Recommended
Recommended
More Related Content
Similar to Scatter PlotScatter PlotWorking141396151261212696.docx
Similar to Scatter PlotScatter PlotWorking141396151261212696.docx (20)
More from anhlodge
More from anhlodge (20)
Recently uploaded
Recently uploaded (20)
Scatter PlotScatter PlotWorking141396151261212696.docx
- 1. Scatter Plot Scatter Plot Working 14 13 9 6 15 12 6 12 12 6 9 6 6 3 3 13 17 6 12 12 12 15 18 15 13 18 3 12 19 14 13 13 13 12 8 6 13 16 15 6 12 6 13 12 17 7 6 12 14 12 13 15 13 13 12 12 18 17 12 10 11 13 12 14 14 17 12 14 16 13 12 18 13 18 15 9 12 17 16 15 12 7 16 16 14 19 13 12 13 16 16 14 15 12 16 18 12 13 17 17 9 9 14 12 14 10 3 12 15 13 18 13 13 8 7 7 12 12 13 13 13 17 13 13 7 15 10 19 7 16 12 13 12 9 12 10 12 6 15 13 13 3 13 12 16 12 6 12 13 14 12 12 16 12 9 12 19 6 16 3 3 9 3 16 13 3 9 12 6 3 11 16 15 22 12 6 13 13 13 16 12 20 13 13 11 13 6 10 13 3 6 3 12 6 3 3 17 6 10 3 8 6 13 12 14 18 13 14 16 13 16 13 13 20 15 17 15 12 9 3 12 12 13 15 18 13 11 17 19 13 16 14 14 14 12 13 14 15 19 12 16 13 15 12 12 13 15 15 12 12 19 3 16 13 11 12 9 9 6 12 14 8 10 17 12 13 12 16 3 15 12 12 13 7 9 3 6 12 13 6 6 3 12 20 13 11 15 9 19 6 12 12 13 15 12 12 12 12 14 15 13 13 13 12 14 9 13 13 12 3 16 12 13 12 15 16 12 9 6 12 9 7 6 12 12 7 6 13 13 14 13 10 13 13 6 3 3 12 6 3 10 6 3 6 3 3 10 3 9 10 14 9 15 18 9 12 15 12 12 19 12 10 13 14 6 13 13 13 14 11 13 3 7 10 13 12 12 12 16 13 13 16 13
- 2. 12 13 13 7 14 13 12 10 12 12 14 15 14 10 12 12 15 12 13 3 3 18 12 12 10 6 12 13 6 15 13 13 12 13 19 12 18 15 12 10 15 6 14 17 11 12 13 12 13 13 9 19 16 6 15 13 14 11 14 7 13 12 16 12 13 18 7 16 4 13 13 10 13 13 12 12 16 13 12 15 13 12 13 6 20 13 12 13 13 12 12 13 15 13 16 12 15 3 13 3 13 16 10 15 6 12 13 10 13 15 10 12 13 16 14 12 16 13 13 14 13 12 13 17 16 12 9 15 13 16 19 13 17 12 13 16 12 12 15 12 11 12 16 16 12 12 12 15 18 12 12 13 13 15 13 13 3 13 12 16 12 12 15 15 15 10 12 12 12 15 10 10 9 12 11 10 12 14 6 20 20 30 40 33 0 40 40 40 42 40 40 55 40 15.5 10 0 48 10 25 0 0 35 0 25 30 45 25 35 20 30 20 35 30 40 36 20 0 40 20 0 30 12 20 40 48 25 20 30 15 20 20 20 0 35 16 20 8 34 0 0 20 25 0 40 20 20 25 16 20 20 27 30 15 0 30 12 15 5 12 30 30 8 25 10 0 35 30 15 0 20 15 15 25 21 0 25 35 25 20 20 36 25 25 30 40 45 20 20 30 45 35 24 40 40 45 20 13 20 16 0 20 25 10 40 40 35 12 20 15 40 18 0 30 40 0 38 40 8 25 20 55 25 10 12 20 30 32 40 25 37 15 26 40 40 27.5 18 40 0 50 40 40 45 20 40 40 47 32 40 50 20 20 15 25 21 45 32 24 20 0 24 5 27.5 30 30 25 42 30 24 40 40 65 0 55 50 48 8 40 32 55 7 40 0 32 17.5 8 0 30 0 30 25 20 0 0 25 28 0 19 50 55 30 0 25 7 20 40 12 25 21 30 0 33 30 0 38 8 20 12 5 22 15 12 16 0 0 35 20 25 21 32 25 40
- 3. 12 20 24 35 41 40 40 28 48 35 50 40 6 0 35 10 48 0 37 30 25 40 50 50 40 20 0 45 64 40 25 0 40 25 0 55 40 40 40 25 20 10 0 15 10 20 35 30 20 25 30 32 15 40 14 0 24 17.5 12 17.5 22 40 30 20 20 35 40 0 27 24 50 32 20 50 45 36 24 40 23 25 40 30 50 47.5 42 20 36 50 40 40 40 30 40 40 45 50 40 32 28 45 15 15 45 15 20 40 35 0 40 45 15 30 32 18 12 25 20 30 40 70 36 14 15 2 20 20 0 25 20 20 0 0 0 22.5 33 20 37 0 24 30 25 20 0 0 6 32 20 30 10 50 45 50 8 30 40 19 50 25 10 40 0 20 8 0 10 0 32 25 40 8 20 30 18 20 30 40 5 0 10 20 20 27.5 0 10 40 0 16 8 0 21 40 15 16 15 30 24 22 20 5 25 0 0 15 6 20 17 12 20 15 32 20 30 0 20 40 0 13 15 20 30 0 14 20 0 25 12 15 20 23 0 40 0 3 40 12 25 37 40 20 24 0 20 0 35 25 0 40 24 0 22 0 25 5 31 0 20 15 42.5 10 25 16 20 6 36 25 0 20 40 30 20 16 38 30 30 6 40 30 0 0 16 24 0 0 25 35 0 5 60 5 0 0 25 0 9 14 9 15 30 20 15 30 0 20 16 15 20 10 0 20 23 X Y PlotDataCredit hrsWorking1420132093064015331206401240124064294064065 5340315.513101706481210122512015018351501325183034512 25193514201330132013351230840636132016015406201206301 31212201740748625122014301215132015201320130123512161 82017812341001101320122514014401720122014251616132012 20182713301815150930121217151651512123073016816251410 19013351230131516016201415151512251621180122513351725
- 6. SLRSimple Linear Regression AnalysisCalculationsb1, b0 Coefficients-2.175749.4721Regression Statisticsb1, b0 Standard Error0.13811.7363Multiple R0.5543R Square, Standard Error0.307212.4008R Square0.3072F, Residual df248.3272560.0000Adjusted R Square0.3060Regression SS, Residual SS38187.667286116.5819Standard Error12.4008Observations562Confidence level95%t Critical Value1.9642ANOVAHalf Width b03.4104dfSSMSFSignificance FHalf Width b10.2712Regression138187.667238187.6672248.32720.0000Res idual56086116.5819153.7796Total561124304.2491Coefficients Standard Errort StatP-valueLower 95%Upper 95%Lower 95%Upper 95%Intercept49.47211.736328.49340.000046.061752.882546.06 1752.88246Credit hrs-2.17570.1381-15.75840.0000-2.4469- 1.9045-2.4469-1.90454 DataCopy3Credit hrs14139615126121269663313176121212151815131831219141 31313128613161561261312177612141213151313121218171210 11131214141712141613121813181591217161512716161419131 21316161415121618121317179914121410312151318131387712 12131313171313715101971612131291210126151313313121612 61213141212161291219616339316133912631116152212613131 31612201313111361013363126331761038613121418131416131 61313201517151293121213151813111719131614141412131415 19121613151212131515121219316131112996121481017121312 16315121213793612136631220131115919612121315121212121 41513131312149131312316121312151612961297612127613131 41310131363312631063633103910149151891215121219121013 14613131314111337101312121216131316131213137141312101 21214151410121215121333181212106121361513131213191218 15121015614171112131213139191661513141114713121612131 87164131310131312121613121513121362013121313121213151 31612153133131610156121310131510121316141216131314131 21317161291513161913171213161212151211121616121212151 81212131315131331312161212151515101212121510109121110
- 7. 12146 CompleteStatistics3Credi HoursCredit hrsMean11.9911032028Median12.5Mode12Minimum3Maximum 22Range19Variance14.3796Standard Deviation3.7920Coeff. of Variation31.62%Skewness- 0.6653Kurtosis0.3533Count562Standard Error0.1600 DataCopy2right-handedleft- handed204020553025402533450040204025420408400404015.5 12108025482010200200203516020301225403540205030402020 35453032403036652055025402820553025123040334830200302 51535204020402048352016402003440050040205025302050202 02518161220702022703061520040304015205201221305302510 20003540300151602420015015202521025352520362525304045 30453524404045201302510404035201540180304003840825205 525101220303225371526404027.5180404540404732405020201 525212420024527.53030254224404005550488403274003217.5 80300302520000195030072040122521038820125221512160035 20213225401220244128355040603510480373025405050400456 4402502505540404025201015102035302025303215401402417. 51217.5223020203540027245032204536244023253047.542203 65040404040404540322845151545154035040451530322520304 03614152020025202000022.53320370243025200323010504550 83040195025100208010032254082030182030501027.50104001 68040151615302422200015617122015322030020401315203001 42002512152023040034012253720240200352504024022025531 201542.5102520636250204030201638303064030001600253556 0502509149153015300201615201002023 CompleteStatistics2Working Hours/Handedright-handedleft- handedMean22.92355371926.2307692308Median22.2525Mode0 20Minimum00Maximum6470Range6470Variance209.2830292.0 240Standard Deviation14.466617.0887Coeff. of Variation63.11%65.15%Skewness0.02800.2312Kurtosis-0.7570- 0.4776Count48478Standard Error0.65761.9349 DataCopyWorking20203040330404040424040554015.51004810 25003502530452535203020353040362004020030122040482520 30152020200351620834002025040202025162020273015030121
- 8. 55123030825100353015020151525210253525202036252530404 52020304535244040452013201602025104040351220154018030 400384082520552510122030324025371526404027.5184005040 404520404047324050202015252145322420024527.5303025423 0244040650555048840325574003217.580300302520002528019 50553002572040122521300333003882012522151216003520252 13225401220243541404028483550406035104803730254050504 02004564402504025055404040252010015102035302025303215 401402417.51217.5224030202035400272450322050453624402 32540305047.54220365040404030404045504032284515154515 20403504045153032181225203040703614152202002520200002 2.533203702430252000632203010504550830401950251040020 8010032254082030182030405010202027.501040016802140151 61530242220525001562017122015322030020400131520300142 00251215202304003401225374020240200352504024022025531 0201542.510251620636250204030201638303064030001624002 5350560500250914915302015300201615201002023 CompleteStatisticsWorking HoursWorkingMean23.3825622776Median23Mode0Minimum0 Maximum70Range70Variance221.5762Standard Deviation14.8854Coeff. of Variation63.66%Skewness0.0987Kurtosis- 0.6143Count562Standard Error0.6279 Variable INFOA survey for a random sample of 562 community college students at a large institutionowner:bobbyjacksonStatCrucnlink:<A href="http://www.statcrunch.com/5.0/index.php?dataid=517207 ">All Survey Data Updated 2011 Fall.xls</A>variablesWorkingHours of work per weekAgeAge of studentCredit Hrs No. of credits enrolled forWebHours on Web per weekExerciseHours exercising per wekReadingHours reading per weekHanded1=right-handed0=left- handedGender(Male, Female)Majorlist of several majors FiveNumbersWorking HoursFive-Number SummaryMinimum0First Quartile14Median23Third Quartile35Maximum70
- 9. BoxPlot Working Hours Working 0 0 0 0.5 1 1.5 14 14 14 0.5 1 1.5 23 23 23 0.5 1 1.5 35 35 35 0.5 1 1.5 70 70 70 0.5 1 1.5 0 70 1 1 14 35 0.5 0.5 14 35 1.5 1.5 ForBoxPlot00.50101.5140.5141141.5230.5231231.5350.535135 1.5700.5701701.501701140.5350.5141.5351.5 FiveNumbers2Working Hours/HandedFive-Number Summaryright-handedleft-handedMinimum00First Quartile1316Median22.2525Third Quartile3540Maximum6470 BoxPlot2 Working Hours/Handed right-handed 0 0 0 0.5 1 1.5 13 13 13 0.5 1 1.5 22.25 22.25 22.25 0.5 1 1.5 35 35 35 0.5 1 1.5 64 64 64 0.5 1 1.5 0 64 1 1 13 35 0.5 0.5 13 35 1.5 1.5 left-handed 0 0 0 2 2.5 3 16 16 16 2 2.5 3 25 25 25 2 2.5 3 40 40 40 2 2.5 3 70 70 70 2 2.5 3 0 70 2.5 2.5 16 40 2 2 16 40 3 3 ForBoxPlot200.5020102.501.503130.5162131162.5131.516322. 250.525222.251252.522.251.5253350.5402351402.5351.540364 0.5702641702.5641.57030102.5641702.5130.5162350.5402131. 5163351.5403 FiveNumbers3Credit HoursFive-Number SummaryMinimum3First Quartile11Median12.5Third
- 10. Quartile14Maximum22 BoxPlot3 Credit Hours Credit hrs 3 3 3 0.5 1 1.5 11 11 11 0.5 1 1.5 12.5 12.5 12.5 0.5 1 1.5 14 14 14 0.5 1 1.5 22 22 22 0.5 1 1.5 3 22 1 1 11 14 0.5 0.5 11 14 1.5 1.5 ForBoxPlot330.53131.5110.5111111.512.50.512.5112.51.5140.5 141141.5220.5221221.531221110.5140.5111.5141.5 DataCopy4Handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedleft-handedright- handedright-handedright-handedright-handedleft-handedright- handedright-handedright-handedright-handedright-handedright- handedleft-handedright-handedright-handedright-handedright- handedleft-handedright-handedleft-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedleft-handedright-handedright-handedleft- handedright-handedright-handedleft-handedright-handedright- handedright-handedright-handedright-handedright-handedleft- handedright-handedright-handedright-handedleft-handedright- handedright-handedright-handedright-handedright-handedleft- handedleft-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedleft-handedright-handedright- handedright-handedright-handedright-handedleft-handedleft- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedleft-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedleft-handedleft- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedleft-
- 13. handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedleft-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedleft-handedright-handedright- handedright-handedright-handedright-handedleft-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handedleft-handedright- handedright-handedright-handedright-handedleft-handedright- handedright-handedright-handedleft-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedleft-handedright-handedright-handedright- handedright-handedright-handedright-handedright-handedright- handedright-handedright-handedright-handed Bar Chart Handed Total left-handed right-handed 78 484 Handed OneWayTableHandedCount of HandedHandedTotalleft- handed78right-handed484Grand Total562 SideBySide Handed/Gender female left-handed right-handed 44 296 male left- handed right-handed 34 188 TwoWayTableHanded/GenderCount of HandedGenderHandedfemalemaleGrand Totalleft- handed443478right-handed296188484Grand Total340222562 Comm College DATAWorkingAgeCredit hrsWebExerciseReadingHandedCODEHandedGenderMajor2018
- 29. handedfemaleEdu141815151521right- handedmaleOth919153201right- handedfemaleEdu15191011001right- handedmaleMed3020120101right- handedfemaleOth20191210230left- handedfemaleMed1521125761right- handedfemaleMed30221541001right- handedfemaleMed0271010221right- handedfemaleMed20221051081right- handedfemaleMed161993381right- handedfemaleBus15181225161right- handedfemaleOth20241131021right- handedfemaleMed1019105561right- handedfemaleMed017125521right- handedmaleCom2018143211right- handedmaleMed2326652321right-handedfemaleOth % Polygons 2 Groups Histogram Freq. & % DistributionFrequency Distribution for WorkingbinsmidptsFrequencyPercentage- 5.100.00%4.908214.59%14.9106211.03%24.92015126.87%34.9 3011620.64%44.94010618.86%54.950356.23%64.96081.42%74. 97020.36%Total562100.00% L’Oreal in China: Marketing Strategies for Turning Around Chinese Luxury Cosmetic Brand Yue Sai Best Marketing Case AFM-CCMP Competition 2014 Maybe it was that eighth glass of baijiu that he had downed to show respect to the department store manager and her team, or their joke that they were honoured to see him but hoped that the head of Lancôme would join him at their next meeting, but all of a sudden doubts assailed Stéphane Wilmet, the new general manager of Yue Sai. Stéphane had always been passionate about China – teaching himself Chinese as a teenager – and had
- 30. looked forward to coming back to China after an assignment with L’Oréal USA. But the challenge ahead was enormous. Yue Sai was one of the very few brands that had managed to lose volume and money in China’s booming cosmetics market – a sore point for L’Oréal. While politely engaging in small talk with his hosts about the superiority of the local cuisine, Stéphane’s mind kept returning to what was needed to turn around the situation and strengthen L’Oréal’s reputation in China. The Chinese Cosmetics Market Brief Overview China has one of the world’s oldest civilizations with a history dating back 5,000 years, and is the most populous nation on the planet with over 1.3 billion people. Thanks to its consistently rapid economic development since the late 1970s, it is now the world’s second largest economy in terms of GDP (see Exhibit 1). The World Bank has projected that it will surpass the United States as the world’s largest economy in the coming decades. Given an enormous increase in disposable income, Chinese consumers increasingly desired more sophisticated, premium products in many categories, including beauty and skincare. Procter & Gamble was the first multinational to enter mainland China’s beauty and skincare market, with Olay in 1989. With the exception of Estée Lauder which waited until 2002, the other multinationals quickly followed: Shiseido in 1991 with Shiseido, L’Oréal in 1997 with L’Oréal Paris, and Unilever in 1998 with Hazeline. They introduced extensive portfolios of high-quality brands and products, and brought marketing expertise, financial resources and cutting-edge R&D (which were soon localized by establishing local research centres). Initially, they drove out weak local brands, replacing them in the most desirable department stores. As of 2010, the top five companies in the beauty and skincare market (including personal care) were all multinationals: P&G, L’Oréal, Shiseido, Unilever and Amway. Yet they still only accounted for 40% of the €18 billion market, and now had
- 31. strong local competition. Firms such as Shanghai Jahwa and Jala had experienced extremely strong growth and their brands were available everywhere, from high-end department stores to local cosmetic stores, presenting a formidable challenge. Specificities of the Chinese Cosmetics Market Distribution Channels When multinationals first entered China, premium cosmetics were almost exclusively distributed via department stores (see Exhibit 2). As in department stores worldwide, brands rent floor space and sometimes pay a sales-based commission to the department store. They are then free to create a store-within-a- store (or counter), staffed with their own beauty assistants, with total control over sales and merchandising (but not, by law, on price). A legacy of the absence of other channels is that, even today, mass-market brands like L’Oréal Paris, Maybelline and Olay have counters in department stores in tier- 2 and tier-3 cities (see Exhibit 3). In 2010, there were over 4,000 department stores in China, with a minimum of 6,000 m2 of retail space. They were stratified into three classes: class-1 stores carrying brands like Lancôme, Chanel and Dior were only present in the largest cities. Hefei, the capital of Anhui Province, a city with 5.7 million people and the world’s fastest growing metropolitan economy,1 only had a class-2 department store. The second distribution channel consisted of beauty store chains like Watsons and Manning (see Exhibit 4). These employed their own beauty assistants who could sell any brand, but they also had smaller spaces dedicated to mass-market brands like L’Oréal Paris, Olay and Vichy, with assistants employed by the brands in the largest stores. The positioning of the LVMH- owned Sephora chain is more upscale, allowing it to carry brands like Estée Lauder and Lancôme (and, of course, Dior). The third channel consisted of countless small local cosmetics stores selling exclusively beauty and personal care products without the help of beauty assistants (see Exhibit 5). New channels of distribution, such as TV-based direct selling
- 32. and ecommerce portals were rapidly emerging. Over half a billion Chinese consumers had access to the internet. Traditional media (e.g., TV, newspapers) were losing their appeal as the younger generation spent a significant portion of time texting, surfing the web, and using social media such as Weibo (a Chinese fusion of Twitter and Facebook). Internet- based retailing was thus likely to have a significant impact on existing channels in the near future. Attitudes to and Usage of Cosmetic Products For decades, cosmetics were seen as “counter-revolutionary” and were virtually non-existent in China. Generations of Chinese women grew up without ever learning about cosmetics from their mothers. This absence of inter-generational norms meant that cosmetic companies— starting with Yue Sai in 1992—had first to educate Chinese consumers about beauty products and routines. But it also created a market of open- minded consumers free of the preconceptions prevalent in many countries: for example, Chinese men were more open to skincare than their European and American counterparts.2 China alone accounted for 70% of the worldwide sales of the Men Expert line of L’Oréal Paris. Chinese women were less interested in colour cosmetics than Europeans or Americans, not to mention Japanese and Korean women, who have the most sophisticated beauty routine in the world. Only 10-15% of the beauty products sold in the Chinese market were makeup products. Many Chinese women viewed makeup as superficial, unnecessary and potentially harmful to skin, and heavy makeup as socially undesirable. The perfume market was tiny in China. Perfumes were more often bought as gifts than actually used. China was therefore primarily a skincare market (as can be seen by the relative space devoted to skincare and makeup at Sephora in Exhibit 4). In China, the younger generation was significantly more receptive to cosmetics products than older consumers. The average cosmetics consumer was in her mid-20s (vs. early-50s in Europe). Most were raised as an only child (or “little emperor”), had significant disposable
- 33. income, and liked novelty. For them, another “generation” meant people who did not overlap at university or were separated by a decade at most (not parents and children). Whereas European and American women associated a brand’s longevity with heritage and prestige (particularly for luxury brands), ‘old’ had negative associations among Chinese consumers. Paradoxically, in parallel with the Chinese focus on novelty, there was a renewed interest in China’s ancient history, traditions and cultural heritage. Popular computer games and television shows were set in ancient China. Cultural beliefs pertaining to food, health and medicine had never been lost, and held true across all age groups. Most Chinese have some knowledge of traditional Chinese medicine (TCM; ) and apply its basic principles, if only because they feel it could do no harm. TCM refers to a wide range of ancient medicinal practices, including herbs, acupuncture and massage, to prevent and treat ailments and enhance health. Common ingredients such as glycyrrhiza uralensis (), lonicera japonica (), “silver ear” mushrooms () and wolfberry () can be purchased in most grocery stores and are cooked with food or made into tea. Other more specific and expensive ingredients (TCM has over 1,800 ingredients) like angelica (), cordyceps (), ginseng (), and notoginseng () are typically bought in special TCM pharmacies (see Exhibit 6). However, China’s economic development and rapid urbanization had come at a price. The country’s environment had deteriorated significantly and a large number of Chinese cities suffered from smog and polluted air and water, prompting a growing number of consumers to use skincare products to protect their skin. The pitfalls of industrialization and some high- profile food safety scandals (e.g., melamine-adulterated milk) had also boosted demand for products made with natural ingredients. Rising Chinese Confidence Chinese consumers were irresistibly drawn to Western brands in the 1990s and 2000s. Even today, a significant number of
- 34. Chinese and Asian cosmetic brands uses French-sounding names (like Franic, Kosé, Laneíge and Mamonde). Consumers began to take an interest in Japanese cosmetics from companies like Shiseido (and its China-only brands like Aupres and Urara), which were perceived to be more knowledgeable about Asian skin and beauty, although historical animosity toward Japan and recent geopolitical tensions were a risk for Japanese brands. Achievements such as sending astronauts into space, hosting the Olympic Games (Beijing 2008) and the World Expo (Shanghai 2010), building bullet trains and advanced planes, and the global success of firms like Haier, Huawei and Lenovo had made Chinese consumers increasingly proud of their nation. This had kindled an interest in products with a local heritage as well as boosting preference for domestic brands. For example, the 2008 launch of Shang Xia ()3, a Shanghai-based sub-brand of Hermès focused on furniture and decorative objects showcasing Chinese heritage and craftsmanship, was seen as a milestone in the rise of Chinese luxury brands. More generally, the reputation for quality, safety and the perceived R&D capabilities of Chinese firms had improved. This was particularly true of cosmetics, because many (including the international brands) were manufactured in China. Still, since most Chinese continued to associate luxury with foreign brands, it was unclear how quickly they would accept Chinese luxury brands. Overall, Chinese consumers, especially those in the tier 1 cities like Beijing and Shanghai, were increasingly sophisticated about brands and products in the beauty and skincare categories. With more opportunities to shop abroad and wider access to information on international fashion trends, they could distinguish true premium brands from those simply aspiring to be perceived as such. A seemingly Western name and image were no longer enough to attract discerning Chinese consumers. L’Oréal China The Group L’Oréal is the world’s largest cosmetics company, with
- 35. worldwide sales of €19.5 billion in 2010. In that year, its sales in China exceeded €1 billion for the first time, an 11.1% increase over the previous year and a double-digit gain for the 10th consecutive year, making China the third-largest market for L’Oréal after the United States and France (vs. its seventh- largest in 2008). L’Oréal had vowed to acquire one billion new customers globally in the next decade, a significant portion of which will come from China. L’Oréal is the second largest beauty and skincare player in China after P&G and No.1 in the luxury segment. It is present in China with almost all of its major brands, with the exception of Body Shop because Chinese regulations require cosmetics to be tested on animals. Five of its brands, including Lancôme and Maybelline New York, are No.1 in their respective categories. The Luxury Product Division (LPD) manages premium brands such as Lancôme, Biotherm, Helena Rubinstein, Kiehl’s, Shu Uemura and Giorgio Armani. The Consumer Product Division (CPD) oversees brands such as L’Oréal Paris, Maybelline New York and Garnier. Other divisions oversee dermo-cosmetic brands (e.g., Vichy) and brands tailored for professional hair salons (e.g., Matrix). L’Oréal has established a Research and Innovation Centre in Shanghai, and has manufacturing centres in Suzhou and in Yichang, where it produces most of its mass and professional brands. Luxury brands, with the notable exception of Yue Sai, are still imported. Yue Sai () Madam Yue-Sai Kan and the Pre-L’Oréal Years (1992-2004) The first modern cosmetics brand of China, Yue Sai, was founded in 1992 by Madam Yue-Sai Kan,4 an Emmy-winning TV host, socialite and entrepreneur (see Exhibit 8), with the aim “to create, produce and sell the very best beauty and skincare products that we can offer to Asian women and to the world, and become the first global cosmetics brand from China.” Her key insight was that the standards of beauty in China were different from those of other cultures; there was no reason why Chinese women had access only to foreign products that had not
- 36. been designed for their specific type of skin and beauty. To promote the brand, Madam Yue-Sai Kan wrote the first book about makeup ever published in modern China, which became a huge best-seller. Battling myriad obstacles and local regulations, she secured distribution in department stores nationwide, personally trained China’s first beauty advisors, and developed a range of red lipstick and basic skincare products designed for Asian skin. The brand’s red lipstick became an icon in China. In 1996, Madam Yue-Sai Kan sold the company to Coty, the New York-based cosmetics firm and world’s largest producer of fragrance, which outbid L’Oréal. Coty pushed the distribution of Yue Sai to reach more cities as well as less premium cosmetic stores. By 1998, Yue Sai had become the No.1 luxury cosmetic brand in China. Coty continued to focus on distribution rather than branding, and started focusing on its own brand, Lancaster. Yue Sai gradually lost relevance, straining the relationship between Coty and Madam Yue Sai. L’Oréal acquired Yue Sai in 2004. L’Oréal CEO, Jean-Paul Agon, declared that adding an established Chinese brand like Yue Sai alongside European brands like L’Oréal Paris, American brands like Maybelline New York, and Japanese brands like Shu Uemura fitted perfectly with L’Oréal’s “beauty for all” mission. That same year, L’Oréal also acquired Mininurse, a Chinese brand targeted at the mass market. Given the enormous potential of the Chinese market, coupled with L’Oréal’s stellar track-record at integrating and developing brands (24 of its 27 major brands were obtained through acquisitions or licensing deals), the future looked bright for Yue Sai under L’Oréal management. The Consumer Division Years (2004-2006) The post-acquisition years were less smooth than anticipated. On the positive side, L’Oréal had acquired a brand with a wide distribution (more than 1,000 stores across different channels), strong sales (€39 million in 2006), historical strength in makeup, a few good skincare products and packaging, and a
- 37. factory and R&D facility. On the other hand, the brand was associated with older consumers, sales were fading, it had lost its marketing and R&D innovative edge, and it was unclear how it fitted into L’Oréal’s brand portfolio in China. Because Yue Sai had such a wide distribution and a moderate price, it was first assigned to the consumer-product division (CPD) of L’Oréal China. CPD tried to apply the marketing strategy that had proven so successful worldwide for L’Oréal Paris, a mix of scientific improvements, celebrity-driven glamour and wide accessibility. Yue Sai was priced slightly below L’Oréal Paris, new products were launched annually, and the brand continued to be distributed in a variety of channels. Communication focused on technology, featured beautiful Chinese actresses and models (see Exhibit 9), and was inspired by the L’Oréal Paris ads (see Exhibit 7). The Luxury Division Years (2006-2010) But the “Chinese L’Oréal Paris” strategy did not produce the intended results and the brand lost sales and awareness, while at the same time L’Oréal Paris was booming (see Exhibit 15). To provide the brand with a new strategy and new set of eyes, Yue Sai was transferred from the CPD division to the smaller Luxury Product Division (LPD) in 2006. LPD immediately promoted Yue Sai featuring a famous Taiwanese movie star, Shu Qi (), to re-establish the brand’s luxury image (see Exhibit 10). To deliver Yue Sai’s longstanding brand promise that “Nobody knows Chinese skin better than Yue Sai,” L’Oréal’s Shanghai Research and Innovation Centre focused on creating products specifically designed for Chinese skin. For example, the Vital Essential line () launched in 2007 incorporated extract of ganoderma mushroom (), a traditional Chinese medicine ingredient believed to foster internal balance and boost internal energy, with a fragrance evocative of the distinctive smell of traditional pharmacies. This product was the most-liked of the Yue Sai line-up, with above-average repeat purchase scores. LPD then hired a reputable Paris-based branding agency and together they chose to reposition Yue Sai as “the first brand to
- 38. stand for Chinese women’s beauty”. They built on the insight that modern Chinese women were radically changing, were proud and self-confident, and had a clear vision of their future and their new role in society. Although they treasured their families, they wanted to build for themselves a new professional, artistic and cultural environment. To communicate the new “modern Chinese women” positioning, L’Oréal invested in a major television and print advertising campaign featuring Chinese supermodel Du Juan (). These ads used such lifestyle taglines as “I hold my future in my hands” () and “I look forward to every day with confidence” (,) to bolster the image of Yue Sai as the brand for modern Chinese women (see Exhibit 11 and Exhibit 12). Consistent with the new positioning, Yue Sai’s prices were notched higher than L’Oréal Paris. LPD tried to compensate for the volume decline brought by higher prices (see Exhibit 14) by entering new distribution channels such as Sephora (see Exhibit 16), while pushing for better deals with distributors in order to enter more cosmetic stores. Meanwhile, the increasing number of foreign premium brands entering the Chinese market led department stores to push Yue Sai’s counters further back in the stores, reducing their visibility and exposure to traffic. Some department stores even delisted the brand. Turning Around Yue Sai Alexis Perakis-Valat, who became CEO of L’Oréal China in 2010 at the age of 39, had big ambitions. He wanted to make L’Oréal the No.1 cosmetics firm in China, and turn China into L’Oréal’s No. 1 market by continuing to push into smaller cities and introducing L’Oréal’s luxury brands, including Kiehl’s and Yves Saint Laurent. Yue Sai’s lacklustre performance was spoiling the picture. Despite a booming market, it had never turned a substantial profit and sales had barely improved (€35 million in 2010 vs. €31 million in 2005). In Alexis’ own words, it was “the pebble in L’Oréal’s shoe”. Internally, it was becoming difficult to
- 39. motivate talent to work on the brand. Externally, it blemished L’Oréal’s reputation as a masterful integrator of acquired brands and companies, which could hamper L’Oréal’s future acquisition endeavours. Alexis and Stéphane, with the help of Ronnie Liang, Yue Sai’s new marketing director, needed to move fast and on all fronts. Strategic Decisions Choosing the Right Value Proposition When it was launched, Yue Sai was the uncontested premium Chinese brand. But today’s competitive landscape was very different. Yue Sai was not perceived as aspirational, unlike foreign brands such as Lancôme, Estée Lauder and Shiseido. It had an uncertain business model, an ageing consumer base, and an unclear positioning, the result of several years of trying various platforms. Yue Sai was not even the only Chinese brand owned by a large multinational company. Aupres (), a Shiseido brand launched in 1994, was developed specifically for and only available in Chinese department stores (see Exhibit 13), and had acquired a reputation for quality and a specific knowledge of Asian skin. The brand had been well managed and sales were around €100 million. There were indications that other multinationals would launch China-specific brands. Chinese firms were catching up with the multinationals. Shanghai-based Jahwa group had recently launched Herborist () which already had sales of €70 million (up from €45 million in 2008) and was available at Sephora in both China and Europe. Its positioning was “blending traditional Chinese herbal medicine with modern biotechnology”. Herborist was unique in that it was distributed in department stores but also in small freestanding beauty stores which offered massage and spa treatments. Another Chinese mass-market brand, Chcédo5 (, owned by the Jala group) reached €165 million in sales in 2010. Its positioning was “Chcédo makes women blossom with natural beauty and charm.” Given the situation facing Yue Sai and the current portfolio of brands of L’Oréal China, the critical issue is whether the brand
- 40. should: 1) keep its new lifestyle positioning as the brand of “confident, modern Chinese women”, 2) be positioned as a Chinese luxury icon symbolizing the nation’s long history and rich heritage, 3) adopt a more affordable value proposition, or 4) try something totally different. To choose the right positioning for Yue Sai, it is essential to decide which aspects of the brand should be retained and which should be discarded. For example, Yue Sai must decide whether to make its association with the L’Oréal group explicit to consumers by becoming a sub-brand (e.g., “Yue Sai by L’Oréal”) or by acknowledging L’Oréal’s ownership (e.g., by adding the tagline “Yue Sai, a Chinese brand of L’Oréal”). Finally, Stéphane and Ronnie need to decide if they should follow Aupres, which has entered the Malaysian market, and expand Yue Sai internationally (but where?) Alternatively, should they consider extending the brand into other product categories (which ones?) or target other consumer segments (which ones)? Marketing Mix Decisions Advertising and Promotion An important decision is whether to continue with the current TV and press campaign or to change it, at a time when media costs are climbing steadily and deteriorating sales limit the advertising and promotion budget. As more and more Chinese brands are relying on celebrities (actresses/actors, singers, athletes), should Yue Sai replace Du Juan with a celebrity or should they stay with a model? At the moment, 80% of Yue Sai’s communication budget is focused on skincare and 20% on makeup. Should this be changed? Further, should they change the current media plan or focus more on new media platforms like Weibo? More generally, they need to determine what resources to allocate to brand communication vs. improving in-store presence, improving the product line-up, or changing distribution channels. Pricing and Distribution
- 41. Stéphane and Ronnie must decide how Yue Sai should be priced within L’Oréal’s brand portfolio in China (especially in comparison with L’Oréal Paris). And whether all of Yue Sai’s products (see Exhibit 17) should be priced similarly, or should they charge more for some lines (which ones?) One of the most important decisions will be to select the right channels of distribution based on the market tier(s) Yue Sai should pursue and the consumers it should target. How should Yue Sai deal with new distribution channels such as ecommerce portals? Should it engage in franchising to create its own stand- alone stores like Herborist? Audience Analysis YOUR NEED(S) YOUR NEED(S) · ?? * ?? · ?? * ?? · ?? * ?? · ?? * ? THEIR WANT(S) SITUATION: SITUATION: AUDIENCE CHARACTERISTICS AUDIENCE CHARACTERISTICS COMM. STRATEGY AUDIENCE CHARACTERISTICS COMM. STRATEGY Primary Audience
- 42. Demographic: Age Gender Culture Religion, Belief Structure Group Membership Education Occupation Other __________ Psychographic: Opinions Attitudes Values Beliefs Pre-Existing Notions about Topic Pre-Existing Notions about You Other ____________
- 43. Situational Analysis: Occasion Audience Size Voluntariness of Audience Expectations Physical Setting Other ____________ Links http://www.claritas.com/MyBestSegments/Default.jsp http://www.point2homes.com/ click on Neighborhoods 1 Audience Analysis YOUR NEED(S) · Have COO understand, from a big picture view, what the data say about United vs its competitor in terms of arrival and departure delays · Have the COO perceive that I am competent and am adding value to the comjpany
- 44. THEIR WANT(S) SITUATION: Memo to COO AUDIENCE CHARACTERISTICS AUDIENCE CHARACTERISTICS COMMUNICATION STRATEGY Primary Audience COO of United Airlines Impatient, keep it short and to the point Demographic Age · 40 < 60 More conservative, formal language Gender Probably male, but don’t be surprised. If female, assume younger and smarter Either gender, need to be professional with little “small talk” Culture, Religion, Belief Structure Chicago is HQ, so assume mid-West background which is more conservative than East Coast Conservative, maybe a need to address “show me” attitude Group Membership(s) Unknown, but probably belongs to one or more trade organizations. May have seen similar data elsewhere Assume COO has benchmark data. Need to stick to what my
- 45. data says Education MBA Need to show my knowledge of statistics and assume COO is quite knowledgeable, too Occupation Logistics, but COO might be a stepping stone It’s all about identifying delays and, eventually, decreasing them Psychographic: Opinions, Attitudes, Values, Beliefs Values evidence in making decisions, needs proof to be solid before acting Believes United is the better airline Stay within the data; don’t stretch it to be more than it is. Don’t speculate Pre-Existing Notions of Topic Maybe skeptical about data sources or data collection method Little is mentioned in my data set description. Best to say what is known and don’t speculate. Know limitations of data. May want to state these Pre-Existing Notions about Me Assuming limited exposure. My credibility, if any, comes from my supervisor Memo needs to be perfect—no noise—or all the credibility of my analysis will be lost Situational Analysis:
- 46. Occasion Memo requested by COO Mention request in opening paragraph Audience Size Probably 1 but COO may share with others Assume it will be shared, do not refer to anything that would compromise COO Voluntariness of Audience Expectations At a minimum, solid data; maximum, a eureka moment on how to sustain an advantage We don’t have one. Need to position as solid evidence that should be combines with other data COO may have or want to get Physical Setting HQ office Probably Word document attached to e-mail with an interoffice hardcopy Bottom line so far is that I need to be professional, know what I am talking about, stay within the data and not speculate, tell the story quickly, maybe ion one page plus appendixes 2
- 47. Writing Process Analysis Page 5 Writing Process Analysis Worksheet Problem/Question 1. What is the situation that has motivated the writer at this point in time? Is the specific writing task addressed? Objective 2. How will the audience initially react to the message? How important will the audience think this message is? What should the audience know, believed, or do as a result of reading this document? How is the objective made clear to the reader?
- 48. Audience 3. (a) Who is (are) the audience(s) for this document? (Identify primary, secondary, and phantom audiences. Phantom audiences (those lurking that you may not initially anticipate—e.g., audience friends and family members, an employee 3 years down the road who runs across the document in a file, auditors, attorneys). Be as specific as possible.) (b) What characteristics of these audiences are relevant to this particular message? How do the characteristics of the various audiences differ? (Think about things that may affect their response to the message as such job position, location, age, gender, level of understanding of the topic, and level of interest in the topic.) (c) Is the document appropriate for the intended audience? Has the writer made an effort to show what the reader can gain (or lose)? What does the audience need to know and what is already known?
- 49. Strategy 4. (a) What obstacles must the writer overcome? What objection(s) can the writer expect reader(s) to have? What negative elements of the message must be de-emphasize or overcome? Is the audience opposed to the message? Will it be easy for the audience to do what is being asked? (b) Does the document provide a strong argument and sufficient use of evidence? Are the sources (if relevant) credible and adequate to persuade the audience? Structure 5. (a) What is the arrangement of arguments (e.g., inductive vs. deductive, chronological, descriptive, facts vs. analysis) and are
- 50. they appropriate to meet the intended objectives? Are the ideas organized logically? Does the document have effective opening and closing statements? Is a follow-up step (if needed) included? (b) How much information does the audience need? What information must the message include? How much does the audience already know about this subject? Does the audience’s knowledge need to be updated? What questions will the audiences have that should be answered? What aspects of the subject does the audience need to be aware of to appreciate the points being made? How much detail is needed? Document Design 6. (a) How will the audiences use the communication? Under what physical conditions? Will it be read in detail, skimmed, used as a reference, potentially used as the basis for a lawsuit, filed? Will it be read on-screen? On paper? Potentially both?
- 51. (b) Is the document design appropriate for the task, the objectives, and the audience? Are formatting (subheads, list, paragraphing) and visual (exhibits, tables, charts) elements used effectively? Or are these elements absent when they should be present? Is the appropriate citation style (if relevant) followed? (c) Do the audiences prefer a direct or indirect structure, e.g., should the writer give her/his recommendation right up front as is typically desired in business writing or should he/she ease into it more gradually? Style 7. (a) What expectations do the audiences have about the appropriate language, structure, and form for the message? What style of writing do the audiences prefer in these situations? Are there any hot buttons or “red flag” words that may create an immediate negative response?
- 52. (b) Does the writing flow and have a rhythm? Is the writing making suitable syntactic choices (for example, active vs. passive voice)? Is the style (formal vs. informal) appropriate for task, objectives, and audience? Does the document conform to conventions for the particular genre and/or discipline? Edit/ Proof 8. Are there problems with standard American usage (grammar, punctuation, and mechanics)? Are there apparent lapses in proofreading? Do errors interfere with meaning or impact? Date: September 25, 2014 To: Southern Life Employees From: Simon Miller, Human Relations Manager Subject: Compliance Improvement
- 53. Here at Southern Life, we strive to accommodate a safe work environment for our employees. Our company rules and guides are set up to keep the office environment professional and fair, though it seems there have been incidents of sexual harassment in the company and we would like to address that issue now. Southern Life’s harassment policy states that behavior that is sexually offensive in the workplace is prohibited. This includes unwarranted sexual advances and other offences that would interfere with an individual's work performance, or create an intimidating, hostile, or offensive work environment. Southern Life has a no tolerance policy when it comes to any instances of sexual harassment. We should all look out for the people we work with and discourage such behavior to keep the environment safe and professional. Sexual harassment can be verbal as well as physical. Anyone who becomes a victim of sexual harassment in the workplace is advised to contact the appropriate higher staff member immediately. Our employees are valuable to us and we will not accept mistreatment of them amongst our staff. A peaceful, non-threatening workplace is safe and is something that we at Southern Life like to hold up to. The incidents of sexual harassment will be dealt with and we hope to prevent further mishaps from happening in the future. Here is a link for more information on sexual harassment: http://www.eeoc.gov/eeoc/publications/fs-sex.cfm Here at Southern Life, we must learn about he issues and learn from mistakes that certain people have made. These incidents are unacceptable and are an offense to both Southern Life employees and the Southern Life image. It is advisable that this letter be taken seriously. Attached is Southern Life’s complete sexual harassment policy. Read all of the policy so you can understand Southern Life’s position on this issue and become more aware about what we would expect the attitude of all Southern Life employees to be like. At Southern Life, a safe,
- 54. neutral work environment is encouraged to make all employees feel comfortable. This letter will serve as a reminder to our employees of what our company stands for. Thank you for your time Sincerely, Simon Miller, Human Relations manager BUGN 280 Excel Project Data File Information 1 – Airline Arrival Study · Direct memos and reports to Chief Operating Officer (COO) of United Airlines A random sample of 444 flights from LAX to JFK in one year. The flight distance is 2475 miles. Numerical Variable of Interest: ArrDelay = arrival delay in minutes where “-“ values are early arrivals (in minutes), “0” values are “on time” arrivals and “+” values are late arrivals (in minutes). Numerical Predictor Variable: DepDelay = departure delay in minutes Categorical Breakdown Variable: Carrier = airline used where “1” = American Airlines , “0”= United Airlines Categorical Variable of Interest: Time = time of departure (A.M., P.M.) 2 – Albuquerque NM RE Study · Direct memos and reports to Chief Operating Officer (COO) of Weichert Realtors, New Mexico A random sample of 117 homes for resale in Albuquerque, NM.
- 55. Numerical Variable of Interest: Price = price of home in thousands of dollars (k) Numerical Predictor Variable: Sqft = square footage of dwelling Categorical Breakdown Variable: Custom = custom design where “1” = Yes, “0” = No Categorical Variable of Interest: Corner = house on corner lot (Yes, No) 3 – American Community Survey · Direct memos and reports to the Editor, Business Section, The New York Times. A random sample of 266 responses to the American Community Survey. Numerical Variable of Interest: WorkInc = work income in thousands of dollars (k) Numerical Predictor Variable: HrsWorked = hours worked per week Categorical Breakdown Variable: Gender = gender of respondent where “1” = Male , “0”= Female Categorical Variable of Interest: HowComm = most typical method of commuting to work (bus, car, subway/rail, taxi, other, works at home, not applicable) 4 – Automobile Study
- 56. · Direct memos and reports to Chief Operating Officer (COO) of the American Automobile Association (AAA) Automobile features taken from a sample of 171 car models. Numerical Variable of Interest: MPG = miles per gallon Numerical Predictor Variable: Weight = weight of automobile in pounds Categorical Breakdown Variable: Origin = origin of car where “1” = US, “0” = Asia or Europe Categorical Variable of Interest: TypeAuto = type of automobile (4 door hatchback, 4 door SUV, coupe, minivan, sedan, wagon) 5 – Beer Study · Direct memos and reports to the Editor, Consumer Reports A study of features in a random sample of 139 beers. Numerical Variable of Interest: PctAlcohol = percent alcohol content in the beer Numerical Predictor Variable: Calories = calories in the beer Categorical Breakdown Variable: DistType = distribution type- where “1” = National , “0”= Regional
- 57. Categorical Variable of Interest: Light = whether the beer product is considered “light” (yes, no) 6 – Birth Weight Study in MA · Direct memos and reports to Commissioner of Health, Commonwealth of Massachusetts A random sample of 189 mothers were studied with respect to the birth weight of their child. Numerical Variable of Interest: BWT = birth weight in grams (below 2500 is considered low) Numerical Predictor Variable: WEIGHT = weight (in pounds) of mother at last menstrual period Categorical Breakdown Variable: Smoke = smoking during pregnancy where “1” = Yes, “0” = No Categorical Variable of Interest: Race = race of mother (white, black, other) 7 – Birth Weight Study in NC · Direct memos and reports to Commissioner of Health, State of North Carolina A random sample of 1000 births from the state of North Carolina. Numerical Variable of Interest: BirthWt = birth weight of child in pounds Numerical Predictor Variable: Weeks = weeks of gestation Categorical Breakdown Variable: MSmoke = was the mother smoking during pregnancy where “1” = Yes, “0”= No Categorical Variable of Interest: MRace = mother’s race (white, non-white)
- 58. 8 – Bond Funds Study · Direct memos and reports to Chief Financial Officer (CFO) of Vanguard A random sample of 180 bond funds and their characteristics. Numerical Variable of Interest: Five-Year Return = five-year return on investment (in percent) Numerical Predictor Variable: One-Year Return = one-year return on investment (in percent) Categorical Breakdown Variable: Category = category of fund where “1” = intermediate government “0” = short term corporate Categorical Variable of Interest: Risk = risk of fund (above average, average, below average) 9 – Business Valuation Study · Direct memos and reports to CFO, Pfizer Corporation Financial information pertaining to a random sample of 71 companies in the pharmaceutical industry. Numerical Variable of Interest: Return on Equity = ROE (in %). Numerical Predictor Variable: Price/Book Value = price to book value ratio. Categorical Breakdown Variable: Type = type of company: PharmPrep (pharmacy prep products) or BioProducts (biological products) Categorical Variable of Interest: Debt/EBITDA Ratio = ratio value: Low (Below 4), Moderate/High (4 or Above) 10 – Candidate Assessment Study · Direct memos and reports to President Susan Cole, Montclair
- 59. State University A random sample of 120 faculty assessments of job candidate qualifications. Numerical Variable of Interest: Salary = salary in k offered to job candidate. Numerical Predictor Variable: Competency Rating = a 7-point numerical scale where 1 is “low” and 7 is “high” Categorical Breakdown Variable: Gender-Candidate = gender of job candidate where M = Male, F = Female Categorical Variable of Interest: School = type of education institution: Private or Public 11 – Cereal Study · Direct memos and reports to Chief Operating Officer (COO) of General Mills A study of a random sample of 76 cold cereal characteristics. Numerical Variable of Interest: calories = calories per serving Numerical Predictor Variable: weight = weight in ounces of one serving Categorical Breakdown Variable: Mfr= manufacturer of cereal product where “1” = General Mills or Kelloggs , “0”= Other Categorical Variable of Interest: Cups = cups in a serving (one or more, less than one) 12 – College Football Study · Direct memos and reports to Provost Willard Gingerich, Montclair State University
- 60. A random sample of financial information regarding 105 college football teams. Numerical Variable of Interest: Football Net Revenue = net revenue in $ obtained by football program. Numerical Predictor Variable: Total Pay = total pay in $ to the coach of the football team. Categorical Breakdown Variable: Location = location of the college with respect to east or west of the Mississippi River where E = East, W = West Categorical Variable of Interest: Conference = institutional conference affiliation: (ACC, Big East, Big Ten, Big 12, CUSA, Ind., MAC, Mt. West, PAC-12, SEC, Sun Belt, WAC 13 – Community College Study · Direct memos and reports to the President, Berry County Community College A survey for a random sample of 562 community college students at a large institution. Numerical Variable of Interest: Working = hours of work per week Numerical Predictor Variable: Credit hrs = number of credits enrolled Categorical Breakdown Variable:
- 61. Handed = hand mainly or always used for writing where “1” = right-handed, “0” = left-handed Categorical Variable of Interest: Gender = gender of student (Male, Female) 14 – Commuting Study · Direct memos and reports to Commissioner of Transportation, City of Atlanta A random sample of 1000 commuters’ characteristics, 500 from Atlanta and 500 from St. Louis. Numerical Variable of Interest: Time = commuting time in minutes Numerical Predictor Variable: Distance = commuting distance in miles Categorical Breakdown Variable: City = city of respondent where “1” = Atlanta , “0”= St. Louis Categorical Variable of Interest: Gender = gender of respondent (m, f) 15 – Credit Unions Study · Direct memos and reports to Editor, Business Section, The New York Times A random sample of 1179 credit unions with assets less than 10 million dollars and their characteristics. Numerical Variable of Interest: Total Net Worth = total net worth in millions of dollars Numerical Predictor Variable: Total Investment = total investment in millions of dollars Categorical Breakdown Variable: AssetSize = asset size where “1” = 5 to 10 billion $ (i.e., “larger”), “0” = under 5 billion $ (i.e., “smaller”) Categorical Variable of Interest: Region = region of the country (R1, R2, R3, R4, R5)
- 62. 16 – Employee Survey · Direct memos and reports to Secretary, United States Department of Labor A random sample of 400 employee characteristics. Numerical Variable of Interest: Salary = salary in thousands of dollars (k) Numerical Predictor Variable: WorkHrs = hours worked last week Categorical Breakdown Variable: BudgetDec = is the employee involved in budgetary decisions where “1” = Yes , “0”= No Categorical Variable of Interest: Gender = gender of employee (male, female) 17 – Faculty Evaluations in TX Study · Direct memos and reports to Commissioner of Higher Education, the State of Texas A random sample of 182 faculty members’ evaluations conducted by students at Texas universities. Numerical Variable of Interest: fac_eval = faculty evaluation (where 1 = poor through 5 = excellent) Numerical Predictor Variable: course_eval = course evaluation (where 1 = poor through 5 = excellent) Categorical Breakdown Variable: School = university faculty member is teaching at where “1” = Texas Austin, “0” = Other Categorical Variable of Interest: Rank = rank of faculty member (tenured, not-tenured) 18 – GSS Study · Direct memos and reports to Secretary, United States Department of Labor GSS survey displaying a random sample of 904 individuals.
- 63. Numerical Variable of Interest: SEI = Social Economic Index of individual Numerical Predictor Variable: PRESTIGE = Occupational Prestige Score (where 0 = NA) Categorical Breakdown Variable: Race = race of individual responding where “1” = White, “0”= Non-White Categorical Variable of Interest: Gender = gender of individual responding (Male, Female) 19 – Heart Stent Study · Direct memos and reports to President, American Heart Association A random sample of 100 coronary heart disease patients who had stents inserted. Numerical Variable of Interest: total_labor_cost = labor cost in dollars Numerical Predictor Variable: total_device_cost = cost of device in dollars Categorical Breakdown Variable: Outcome = outcome of stent insert procedure where “1” = Successful, “0” = No Change or Failure Categorical Variable of Interest: Gender = gender of patient (M, F) 20 – Human Resources Survey · Direct memos and reports to Vice President for Human Resources, The MLB Corporation The data are a random sample of 120 employee responses to a survey conducted by the VP of Human Resources at a large company. Numerical Variable of Interest: Salary = salary of the employee in thousands of dollars
- 64. Numerical Predictor Variable: Age = age in years Categorical Breakdown Variable: Ethnicity = ethnicity of the employee where “1” = Minority , “0”= Not Minority Categorical Variable of Interest: Gender = gender of employee (Male, Female) 21 – LI RE Study · Direct memos and reports to Chief Operating Officer (COO) of Weichert Realtors, Long Island, NY A random sample of 90 home characteristics in three Long Island communities. Numerical Variable of Interest: AppraisedValue = appraised values of homes in thousands of dollars (k) Numerical Predictor Variable: House Size = size of dwelling in square feet Categorical Breakdown Variable: Town = Long Island community where “1” = Freeport, “0” = Glen Cove or Roslyn Categorical Variable of Interest: Pool = whether the property has a pool (Yes, No)
- 65. 22 – Loans & Debt Study · Direct memos and reports to Editor, Business Section, The New York Times. Loans and credit card debt study from a random sample of 260 college students. Numerical Variable of Interest: Loans = loans in $ outstanding Numerical Predictor Variable: CC Debt = credit card debt in dollars outstanding Categorical Breakdown Variable: Gender = gender of respondent where “1” = Male , “0”= Female Categorical Variable of Interest: Class = class level of registered student (fr, so, jr, sr) 23 – Montclair & Millburn RE Study · Direct memos and reports to Chief Operating Officer (COO) of Weichert Realtors, New Jersey A random sample of 93 homes sold in Montclair and Millburn New Jersey. Numerical Variable of Interest: PRICE = price in thousands of dollars (k) of the house sold Numerical Predictor Variable: ASSESSVAL == assessed value of house in thousands of dollars (k)
- 66. Categorical Breakdown Variable: TOWN = location of house sold where “1” = Montclair, “0”= Millburn Categorical Variable of Interest: STYLE = style of house (bi-level, Cape Cod, colonial, custom home, ranch, split level, Tudor, Victorian ) 24 – Mutual Funds Study · Direct memos and reports to Editor, Business Section, The New York Times. A random sample of 868 mutual funds and their characteristics. Numerical Variable of Interest: Five-Year Return = five-year mutual fund return (in percent) Numerical Predictor Variable: Three-Year Return = three-year mutual fund return (in percent) Categorical Breakdown Variable: Objective = objective of mutual fund where “1” = Growth, “0” = Value Categorical Variable of Interest: Fees = managerial fees (Yes, No) 25 – Nutrition Study · Direct memos and reports to Commissioner of Health, State of New York. A random sample of 315 patients involved in a nutrition study. Numerical Variable of Interest: Calories = amount of calories consumed per day Numerical Predictor Variable: Fat = amount of fat consumed per day Categorical Breakdown Variable: Smoke = does the patient smoke where “1” = Yes, “0”= No Categorical Variable of Interest: Gender = gender of patient (Male, Female)
- 67. 26 – PA RE Study · Direct memos and reports to Chief Operating Officer (COO) of Weichert Realtors, Pennsylvania Assessed value and characteristics of a sample of 362 recently built homes in PA. Numerical Variable of Interest: AssessedValue = assessed value in thousands of dollars (k) Numerical Predictor Variable: TotalRooms = total number of rooms in the house Categorical Breakdown Variable: Basement= does the house have a basement where “1” = Yes , “0”= No Categorical Variable of Interest: Fireplace = does the house have a fireplace (absent, present) 27 – Public College Value Study · Direct memos and reports to Secretary, United States Department of Education A random sample of 100 public colleges and universities and their characteristics. Numerical Variable of Interest: 4-Yr.Grad.Rate = four year graduation rate (in percent) Numerical Predictor Variable: Total cost per yr (in state) = total cost in dollars per student per year at institution Categorical Breakdown Variable: Region = location of college or university where “1” = Atlantic or Eastern “0” = Other Categorical Variable of Interest: DebtAbove20k = is average student debt at graduation above $20,000 (Y, N)
- 68. 28 – Retirement Funds Study · Direct memos and reports to Professor Deniz Ozenbas, Montclair State University A random sample of financial information regarding 316 mutual funds. Numerical Variable of Interest: 3YrReturn% = return on investment (in %) over a three year period. Numerical Predictor Variable: 1YrReturn% = return on investment (in %) over a one year period. Categorical Breakdown Variable: Type = type of fund: Growth or Value Categorical Variable of Interest: Risk = risk level for fund: Low, Average, High 29 – ROI College & University Study · Direct memos and reports to Secretary, United States Department of Education
- 69. Return on investment (ROI) data for a sample of 252 colleges and universities in the USA. Numerical Variable of Interest: 30 YEAR NET ROI = 30 year net return on investment in dollars Numerical Predictor Variable: AVG AID AMOUNT = average amount of aid per student in dollars Categorical Breakdown Variable: TYPE = type of institution where “1” = Private, “0” = Public Categorical Variable of Interest: CATEGORY = category of institution (public, private, private research, liberal arts, business, engineering, art-music-design) 30 – TV Set Study · Direct memos and reports to Editor, Consumer Reports A random sample of 174 Tv models with their characteristics. Numerical Variable of Interest: Overall Score = score provided by consumers rating the product.
- 70. Numerical Predictor Variable: Quality Rating = summation of ratings of features provided by Consumer Reports. Categorical Breakdown Variable: Type TV = type of television where P = Plasma, L = Liquid Categorical Variable of Interest: SizeGP = size of TV screen Where Small = below 40”, Medium = 40” to 49”, Large = 50” or more 31 Urban Study · Direct memos and reports to Editor, Real Estate Section , The New York Times A random sample of 198 urban resident characteristics. Numerical Variable of Interest: Internet Hrs = hours spent last week on the internet Numerical Predictor Variable: Hours worked = hours worked for pay last week Categorical Breakdown Variable: Gender = gender of urban resident where “1” = Male, “0” = Female Categorical Variable of Interest: Political Philo = political philosophy of the urban resident (Liberal, Moderate, Conservative)
- 71. 32 – Used Autos Study · Direct memos and reports to Chief Operating Officer (COO) of the American Automobile Association (AAA) A random sample of 743 recently sold used cars and their characteristics. Numerical Variable of Interest: Price = price in thousands of dollars (k) Numerical Predictor Variable: Mileage = mileage at sale of used vehicle Categorical Breakdown Variable: Origin = origin of vehicle where “1” = USA , “0”= Asia or Europe Categorical Variable of Interest: Type = type of vehicle (Coupe, Minivan Muscle Cr, PickupT, Sedan, SedanWg, Sports Cr, SUV, Van, Wagon) 33 – UT Speeding Violation Study · Direct memos and reports to Commissioner, Bureau of Motor Vehicles, State of Utah A random sample of 118 individuals given a speeding ticket in UT. Numerical Variable of Interest: Age at Incident = age (in years) of individual when given the speeding ticket Numerical Predictor Variable: Age at License = age (in years) of individual when license was obtained Categorical Breakdown Variable: Gender = gender of the individual given the speeding ticket where “1” = Female, “0” = Male Categorical Variable of Interest:
- 72. Road = type of road on which the speeding ticket was given (Backroad, City, Freeway) 34 – Wine Study · Direct memos and reports to the Editor, Food and Beverages, The New York Times. A study of the characteristics of a random sample of 100 wines. Numerical Variable of Interest: Alcohol = alcoholic content (in %). Numerical Predictor Variable: Density = wine density measurement. Categorical Breakdown Variable: Type = type of wine: Red or White Categorical Variable of Interest: Quality Rating = 10-point scale quality rating: where Low = 5 or Below, High = 6 or Above 35 – Zagat NYC Restaurant Study · Direct memos and reports to Editor, Food Section , The New York Times A random sample of 66 NYC restaurants rated by Zagat with their characteristics.
- 73. Numerical Variable of Interest: Cost$ = cost rating (in dollars) Numerical Predictor Variable: Décor&Service = combined décor and service rating (each on 1 to 30 scale) Categorical Breakdown Variable: Type Food = type of food where “1” = Asian, “0” = Non-Asian Categorical Variable of Interest: HighPopIndx = whether the Zagat Popularity Index is 90 or higher (Yes, No)