± mother & child = 0. µword of mouth .55 0204 xword of mouth = 0. µquality. 7007 sprice^2 = 95.83850527 Œc c .126435184 ëobs = ((xrenowned doctor .7333 9 scelebrity endorsed^2 = 48.4 99 sbrandname^2 = 35.ANNEXURE II H0 : µrenowned doctor = µmother & child H : µrenowned doctor > µmother & child Į = 0.05 xrenowned doctor = 3. µbrandname.

55307 Grand mean = 6.)/(nT-k))sj^2 = 96.479 ESTIMATE OF WITHIN VOLUMN VARIANVE ı^2w = ™((nj.6326 k=6 nT = 882 ESTTIMATE OF BETWEEN VOLUMN VARIANVE ı^2b = ™(nj(xj ± grand mean)^2/(k.= 5 3ENOMINATOR 3EGREES OF FREE3OM Number of degrees of freedom in the denominator of the F ratio = (nT ± k) = 882-6 = 876 Fcritical = 2.9896 NUMERATOR 3EGREES OF FREE3OM Number of degrees of freedom in the numerator of the F ratio = (k.spublicity^2 = 58.) = 6.) = 7224.3397 Fobs = between column variance/within column variance = ı^2b/ ı^2w = 74.2 Œ‰c c .

123828672 ëobs = ((xrenowned doctor .46100319 ëcritical = .xayurvedic person ) ± (µrenowned doctor .090705047 n = n2 = 147 ırenowned doctor ± ayurvedic person = sqrt((ırenowned doctor^2/n )+( ıayurvedic person^2/n2)) = 0.05 xrenowned doctor = 3.µayurvedic person)* H0)/ırenowned doctor ± ayurvedic person = 3.03169418 ıayurvedic person = 1.96 Œ0c c .ANNEXURE IV H0 : µrenowned doctor = µayurvedic person H : µrenowned doctor > µayurvedic person Į = 0.843537415 xayurvedic person = 3.414965986 ırenowned doctor = 1.

96 Œ£c c .5 H : µmultiple brands > 2.086584504 ëobs = (xmultiple brands .049781318 ıxmultiple brands = ımultiple brands/sqrt(n) = 0.84577319 'critical = .µ H0)/ ıxmultiple brands = 12.ANNEXURE V H0 : µmultiple brands ” 2.5 Į = 0.612244898 ımultiple brands = 1.05 n = 47 xmultiple brands = 3.

"Celebrity Endorsement: A Literature Review". [   .Jack jrout and Al Ries 2 Erdogan (1999).   1 Positioning: A battle for mind .


291-314 3 www. Effective Advertising: Understanding mhen. Grant (1989). 15. "mho is the Celebrity Endorser?" [         .. 2003 5 jellis. and mhy Advertising works 6 McCracken. 4 Hindu Business Line.thedayaftertomorrow.

and Event Sponsorship as advertising cues affecting consumer Pre purchase attitude"..magindia. "Brand ± 2003 8 www. [   .com 9 www. May 13. 310-321. 10 Business Standard. 16 (December).com 12 Dean (1999). 7 www.blonnet.indiantelevision. 2005 11 www.synovate.

"jhe Impact of Corporate Credibility and Celebrity Credibility on Consumer Reaction to Advertisements and Brands". 1-12 13 Goldsmith. Lafferty and Newell (2000).  . [   . Number 3. Volume XXVIII.

number 3.  . Rangan (1997) June. Zafer Erdogan. Mathur and 16 B. "jhe mealth Effects Associated with a Celebrity Endorser: jhe Michael Jordan Phenomena".blonnet. [   . Journal of Advertising Research. Volume XXIX. "Selecting Celebrity Endorsers: jhe Practitioner's Perspective". K. 15 www. Michael J. Baker and Stephen jag (2001) June. I. 43-54 14 L. Marhur.


com ± article 'Celebrity Endorsements in brands 19 jripp. [   . Jensen and Carlson (1994) March.. "jhe Effect of Multiple Product Endorsements by Celebrities on Consumers' Attitude and Intentions". 39-48 18 indiainfoline.



535-547 c Œuc c . Vol 20..

O` QUESTIONNAIRE èc   cc ›c   cc ›c R   cc Œc  cè cc cc  c    cc c c .


c  c c c  c  c c cc c  cc   cc  c  cc    c cc mcc .

cc   cc  ccccccccccccccccccccccccccccè c c c cc c c c   c c   c  cc ›c  c  cc ›c   c ›c   c ›c O c ›c  c  c c  c  c c .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c ‰c c  c.

 c  .


 c  cc   c  c .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c 0c  c.


c .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c c Œ¦c c .

£c c  c.

 c  .


 c  cc   c  c .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c uc  c   cc .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c ¦c c  c.

 c  .


 c c   c  c .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c è c c   cO  c c .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c èècc  c.

 c  .


 c c   c  c .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c èŒc c.

c c.

c .

c c!c c ›c  c  c ›c   c ›c   c ›c O c ›c  c  c ècc  c.

 c  .

cc c!c cc.

 c c   c  c .

cc ›c  c  c ›c   c ›c   c ›c O c ›c  c  c  c c .

ècc c c c c .


cc  c c c   c .

ccc c  cc .

cc c  c ›c  c  c ›c   c ›c   c ›c O c ›c  c  c è‰cO c  c  cc c  cc.

c   c  c   c ›c ë c ›c c è0cOc   c cc  c  c  cc cc c cc   cc .

c c   c  c ›c  c  c ›c   c ›c   c ›c O c ›c  c  c èc c .