
Discuss Marketing Research of Asbury Automotive Group within the Marketing Research ( MR ) forums, part of the PUBLISH / UPLOAD PROJECT OR DOWNLOAD REFERENCE PROJECT category; ...
 Thread Tools  Display Modes 
Marketing Research of Asbury Automotive Group 
Marketing Research of Asbury Automotive Group 
March 31st, 2011
Asbury Automotive Group (NYSE: ABG) is a Fortune 500 company based in [Atlanta], and was founded in 1995 by who also The company operates auto dealerships in various parts of the United States. In 2006 it ranked 364 out of 500 [1] As of First Quarter 2008, it is one of the largest automobile retailers in the U.S. 2006 revenues were reported to be approximately $5.7 billion.[2] There are 120 franchises selling and serving 33 different automotive brands. With respect to this model, the data gathered will be assessed through the help of Microsoft excel and a statistical software called SPSS. Basically, the SPSS software will be used to validate the hypothesis. Thus, descriptive statistics, correlation and Chisquare will be run in SPSS software. Descriptive Statistics In the descriptive statistics, it is likely that the study will be inexpensive and swift. It can also propose unexpected hypotheses. Nevertheless, this statistics will be very firm to rule out different clarifications and principally deduce causations. This descriptive statistics utilizes observations in the study. In descriptive statistics measures of central tendency (e.g. mean, median, and mode) and measures of dispersion (e.g. standard deviation, range, variance) will be computed. Correlation[1] According to Guilford & Fruchter (1973), the strength of the linear association between two variables is quantified by the correlation coefficient. Since this paper is in quantitative approach which is also mainly limited to counting, coming up with frequency and cumulative distributions, and computations of percentages, then these methods of analysis yield facts and data, the uses are quite limited. Facts in and of themselves do not speech much, for instance, of achievement or performance are related to other factors that such phenomena are better understood, predicted and to some extent even controlled. The basic purposes of sciences are description, explanation, prediction and control. Differences in a performance, for example, are better explained if other phenomena, events or even other performance are used to account for each difference. This is achieved through a process called correlation. In a sense ttests and Ftests are special cases of correlation. Sometimes such relationship show causeeffect but sometimes it is just plain relationship. Correlations may either be bivariate (at least) or multivariate. Actually, in this paper, the use of Pearson Product moment correlation is considered. The Pearson Product moment correlation is used if the purpose is to determine the relationship or covariation between two variables that are usually of the interval type of data. Basically, there are two types of correlation depending on the nature of correlation. Correlation may either be positive or negative. Correlation is positive if the objects, items or cases who got high in one variable are also those who got high in another variable, and those who got low in one variable also got low in the other variable. Correlation is negative if the reverse seems to be the pattern. That is, those who got high in one factor are generally the ones who got low in the other factor; those who got low in one factor got high in the other factor. Correlation, or r for short in the case of a Product Moment Correlation ranges from r = 1.00 to r = +1.00 as limiting values. If r = +1.00 nor r = 1.00. If the general pattern of scores indicates positive correlation or negative correlation, there are usually stray cases which do not fit the mold. These cases cause the correlation to be less than perfect, that is the r may range between, say r = .01 to r = .99 in the case of positive correlation; r =.01 to r = .99 in the case of negative correlation. The formula used in this type of statistic is: = Correlation between X and Y = Sum of Variable X = Sum of Variable Y = Sum of the product X and Y N= Number of Cases = Sum of squared X score = Sum of squared Y score The previous formula used in computing correlation coefficient standardizes the values. Therefore no matter what changes in scale or units of measurement are given it will not affect its value. For this cause, the correlation coefficient is frequently more helpful than a graphical representation in evaluating the strength of the relationship between two variables. Aside from this, if the correlation index of the calculated rxy is not perfect, then it is recommended to use the following classifications (Guilford & Fruchter, 1973): rxy Indication between ± 0.80 to ± 1.00 : High Correlation between ± 0.60 to ± 0.79 : Moderately High Correlation between ± 0.40 to ± 0.59 : Moderate Correlation between ± 0.20 to ± 0.39 : Low Correlation between ± 0.01 to ± 0.19 : Negligible Correlation Chisquare Analysis[2] As indicated in the paper of Guilford & Fruchter, (1973), the indicated formula below is utilized to assess Ho for all forms of ChiSquare tests: Where: fo = observed frequency in the cell. fe = expected frequency in the cell (if Ho was true). Note: the fe values for a no preference ChiSquare will always equal each other. The fe values for the no difference from an alternate population are specified by the Ho. To determine fe for the no preference version of the Goodness of Fit ChiSquare, use the following formula: The fe for the no difference from an alternate population are based on information provided about the alternative population. On the other hand, the degrees of freedom for a oneway ChiSquare is k1, where k is the number of cells (i.e, the number of levels) in the design. Basically, Chisquare is the most commonly reported nonparametric statistic. It can be used with one or more groups. It compares the actual number (freuquency) in each group with the expected number. The expected number can be based on theory, experience, or, or comparison groups. The question is whether the expected number differs significantly from the actual number. Chisquare is used when the data are nominal (categorical). With regards to chisquare statistics, there are four assumptions that should be considered: Frequency of Data Adequate sample size measures independent of each other Theoretical basis for the categorization of the variables The first assumption is that the data are frequency data, that is, a count of the number of subjects in each condition under analysis. The chisquare cannot be used to analyze the difference between scores or their means. If the data are not categorical, they must be categorized before being used. Whether to categorised depends on the data and the question to be answered. The second assumption is that the sample size is adequate. In cross tabulation procedures, cells are formed by the combination of measures. None of the cells should be empty. Expected frequencies of less than five in 2 x 2 tables present problems. In larger tables, many researchers use the rule of thumb that not more than 20% of the cells should have frequencies of less than five (SPSS, 1999; p. 67). If the cells do not contain adequate numbers, then the variables should be restructured to have fewer categories. The third assumption is that the measures are independent of each other. This means that categories created are mutually exclusive; that is, no subject can be in more than one cell in the design, and no subject can be used more than once. It also means that the response of one subject cannot influence the response of another. The fourth assumption is that there is some theoretical reason for the categories. This ensures that analysis will be meaningful and prevents “fishing expeditions.” The latter could occur if the researcher kept recategorizing subjects, hoping to find relationship between variables. Research questions and methods for analysis are established before data collection. Although these may be modified to suit the data actually obtained, the basic theoretical structure remains. Advertisements
 
Friends: (0)  
Re: Marketing Research of Asbury Automotive Group 
Re: Marketing Research of Asbury Automotive Group 
March 3rd, 2016
Quote:
It was really appreciable and i am sure it would help many people. Well, i found some important information Privacy Policy of Asbury Automotive Group and wanna share it with you and other's. So please download and check it.  
Friends: (0)  
Bookmarks 
Related to Marketing Research of Asbury Automotive Group  
 
Thread Tools  
Display Modes  
 