Marketing Research:

An Applied Orientation
Seventh Edition, Global Edition

Chapter 15
Frequency Distribution,
Cross-Tabulation &
Hypothesis Testing

Lecturer: Prof. Maya F. FARAH

 Chapter Outline

1. Frequency Distribution
2. Statistics Associated with Frequency Distribution: Measures of Location, Variability,
Shape
 Internet Usage Data

Table 15.1 contains data for 30

respondents giving:

 Gender (1=male, 2=female),

 Familiarity with the internet

(1=very unfamiliar, 7=very familiar),

 Net usage in hours per week &

attitude toward the Net & technology
(1=very unfavorable, 7=very favorable),

 Whether the respondents have done

shopping or banking on the net
(1= yes, 2= no).
 Frequency Distribution

 In a frequency distribution, one variable is considered at a time.

 A frequency distribution produces a table of frequency counts, percentages, &

cumulative % for all the values associated with a variable.

 Helps determine the extent of item non-response & indicates the extent of
illegitimate responses (ex.: values 0 or 8): for corrective action purposes.

 Indicates the shape of the distribution of the variable.

 Helps constructing visual representations: histogram, pie charts,…

Frequency of Familiarity with the Internet

… / Number of
actual responses.
Frequency Histogram
 Statistics Associated with Frequency Distribution:
Measures of Location, Variability & Shape
1. Measures of Location: describe the center of a distribution
 Mean: average of the responses
 Mode: most commonly given response
 Median: middle value of the data when arranged in an ascending or descending order (used
for ordinal data).
2. Measures of Variability: describe the dispersion of the values of the variable around the central
tendency measures.
 Range
 Interquartile range
 Variance (mean squared deviation of all the values from the mean) & Standard deviation
 Coefficient of variation: for ratio scales because it is a unitless measure
3. Measures of Shape: statistics that describe the shape of the frequency distribution curve.
 Skewness: In a skewed frequency distribution curve, the distribution is not symmetric about
a maximum but instead has one of its tails longer than the other.
 Curtosis: relative peakedness or flatness of the curve described by frequency distribution.
 Statistics Associated with Frequency Distribution:
1- Measures of Location: Mean

The mean, or average value, is the most commonly used measure of central tendency.

The mean , is given by

Where,

Xi = observed values of the variable X

n = number of observations (sample size)

= (2*2 + 62*3 + 62*4 + 3*5 + 8*6 + 4*7) / 29 = 4.724

 Statistics Associated with Frequency Distribution:
1- Measures of Location: Mode

 The mode is the value that occurs most frequently.

 It represents the highest peak of the distribution.

 A good measure of location when the variable is categorical or grouped into categories.
 Statistics Associated with Frequency Distribution
1- Measures of Location: Median

 The median of a sample is the middle value when the data are arranged in ascending
or descending order.

 If the number of data points is even, the median is estimated as the midpoint between
the 2 middle values: by adding the 2 middle values & dividing their sum by 2.

 It is the 50th percentile.

 Statistics Associated with Frequency Distribution:
2- Measures of Variability: Range & Inter-quartile range

 The range measures the spread of the data: difference between the largest &
smallest values in the sample.
Range = Xlargest – Xsmallest
Ex: Range = 7 - 2 = 5

 The inter-quartile range is the difference between the 75th & 25th percentile.
 For a set of data points arranged in order of magnitude, the pth percentile is the value
that has p% of the data points below it & (100 - p)% above it.
 Statistics Associated with Frequency Distribution:
2- Measures of Variability:
Variance, Standard deviation & Coefficient of Variation

 The variance: mean squared deviation from the mean. It can never be negative.
 The standard deviation is the square root of the variance.

Ex: s2= 2.493, s=1.579

 The coefficient of variation: the ratio of the standard deviation to the mean expressed
as a percentage, & is a unitless measure of relative variability.
 Statistics Associated with Frequency Distribution:
3- Measures of Shape: Skewness

 Skewness: tendency of the deviations from the mean to be larger in one direction than
in the other: tendency for one tail of the distribution to be heavier than the other.
 It can be either symmetric (values on either side of the center of the distribution are the
same, mean =mode= median) or skewed.
 Statistics Associated with Frequency Distribution:
3- Measures of Shape: Kurtosis

 Kurtosis is a measure of the relative peakedness or flatness of the curve defined by the
frequency distribution.

 The kurtosis of a normal distribution is zero.

 If the kurtosis is positive: the distribution is more peaked than a normal distribution.

 If the kurtosis is negative: the distribution is flatter than a normal distribution.

A General Procedure for Hypothesis Testing
 A General Procedure for Hypothesis Testing

 A null hypothesis (Ho) is a statement of the status quo, one of no difference or no effect.
If the null hypothesis is not rejected, no changes will be made.

 An alternative hypothesis (HA) is one in which some difference or effect is expected.

Accepting the alternative hypothesis will lead to changes in opinions or actions.

 Ho refers to a specified value of the population parameter (e.g., μ, , π), not a sample
statistic (e.g., X̅ ).

 Ho may be rejected, but it can never be accepted based on a single test.

 In research, Ho is formulated in such a way that its rejection leads to the acceptance of
the desired conclusion. HA represents the conclusion for which evidence is sought.