Log in to StudySoup
Get Full Access to MKG 425 - Study Guide - Final
Join StudySoup for FREE
Get Full Access to MKG 425 - Study Guide - Final

Already have an account? Login here
Reset your password

/ Marketing / MKT 425 / comm-425 study guide

comm-425 study guide

comm-425 study guide


School: 1 MDSS-SGSLM-Langley AFB Advanced Education in General Dentistry 12 Months
Department: Marketing
Course: Marketing Research
Professor: Ceren ekebas-turedi
Term: Fall 2016
Tags: final, MKG, 425, Marketing, research, chapter9, chpater10, Chapter12, and chapter13
Cost: 50
Name: Mkg 425
Description: This a a very detailed study guide for marketing research 425, Dr. Turedi. This covers all material needed to prep for the final; including Chapter 9 Selection the Sample, Chapter 10 and 12 Determining
Uploaded: 12/10/2016
11 Pages 176 Views 0 Unlocks

FINAL REVIEW MKG 425 (Post- Midterm-Chapters) Chapter 9- Selecting Sample : Concepts important in sampling: population, census, random sample, sample and  sampling frame o Population-the entire group under study as defined by research objectives o Census-an accounting of the complete population o Sample- a subset of the population that should represent the entire group o Sampling Frame- list from which the potential respondents are drawn (always draw sampling frame of who you can reach) Sampling Error: error in a statistical analysis arising from the unrepresentativeness of the sample taken o Sample error: any error in a survey that occurs because a sample is used Sampling Frame Error- degree to which the sample frame fails to account for all of the  population o (can be prevented to some extent: ie. Greater sample size greater the result) o If you cant apply sample to all population then this is sampling error o Always want error to be small o Almost always there will be sampling error o When sample size increase sample error decreases  o Researchers need to choose sample instead of taking the entire population bc of the  following: When budget is restricted, human resources are limited, time is limited, sampling is  the most efficient versus the entire population; can still obtain information that is  suitable and accuracy in a quicker and inexpensive manner o Waste of resources to use the entire population o Sample drawn scientifically, provides accuracy in representing population interest o Assessing all individuals may be impossible, impractical, expensive or inaccurate o Hardly know who makes up entire population o Too costly in terms of HR and other expenses o Time consuming, which adds more cost o Whole population means a lot of error to control and monitor The five steps of Sampling 1. Identify the population  o A population is the group of people that you want to make assumptions  about 2. Specify a sampling frame  o A sampling frame is the group of people from which you will draw your  sample. 3. Specify a sampling method  o There are basically two ways to choose a sample from a sampling frame:  randomly or non-randomly.   There are benefits to both. Basically, if your sampling frame is  approximately the same demographic makeup as your population, you  probably want to randomly select your sample 4. Determine the sample size o In general, larger samples are better, but they also require more time and  effort to manage 5. Implement the plan o Once you know your population, sampling frame, sampling method, and  sample size, you can use all that information to choose your sample. Researchers define populations in specific terms such as “heads of households located in areas served by the company who are responsible for making the best control decision." Researcher bias, also referred to as experimenter bias- a process where the individual  preforming the research influence the results. o Sometimes done to portray a certain outcome  Sometimes arises when researcher(s) select subjects that are  more likely to generate a desired outcome o Sometimes arises from experimental error & failure to take into  account all possible variables *Bias is the one factor that makes qualitative research more dependent upon experience and judgment than quantitative research Sampling bias- a bias in which a sample is collected in such a way that some members of the intended population are less likely to be included than others Two types of sampling include probability and non-probability o Also referred to as random sampling and non-random sampling Probability Sampling Vs. Non-Probability Sampling ∙ Probability sampling- each member has a fixed, known opportunity to belong to the sample ∙ Non-Probability sampling- there is no specific probability of and individual to be a  part of the sample. Basis For Comparison Probability Sampling Non-probability Sampling Meaning: Sampling technique, in  which the subject of the  population get an equal  opportunity to be selected  as a representative sample. Method of sampling  wherein, it is not known that which individual from the  population will be selected  as a sample. Alternately known as: Random Sampling Non-random Sampling Basis of selection: Random Arbitrarily Research: Conclusive Exploratory Result: Unbiased Biased Method: Objective Subjective Inferences: Statistical Analytical

How Do You Know When the Results Are Significant?

What is the size of the sample?

What is the method (process) for sample selection?

If you want to learn more check out a major advantage of countertrade is that it
We also discuss several other topics like anatomy and physiology 1 study guide

Hypothesis: Tested Generated

We also discuss several other topics like ulyssees grant
We also discuss several other topics like physics 212 uiuc
Don't forget about the age old question of psych 111
If you want to learn more check out zachary selden uf

A simple random sample- is a subset of a statistical population in which each member of the subset has an equal probability of being chosen. o Simple random sampling: the probability of being selected into the  sample is “known” and equal for all members of the population   E.g., Blind Draw Method  Random Numbers Method o An example of simple random sample would be drawing 15 student  names out of a hat from a class of 40 students. Researchers do not use SRS much in their research for the following reasons: Not efficient –hard to do bc you don’t know – not convenient (like lottery) • Advantage:  • Known and equal chance of selection…this makes it a probability  sample. EVERYONE has a chance! • Disadvantages: • Cumbersome to provide unique designations to every population  member when the population is large! Overcome when you have electronic dataset The main steps in a sample plan are: 1. Define the problem 2. Determine research design o Ie. The scientific method, which includes the following steps: 1. Formulate a problem 2. Develop a hypothesis 3. Make predictions based on the hypothesis 4. Devise a test of the hypothesis 5. Conduct the test 6. Analyze the results  3. Identify data types and sources  4. Design data collection forms and questionnaires  5. Determine sample plan and size   o Your marketing research project will rarely examine an entire population. It’s  more practical to use a sample—a smaller but accurate representation of the greater population. In order to design your sample, you must find answers to  these questions:   From which base population is the sample to be selected? What is the  method (process) for sample selection? What is the size of the sample? 6. Collect the data 7. Analyze and interpret the data Important points about sampling  ∙ Sampling method (not sample size) is related to representativeness ∙ Only a probability sample (random sample) is truly representative of a population but it’s inconvenient ∙ Sample size determines accuracy of findingsWhen you increase sample size you reduce error (increase sample size you increase  accuracy) Representativeness is very importantCh 10& 12- Determining the size of a sample & Using descriptive  analysis and hypotheses testing  Measures of Central Tendency are as follows: o Mode- a descriptive analysis measure defined as that value in a string of  numbers that occurs most often. o Median- expresses that value whose occurrence lies in the middle of an  ordered set of values Sample Size determines the accuracy of the findings. Sampling method (not sample size) is related to representativeness. Sample accuracy- refers to how close a random sample’s statistic is to the true  population’s value it represents. Relationship of Sample size and Sample Accuracy: o Sample size is not related to representativeness o Sample size is related to accuracy  The Confidence Interval Methods Of Determining Sample Size • Variability: refers to how similar or dissimilar responses are to a given question • P: percent saying “yes” • Q: 100%-P • Important point: the more variability in the population being studied, the higher  the sample size needed to achieve a stated level of accuracy. All measures of variability are concerned with depicting the “typical” difference  between the values in a set of values. • There are three measures of variability: o Frequency distribution o Range o Standard deviation • A frequency distribution is a tabulation of the number of times that each  different value appears in a particular set of values. • The frequency for each value divided by the total number of observations for all values, resulting in a percent, called a percentage distribution. • Range: identifies the distance between lowest value (minimum) and the  highest value (maximum) in an ordered set of values. • Variance: how widely your data vary (spreading out from the mean) • Standard deviation: indicates the degree of variation or diversity in the  values in such a way as to be translatable into a normal or bell-shaped curve  distribution. Standard deviation indicates the degree of variation in a way that can be translated into  a bell-shaped curve distribution (measure of how spread out numbers are.) High=spread out , low= close to the mean SD Tells you something…. • The level of agreement among respondents when they answer particular question. • If SD is small – distribution values are close to the meanRemember….. Standard Deviation • St Deviation describes the average distance of distribution values from the mean.  • Logic: If we subtract each value in a distribution from the mean and then add them up, this result would be close to zero (positive and negative will cancel each other). Z Score A z score reflects how many standard deviations above or below the population mean a  raw score is.  (It’s not the number but your interpretation (ie. If you know inches but not cm, ibs but  kg)) ∙ Bottom Line…. o If you are have a set of measurement scores on different measures using Z scores you can tell how the scores are placed in their distributions. Then you  can compare them.  o Z score is the number on a ruler! Confidence interval- the range of values so defined that there is a specific probability  that the value of a parameter lies within it. Hypothesis Testing • An effect exists: HA • An effect does not exist: Hnull • We compute a test statistic that represents the alternative hypothesis and  calculate the probability that would get a value as big as the one we have if the  null were true.  • If p is less than .05, we reject the idea that there is no effect. – means statistically  significant  • If p is greater than .05, we do not reject the idea that there is no effect.  Null and Alternative Hypothesis summary • The equality part of the hypotheses always appears in the null hypothesis. • In general, a hypothesis test about the value of a population mean m must take  one of the following three forms (where m0 is the hypothesized value of the  population mean).Chapter 13- Implementing basic differences tests Why differences are Important Remember… null is assume… alternative is what we are trying to prove • Manipulation is powerful and lets us to compare groups. Comparison is made  based on group means  • In more clear terms: • Two samples of data are collected and means are calculated. • If they come from the same population, then we expect their means to be  roughly equal.  • Therefore, Null Hypothesis says that manipulation has no effect on the  participants -sample means will be similar.  • T- test is used for this (also called independent t-test) How Do You Know When the Results Are Significant? • If the null hypothesis is true, we would expect there to be no differences between  the two percentages. • Yet we know that, in any given study, differences may be expected due to  sampling error. • If the null hypothesis were true, we would expect 95% of the z scores computed  from 100 samples to fall between +1.96 and −1.96 standard errors.Pre-Midterm Chapters  Introduction to Marketing Research (MR) & MR process & Defining  Problems  Marketing research is the process of designing, gathering, analyzing, and reporting  information that may be used to solve a specific marketing problem. (Hearing the  existing or future customer!) Purpose: To link the consumer to the marketer by providing information that can be used in making marketing decisions It is important to understand the needs of the consumers to accurately market to and  design products for the consumer. Understanding consumer needs is critical.  It is important to understand the problem rather than the symptom. If the problem is  incorrectly defined, all else is wasted effort. Information can be costly so it is important to determine if the marketing research will  result in a positive financial gain or meeting the company’s strategic goals.  Marketing is NOT NEEDED WHEN: • The information is already available. • Decisions must be made now.  • We can’t afford research.  • Costs outweigh the value of marketing research. Research objectives state what the researchers must do and accomplish. Research Design Research design is a set of advance decisions that make up the master plan specifying  the methods and procedures for collecting and analyzing the needed information. Exploratory - It is usually conducted when the researcher does not know much about the  problems. It is used to: • Gain background information  • Define terms  • Clarify problems and hypothesis  • Establish research priorities Descriptive – It is desirable when we wish to project a study’s findings to a larger  population, if the study’s sample is representative. It is undertaken to describe answers  to questions of who, what, where, when, and how. Causal – Relates to situations of cause an effect (“if x, then y”). Causal studies are  conducted through the use of experiments and capable of determining cause-and-effect  relationships. Quantitative – research involving the use of structured questions in which response  options have been predetermined and a large number of respondents involved Qualitative – Research involving collecting, analyzing, and interpreting data by observing what people do and say; it can be quantified Exploratory - It is usually conducted when the researcher does not know much about the  problems. It is used to: • Gain background information  • Define terms  • Clarify problems and hypothesis  • Establish research priorities Research Methods: case analysis & focus group Descriptive – It is desirable when we wish to project a study’s findings to a larger  population, if the study’s sample is representative. It is undertaken to describe answers  to questions of who, what, where, when, and how. Research Methods: Cress-sectional and longitudinal  Cross-sectional studies measure units from a sample of the population at only one  point in time (or “snapshot”). Observational. o Longitudinal studies repeatedly measure the same sample units of a population  over time. Also observational, researchers conduct several observations of the  same subjects over a period of time, sometimes lasting many years. An experiment is defined as manipulating an independent variable to see how it affects a dependent variable, while also controlling the effects of additional extraneous variables. Example: Medical Drug Testing – Over a period of time testing a control and experimental group to determine statistical value (if any) of the independent variable(s).  Control group: control of extraneous variables is typically achieved by the use of a second group of subjects Experimental group: the group that has been exposed to a change in the independent  variable Internal validity is concerned with the extent to which the change in the dependent  variable is actually due to the change in the independent variable. External validity refers to the extent that the relationship observed between the  independent and dependent variables during the experiment is generalizable to the “real world.”Survey Data Collection Methods Marketing Researchers conduct surveys to gain a better understanding of individuals on  certain information. A survey involves interviews with a large number of respondents  using a predesigned questionnaire. Advantages include: • Standardization • Ease of Administration • Ability to tap the “unseen” • Suitability to tabulation and statistical analysis • Sensitivity to subgroup differences  Level of measurement or scale of measure is a classification that describes the nature  of information within the numbers assigned to variables. Psychologist Stanley Smith  Stevens developed the best known classification with four levels, or scales, of  measurement: nominal, ordinal, interval, and ratio. Nominal: Categorical Scale those that use only labels. Measures categories Ordinal: Those with which the researcher can rank-order the respondents or responses. Interval: Rating scale for subjective properties in which the distance between each  descriptor is one scale unit (equal distance between any tow consecutive measures) Ratio: Ones in which a true zero exists, meaningful zeros +intervals Interval and Ratio are used when the distance between each level is known Reason – certain types of data require different measurements of data; no one scale can  apply.  Reliability: respondent responds in the same or a similar manner to an identical or  nearly identical measure Validity: accuracy or exactness of the measurement External Validity: The extent to which the results can be applied to and across  different persons, settings and time (nothing more than the independent variables  affect the dependent variables)  Internal Validity: The extent to which the observed effect is caused only by the  experimental treatment condition (generalization)
Page Expired
It looks like your free minutes have expired! Lucky for you we have all the content you need, just sign up here