MKF5912 - Marketing Research Data Analysis: SPSS Output Analysis

This assignment presents an analysis of marketing research data, focusing on hypothesis testing, cross-tabulation, and the interpretation of SPSS output. Part A examines the analysis of output, including p-values and levels of significance, with examples of cross-tabulation and its utility in identifying relationships between variables. Part B delves into the variables used in cross-tabulation, including how to handle variables that cannot be directly used in cross-tabulation strategies, and how to perform the necessary calculations to incorporate these variables. The document also includes an analysis of correlations, including Pearson correlation, and provides a sample cross-tabulation question to illustrate the process of hypothesis testing, as well as the Chi-Square test to determine the association between age and brand preference. The assignment provides detailed steps to formulate hypotheses and interpret the results of the statistical tests.

Marketing Research Data Analysis I Logic of Hypothesis Testing and
Cross Tabulation

Table of Contents
Part A...............................................................................................................................................3
Part B...............................................................................................................................................3

Part A
1. Analyses of output
The output result shows the p value is greater than 0.05 (0.055 > P > 0.05). This indicates that
there is evidence of failed to reject null hypothesis and no variables effect each other.
2. Level of significance
The other levels of significance exists includes 99% and 90%. If the level of significance is
allowable at 90% confidence interval. Then, null hypothesis will be rejected on the ground that
value of p is lower than significance level (0.055 < P < 0.10).
3. Cross-tabulation
The minimum number of observed and expected counts in cross-tabulation provides the data
about degree of freedom, which again useful in identifying critical value of assigned variables.
Routine studies estimate the expected recurrence that would be normal in a cell if the factors
were autonomic. By taking a look at the differences between the detected cell studies and normal
cell levels, you can see which factors have the biggest differences, which can be reliable.
Part B
Variables in Cross-tabulation
Cross-tabulation, also known as a cross-tab or fitness table, is a measurable tool for unlimited
information. Unauthorized information includes inherently unrelated values. Scientists use
hyper-classification to examine the connection within information that is not immediately clear.
It is very valuable in surveys and statistical analysis studies. A crosstab report shows the link
between at least two studies performed in the experiment.
The crosstab is a well-known solution for analyzing measurable information. As a monitoring /
exposure tool, it tends to be used with any level of information: prescriptive or accessible. Treat
all information as easy to see (visible information is not considered. It is sorted).
Treatment of variables that cannot be used directly in cross-tabulation

Not all factors in the rankings and denominators can be used directly in a cross-adjustment
strategy for SPSS. Steps to record these factors in cross-classifications:
The first step is to develop the crosshairs yourself. Calculate the figure that should be reached in
the cell where variable 1 (drug) rises to 1 and variable 2 (disease) rises to 1. This is 0.33 * 276 =
91.
You must do the same for the cell where variable 1 equals 2 and variable 2 equals 1 (0.34 * 392
= 135). To get the figure for the cell where variable 1 equals 1 and variable 2 equals 2, we
subtract 91 from 276 to 185. A similar strategy must be followed for its cell where variable 1 is
equal to 2 and variable 2 is equal to two (392-135 = 257).
In order for SPSS to extract the cross-section and calculate the Chi-square value, you can use the
"weight by" option. It will also receive the same offer as the "standard" database. So when you
need to know if there is a relationship between two similar factors and you do not have the first
data set, know enough about the extensions and nouns to get an answer.
Correlations
What is your
nationality?
Do you use
Instagram?
2. How old
are you?
How often do you use
Instagram in a day?
What is your
nationality?
Pearson
Correlation 1 -.506** -.102 -.097
Sig. (2-tailed) .002 .554 .573
N 36 36 36 36
Do you use Instagram? Pearson
Correlation -.506** 1 .202 -.053
Sig. (2-tailed) .002 .239 .760
N 36 36 36 36
2. How old are you? Pearson
Correlation -.102 .202 1 -.234
Sig. (2-tailed) .554 .239 .170
N 36 36 36 36
How often do you use
Instagram in a day?
Pearson
Correlation -.097 -.053 -.234 1
Sig. (2-tailed) .573 .760 .170
N 36 36 36 36
**. Correlation is significant at the 0.01 level (2-tailed).