Professional Documents
Culture Documents
Part A:
Descriptive research is done to describe the answers to the who, what, where, when and
how questions. When we want to know who our customers are, which brands they buy and
how much, where they buy the brand, when to shop and how they learn about our products,
we turn to descriptive studies. Descriptive research is also desirable when we want to project
the study's findings to a larger population group. If the sample of a descriptive study is
representative, the findings can be used to predict some variables of interest such as sales.
Causality research is used to measure causality in relationships, such as "if x, then y".
Cause and effect is a condition in which one or more variables affect one or more other
variables. When conducting cause and effect research, the "if-then" statement becomes the
way we manipulate variables of interest. For
Question 6: Four different types of probability sampling methods are: Simple random
sampling, Systematic sampling, Cluster sampling, Stratified Sampling
- Stratified Sampling: Divide the population into different subgroups and then sample all of
these subgroups. For example, the researcher can divide an adult sample into subgroups
according to age, such as 18–29, 30–39, 40–49, 50–59, and 60 and older. To stratify this
sample, the researcher would then randomly select a proportional number of people from
each age group. Stratified random sampling provides better population coverage as
researchers have control over subgroups to ensure they are all represented in the sample.
- Simple random sampling: the probability of being selected into the sample is “known” and
equal for all members of the population. For example: The names of 25 employees were
chosen from a company with 250 employees. In this case, the population is 250 employees
in total, and the sample is collect random which each employee has an equal chance of
being selected. Simple random sampling is effective when the company want to have the
result straight away. It also cost less that the company can research it through the internet.
Question 4:
The person-administered survey is the survey which conducted by the humans such as an
interviewer reads the question, in person or over the phone, to the respondent and records
their responses without using a computer.
- Person-administered surveys have four unique advantages: They offer feedback, rapport,
quality control, and adaptability.
1.Feedback: The interviewer can easily give the feedback after the survey. A human
interviewer may be allowed to adjust his or her questions according to verbal or nonverbal
cues.
2.Rapport: It is often helpful to have another person present to develop some relationship
with the respondent early in the questioning process. One can create trust and
understanding that other forms of non-personal data collection cannot achieve.
3. Quality Control: Using a personal interviewer ensures that every question will be asked of
the respondent. Additionally, some researchers feel that respondents were more likely to be
honest when they answered directly.
1. Slow speed: Sometimes the individual interviewer just needs to jot down the respondent's
answer using pencil and paper, this requires a separate data entry step to create the
computer data file.
2. High cost naturally: It is more expensive to use a face-to-face interviewer than to mail the
questionnaire to the respondent . Often, the individual interviewers are highly trained and
skilled, which explain the cost factor.
Advantages of Computer-Assisted Surveys: speed, Relatively Error-Free Interviews, use of
picture
1.Speed: Perhaps the greatest advantage of computer-assisted data collection is its ability to
collect survey data very quickly. The computer aided approach is much faster than the
purely human interviewing approach. A computer doesn't become tired or bored, and it
doesn't make human errors. The speed factor translates into cost savings.
3.Use of Pictures: Audiovisuals and Graphics Computer graphics can be integrated into
questions as they are viewed on a computer screen. Rather than having an interviewer pull
out a picture of a new type of window air conditioner, for instance, computer graphics can
show it from a 360-degree perspective. High-quality video may be programmed so that the
respondent can see the product in use or can be shown a wide range of audiovisual
displays.
1.Technical Skills May Be Required: Significant programming skills are required to master
computer interfaces.
2.Setup Costs Can Be High: While computer technology can result in increases in
productivity, there can be high setup costs associated with getting some of these systems in
place and operational.
Question 2:
- Incompatible Reporting Units: Secondary data are provided in reporting units, such as, in
the case of area units, county, city, metro area, state, region, ZIP code, and other statistical
areas. A researcher’s use of secondary data often depends on whether the reporting unit
matches the researcher’s need. County data is almost incomplete. Another marketer wants
to know the demographic structure of each ZIP code in a major city to determine which ZIP
codes to target for a direct mail campaign. Again, county data will be inconsistent.
- Outdated Data: Sometimes a marketing researcher will find the information reported with
the desired unit of measurement and the proper classifications; however, the data may be
outdated and no longer reliable. Some secondary data are published only once. However,
even for secondary data published at regular intervals, the time that has passed since the
last publication can be a problem when applying the data to a current problem. The
researcher must assess the usefulness of the available data.
Part B
Question 9
The SPSS testing is an independent sample t test analysis whether English-speaking and
Non-English Speaking Background have different confident in cooking vegetables
Question 10
The SPSS testing is a Correlation test analysis whether Attitude has any relationship with
Intentions
- Decision rule: if calculated significance value is (SPSS output) < Critical Significance value
(0.05)
- Reject Null Hypothesis (this means alternative hypothesis is our conclusion)
- Decision: Calculate significance value is 0.000 <0.05
- This means we reject the null hypothesis (Alternative hypothesis is accepted)
Attitude does have strong relationship with Intentions which is reflected through the Pearson
Correlation coefficient (.381)
Question 8:
The SPSS testing is a Chi –Square testing analysis whether the Non-English Speaking
Background determines the frequently watch cooking shows on Television.
Ho: Non-English Speaking Background does not determine the frequently watch cooking
shows on Television
H1: Non-English Speaking Background determines the frequently watch cooking shows on
Television
Recommendation: The does determine the frequently watch cooking shows on Television.
They may find out the different langue may difficult to understand which in TV people speak
more faster than normal.
Short answer practice
Q1. What is the relationship between the following research designs: exploratory,
descriptive and causal?
The relationship between each other is the step by step method which is used for research
purposes. The causal step is not always needed or ideal for marketers.
Q2. You are charged with the responsibility of determining whether men are brand
conscious when shopping for camping equipment. List the ways in which this
information could be obtained. Which method is best and why?
As a researcher there are a number of ways in which the information could be obtained.
Through two main sources of collection which can be either: Communication or Observation
Dependant on the researcher’s objectives the most suitable collective methods are:
- Surveys
- Focus Groups
- Interviews
Personally I would recommend the use of online surveys as they can be the cheapest yet
quickest way to gather information for the researcher.
-> As the surveys would provide the basis of information needed for the marketer, if a more
detailed research is required the marketer can intend to look at multiple uses of marketing
research and using a mix of multiple methods.
Q3. What role does exploratory research play in the marketing research process?
How does exploratory research differ from other forms of marketing research?
Exploratory research differs from other marketing research types through the format and
structure it follows. Exploratory research has a more relaxed approach in comparison to
others, as exploratory research works well when the marketer doesn’t know much about the
research objectives. Exploratory research can play the beginning phase of a marketing
research process.
Q5. ABC Bank has 100,000 customers. The management wishes to draw a sample of
200 customers.
(a) Identify the population and sampling frame that could be used.
Target Population:
All Australian, household and business customers of ABC Bank branches in NSW as of July
2016
- Sampling Frame:
ABC Bank’s Sampling Frame would be a list of all customers at all ABC Bank’s branches
across NSW. (all demographics)
- Sampling Technique:
I would recommend Simple Random technique. As this technique would be really easy to
undertake for the management team and as all the names and details are available to the
Bank’s database that would contribute to the random draw factor. As the question does not
specify not to focus on a particular segment, Simple Random Technique is best suitable for
the ABC Bank.
Q6. Develop a plan for conducting a focus group to determine traveller attitude toward
preferences for airlines. Specify objective of the focus group and write a screening
questionnaire.
Objectives:
What kind of attitudes do travellers have towards the top 3 airlines?
Which airline do travellers prefer the most and why?
Screening Questionnaire:
Frequency of travel?
Frequency of airline usage?
International or Domestic?
Have you travelled on an airline in the past month? Which other airlines are you aware of?
What other airlines would you consider while travelling?
What airlines have you travelled on in the past 5 years?
Q8. Study the following SPSS outputs (please note: scale used was 1 “Strongly
Disagree” through to 7 “Strongly Agree”), and then:
- Test gì
- Investigating cái vấn đề gì (xem ở bảng)
- Scale used là cái gì (đề cho)
xem mean
xem % confidence interval cos chenh nhieu hay k. (so với chỗ mean difference và
error mean)
chenh nhieu => dis;
k chenh nhieu => agree
- Null Hypothesis: Students do not trust comments made by their Facebook friends.
- Alternative Hypothesis: Students do trust comments made by their Facebook friends.
Decision Rule:
- If the significance level is less than 0.05 then we reject the null hypothesis, alternatively if
the corresponding t-value is greater than 1.56 then again we reject the null hypothesis.
With the results provided we reject the null hypothesis as the significance level is less than
0.05, as the corresponding t-value is greater than 1.56
Recommendation = In conclusion the results provided, individuals trust the comments made
by their Facebook friends.
a) The SPSS testing is a Chi-Square testing analysis which is investigating whether age
determines the amount of hours you spend on Facebook each day.
- Null Hypothesis: Age does not determine the amount of hours spent on Facebook each
day.
- Alternative Hypothesis: Age does determine the amount of hours spent on Facebook each
day.
b) SignificanceLevel=0.05
Decision Rule
- If significance level is less than 0.05 then we reject the null hypothesis Significance Level =
0.005
With the results provided we reject the null hypothesis, as there is an association between
an individual’s age and the amount of hours spent on Facebook each day. Accepting the
alternative hypothesis, there is a weak association between the variables according to
Cramer’s V.
Recommendation = Age does determine the amount of hours spent on Facebook each day.
a) The SPSS testing is a correlation testing analysis which is investigating the relationship
between life satisfaction and job satisfaction and whether the two have a correlation with
each other.
b) Significance Level=0.05
Decision Rule
- If the significance level is less than 0.05 then we reject the null hypothesis.
Significance Level = 0.000
With the results provided we reject the null hypothesis and accept the alternative hypothesis
CHAPTER 3:
Secondary data is gathered and recorded by the company (“internal”) or someone else
(“external”) prior to and for a purpose other than the current project:
Secondary data sources: company, library, internet, public report, literature review,
customer feedback through phone are sources of secondary data
Advantages:
(1) Secondary data can be obtained quickly
(2) compared to collecting primary data, secondary data are inexpensive
(3) secondary data are readily available
(4) secondary data may enhance primary data collection by providing a current look at
issues, trends, yardsticks of performance
(5) secondary data may be all that is needed to achieve the research objective.
Disadvantages:
1. incompatible reporting units
2. mismatch of the units of measurement
3. differing definitions used to classify the data
4. timeliness of the secondary data
5. lack of information needed to assess data credibility.
Customized service data: exclusively collect for industry to sell for
clients
CHAPTER 4:
- Methods:
+ Secondary Data Analysis
+ Experience Surveys
+ Case Analysis
+ Focus Groups
•Causal research designs. Conducted to identify cause and effect relationships between two
or more variables.
•The type of research design selected depends on the degree of uncertainty in the problem
definition:
- High level of uncertainty -> Exploratory research.
- Low level of uncertainty -> Conclusive research.
Independent variables are variables over which the researcher has control and wishes to
manipulate to measure the effect on the dependent variable.
Extraneous variables are all of the variables other than the independent variables that may
have an effect on the dependent variable.
CHAPTER 5:
Qualitative Quantitative
3 main limitations:
subjective – depend on
interviewers because the same
respondents but
small sample size
cannot have statistic
Qualitative Research
Qualitative research involves collecting, analyzing, and interpreting data by observing what
people do and say. Qualitative research techniques afford rich insight into consumer
behavior.
VD: yêu cầu vài người thể hiện ý kiến về cai rượu ở sinh viên. Ta sẽ nhận nhiều câu trả lời
khác nhau. Sau khi nghiên cứu kĩ, ta có thể mô tả từng câu hỏi rằng nó là tích cực, tiêu cực
hay trung lập.
•Research mostly used to gain preliminary insights into decision problems and opportunities.
•Places emphasis on words, stories, visual portrayals and expressive descriptions.
•Typically associated with exploratory designs.
Quantitative Research
Quantitative research is defined as research involving the administration of a set of
structured questions with predetermined response options to a large number of respondents.
•Research that places heavy emphasis on producing generalizable data.
•Places emphasis on numbers and rigorous mathematical analysis.
•Typically associated with descriptive and causal designs.
Observation methods
are techniques in which phenomena of interest involving people, objects, and/or activities
are systematically observed and documented.
To observe real situation happening between customers and sale people => in situ
- observe how sales person serve the customers in a short period of time
- private not public one because of small sample size
How focus group work? Focus group participants’ comments are encouraged and guided
by moderators.
Not use in prediction or when a major decision affect company’s livelihood rests on research
results
IN-DEPTH INTERVIEWS
An in-depth interview, commonly referred to as an IDI, is defined as a set of probing
questions posed one-on-one to a respondent by a trained interviewer to gain an idea of what
the respondent thinks about something or why he or she behaves in a certain way.
PROTOCOL ANALYSIS
Protocol analysis places people in a decision making situation and asks them to verbalize
everything they considered.
PROJECTIVE TECHNIQUES
Projective techniques involve situations in which participants are placed in (projected into)
simulated activities in the hopes that they will divulge things about themselves that they
might not reveal under direct questioning.
CHAP 7:
the pro income of data survey method. Study carefully slide 8 in chap 14
CHAP 8:
Types of Measures
Nominal measures are defined as those that use only labels; that is, they possess only
the characteristic of description. Examples include designations as to race, religion, type
of dwelling, gender, brand last purchased, and buyer/non buyer.
Answers involve yes–no, agree–disagree, or any other instance in which the descriptors
cannot be differentiated except qualitatively.
Ordinal measures permit the researcher to rank order the respondents or their responses.
For instance, if the respondent is asked to indicate his or her first, second, third, and fourth
choices of brands, the results are ordinally scaled.
Ordinal scales indicate only relative size differences among objects: greater than, less than,
or equal to.
Scale measures are those in which the distance between each level is known.
- Do not use leading questions that have strong cues on how to answer.
- Do not use loaded questions that have unjustified assumptions.
- Do not use double-barreled questions that ask two questions at the same time.
- Do not use overstated questions with wording that overemphasizes the case.
QUESTION FLOW
- Screens: Used to select the respondent types desired by the researcher to be in the survey
- Warm-up questions: get the respondent’s interest and demonstrate the ease of responding
to the research request.
- Transitions are statements made to let the respondent know that changes in question topic
or format are forthcoming.
- Complicated and difficult to answer questions are placed deep in the questionnaire.
- Demographics questions are used to classify respondents into various groups for purposes
of analysis.
CHAP 9,10
The population is the entire group under study as defined by research objectives.
The sample is a subset of the population, and the sample unit pertains to the basic level of
investigation.
Conduct a census study, aim at total customers => cover data collection to all people in the
population
Sample means selecting proportion in the population to save time and money
Sample frame: lists of respondents, frame to select sample. Sample unit should be individual
who are qualified for recruitment
Sample error: select some for study and others are not selected
Sample frame error: area are not selected for study
Sample size
a term to define the number of subjects included in a sample size. By sample size, we
understand a group of subjects that are selected from the general population and is
considered a representative of the real population for that specific study.
n = N*X / (X + N – 1),
Sampling: the way you select information, select methods for survey
Probability samples are samples in which members of the population have a known
chance (probability) of being selected into the sample.
Nonprobability samples , on the other hand, are samples where the chances (probability)
of selecting members from the population into the sample are unknown.
Systematic Sampling
Using a sample frame that lists members of the population, the researcher selects a random
starting point for the first sample member. A constant skip interval , calculated by dividing the
number of population members in the sample frame by the sample size, is then used to
select every other sample member from the sample frame. This procedure accomplishes the
same end as simple random sampling, and it is more efficient.
Cluster Sampling
The sample frame is divided into groups called clusters, each of which must be highly similar
to the others. The researcher can then randomly select a few clusters and perform a census
of each one (one stage). Alternatively, the researcher can randomly select more clusters and
take samples from each one (two stages). This method is desirable when highly similar
clusters can be easily identified, such as subdivisions spread across a wide geographic
area.
Stratified Sampling
If the population is believed to have a skewed distribution for one or more of its
distinguishing factors (e.g., income or product usage), the researcher identifies
subpopulations in the sample frame called strata . A simple random sample is then taken of
each stratum.
CHAP 13
5. Integrated Features
The leading panel companies usually have
several survey services for customers.
responsible for answer they provide, avoid they get incentive, fast to access and get
information from them based on database, but those professional respondents pay
less attention => that’s why quality of data is low
SPSS
CHAPTER 12:
Descriptive analysis is used to describe the variables (question responses) in a dataset (all
respondents’ answers).
Difference analysis is used to compare the mean of the responses of one group to that of
another group, such as satisfaction ratings for “heavy” users versus “light” users.
CHAPTER 13:
t test is defined as the statistical inference test to be used with small samples sizes
(n <= 30).
Any instance when the sample size is >= 30 requires the use of a z test.
DIFFERENCES BETWEEN PERCENTAGES WITH TWO GROUPS (INDEPENDENT
SAMPLES)
- the first step requires a comparison of the two percentages (using arithmetic).
of confidence
ANOVA will “signal” when at least one pair of means has a statistically
significant difference, but it does not tell which pair
CHAPTER 14:
Chi-square
The Chi-square distribution is skewed to the right and the rejection region is always at the
right-hand tail of the distribution
It differs from the normal and t distributions in that it changes its shape depending on the
situation at hand, and it does not have negative values.
-> the Asymp. Sig. corresponds to the probability of support for the null hypothesis.
Significance in this example is .020 (con này nhỏ hơn 0.05), which means that there is
practically no support for the hypothesis that Gender and Favorite magazine type are not
associated. In other words, they are related.
In other words, because the significance is less than .05, it is worthwhile to inspect and
interpret the percentages in the cross-tabulation table.
SPSS VIDEO
Independent sample test
dùng để xem biến định lượng khác với biến định tính hay k
● Independent Sample T-Test chúng ta sẽ áp dụng kiểm định sự khác biệt trung
bình với trường hợp biến định tính có 2 giá trị.
Ví dụ như biến giới tính (nam, nữ), biến thành phố (TPHCM, Hà Nội), biến vùng miền
(Miền Bắc, Miền Nam)… Trường hợp biến định tính có 3 giá trị, chúng ta sẽ thực hiện
3 cặp so sánh (1-2, 1-3, 2-3). Tuy nhiên, việc so sánh từng cặp giá trị như vậy khá bất
tiện và mất thời gian nếu số giá trị tăng lên 4, 5, 6…
● ANOVA giúp chúng ta giải quyết trở ngại của Independent Sample T-Test.
Phương pháp này giúp chúng ta so sánh trị trung bình của 3 nhóm trở lên.
ANOVA có 3 phương pháp: ANOVA 1 chiều, ANOVA 2 chiều và MANOVA.
Tuy nhiên, trong phạm vi tài liệu này chúng ta chỉ nói tới phương pháp
ANOVA 1 chiều (One-Way ANOVA).
b. Critical significance value is 0.05, the test is done on a 95% confidence interval.
Compare critical significance value with calculated significance value based on the
decision rule.
Decision Rule: If calculated significance value <0.05, then reject null hypothesis.
Decision rule: if calculated significance value <0.05, then we reject the null
hypothesis
a. The SPSS testing is ANOVA testing analysis investigating [ cái vấn đề này đề
cho].
b. Critical significance value is 0.05, the test is done at a 95% Confidence Interval
Decision rule: if calculated significance value < 0.05, we reject the null
hypothesis.
Chi - squared test helps to find out the association between variables.
a. The spss test is Chi-Square testing analysis investigating [vấn đề này đề cho].
b. Critical significant value is 0.05, the test is done at a 95% confidence level.
Decision rule: if the calculated significance level < 0.05, we reject the null
hypothesis,
Calculated significance value is .029 < 0.05
We reject the null hypothesis
Therefore, viết câu statement của alternative hypothesis.
Câu 5:
a. The spss test is One - sample t test analysis investigating [đề cho].
Compare critical sig value with calculated sig value depend on the decision
rule
Decision rule: If signìicance value < 0.05, we reject the null hypothesis
Câu 6: