Quantitative Data Analysis
Quantitative Data Analysis
1
What is data analysis?
Kisilu Kombo & Delno Tromp (2006)
• Refers to examining what has been collected in a survey or
experiment and making deductions and inferences
• Involves uncovering underlying structures; extracting
important variables, detecting any anomalies & testing any
underlying assumptions
• It involves scrutinizing the acquired information and
making inferences
2
Why carry out data analysis?
• The major purpose is to obtain usable and useful information
• The analysis whether qualitative or quantitative, may :
• Describe and summarise data
• Identify relationships between variables
• Compare variables
• Identify the difference between variables
• Forecast outcomes
3
Data analysis
• The term “data analysis” refers to the process by
which large amounts of raw data is reviewed in
order to determine conclusions based on that data.
• The data is often unorganized, and may come from
different sources
* 4
Definition of data analysis
• Data analysis is the process of bringing order, structure
and meaning to the mass of collected data.
• It is a practice in which raw data is ordered and
organized so that useful information can be extracted
from it.
• The nature of data analysis varies, and correlates to the
type of data being examined
* 5
Types of data analysis
• There are two broad categories:
• 1.QUANTITATIVE analysis
• 2. qualitative analysis.
• Quantitative data analysis is the process by which
numerical data is analyzed
• Qualitative data is the process by which data is not
described through numerical values, but rather by some
sort of descriptive context such as text is analyzed
* 6
Types of data analysis
• In practice, most researchers and evaluators
agree that combining quantitative and qualitative
techniques (sometimes called triangulation of
methods) produces a richer and more
comprehensive understanding of a study
* 7
QUANTITATIVE DATA ANALYSIS
• Quantitative data analysis is a systematic approach to
investigations during which numerical data is collected and/or the
researcher transforms what is collected into numerical data.
• Quantitative data analysis often describes a situation or event,
answering the “what” and “how many” questions you may have
about some thing.
• Quantitative data is processed before actual analysis by
conducting : editing/cleaning and coding
8
Quantitative data analysis
• Quantitative research involves analyzing numerical
data.
• Analysis of data is done using statistics (e.g.
regression analysis) or mathematical models
• Quantitative data analysis can be defined as the
process of presenting and interpreting numerical
data
* 9
Data analysis procedure
1. Data preparation: Checking, editing and coding
2. Data entry: entering the data into the computer
3. Data processing and analysis: Conducting statistical analysis
4. Presentation of results: Tables, charts or graphs may be used
5. Interpretation of findings. Explaining the meaning of data
individually
6. Conclusions. Proposing direct answers to the research question.
* 10
Scales of measurement
• Before you begin your analysis, you must identify
the level of measurement associated with the
quantitative data.
• The level of measurement can influence the type
of analysis you can use.
• Let us revise the four levels of measurement that
we learnt in the previous classes.
* 11
Scales of measurement
The scales of measurement include;
»Nominal
»Ordinal
»Interval
»Ratio (scale)
* 12
Nominal scale
• Data from categorical variables is measured on a
nominal scale.
• A nominal scale classifies categorical data into
distinct classes.
• Examples include; names of districts in Uganda
(Kampala, Mukono, Jinja, Pader, Gulu.),
• Marital status (single, married, divorced,
widowed).
* 13
Ordinal scale
• This scale like the nominal scale classifies subjects
• The ordinal scale however ranks subjects in terms of
degree to which they possess a characteristic of
interest
• The ordinal scale puts the subjects in order from
highest to lowest, from most to least
• The interval between ranks is not equal
* 14
Ordinal scale
• Ordinal scales are also measure of qualitative
data but only in cases where categories are
ordered.
• An ordinal scale is stronger than the nominal
scale.
• Used to measure attitudes on the basis of
judgment (strongly agree 4, agree 3, disagree 2,
strongly disagree 1), or when preference are
made
* 15
Interval scale
• An interval scale is described as an ordered scale
in which intervals have equidistant measures.
• For example the difference between 10 and 12 is the
same difference between 20 and 22.
• However, the doubling or tripling rule does not
hold with the interval scale since the scale does
not have a true zero.
* 16
Ratio scale
• The ratio-scale is the most common scale used
to measure quantitative data.
• Ratio data provides the highest level of
measurement.
• Unlike the interval scale, the ratio has a true and
meaningful zero as well as an equidistant
measure.
* 17
Ratio scale
• For example the difference between 10 and 15 is
the same difference between 20 and 25.
• Further, a 12 year old boy is thrice as old as a 4
year old boy.
• Examples of data measure on ratio-scale include;
age, money, time because all these variables
have a meaningful zero
* 18
Types of statistics
• Quantitative data analysis often involves
descriptive statistics and inferential statistics.
• To make sense of masses of data, the data is
summarized in some way, so that the reader
has some idea of the typical values in the data
and how these vary.
• To do this, descriptive or summery statistics is
used.
* 19
Descriptive statistics
– Descriptive statistics describes basic features of
data in a study.
– Provide trends of what is going on with the data
and also enable researcher’s present large data
sets in manageable forms.
* 20
Descriptive statistics
• Descriptive statistical analysis therefore is very
critical during initial stages of any quantitative
data analysis since it shows what the data is
like.
• Descriptive statistics too enables researchers of
quantitative studies visualize and summarize
data without carrying out any modeling.
* 21
Descriptive statistics
– Since no models are involved, descriptive
statistics can neither be used to neither test
hypothesis nor make any future predictions
using the study in question.
– Descriptive statistics include measures of
central tendency (averages: mean, median and
mode) and measures of variability about the
average (the standard deviation and the range)
* 22
Descriptive statistics
• These summaries may either form the basis of the
initial description of the data as part of a more
extensive statistical analysis, or they may be
sufficient in and of themselves for a particular
investigation.
* 23
Eg. Descriptive analysis of results
Teacher Evaluation Disagree Non-committal Agree
HOD assesses the way I teach 369 (39.5%) 51 514 (55%)
(5.5%)
Setting targets with the 391 (41.8%) 37 (3.9%) 507 (54.3%)
HOD
Evaluations HOD based on 391 (41.8%) 51 (5.5%) 492 (52.7%)
the targets set
* 25
Inferential statistics
•The choice of statistical method depends mainly on the level of
measurement of the variables
Types of Inferential Statistics
1.Inferential Statistics for Association
2.Inferential Statistics for Comparing Means
* 26
1. Inferential Statistics for Association
a). Correlation Analysis
If we are interested in whether two variables are related, then
we are interested in whether changes in one variable are
met with similar changes in the other variable.
To see the nature/ strength, direction and significance of the
bivariate relationships of the two variables used in the survey
or study, correlation is the right tool to deploy.
* 27
Directions of Relationships
Common Uses
The bivariate Pearson Correlation is used to measure the following:
(i). Correlations among pairs of variables
(ii). Correlations within and between sets of variables
What does Pearson’s Correlation indicate?
The bivariate Pearson correlation indicates the following:
1. Whether a statistically significant linear relationship exists between two
continuous variables
2. The strength of a linear relationship (i.e., how close the relationship is to
being a perfectly straight line)
3. The direction of a linear relationship (increasing or decreasing/ +Ve or -Ve)
eg. Correlations
significant at 0.01 level(2-tailed)
* 33
2.Regression analysis
• Regression analysis is a type of analysis used when a
researcher is interested in finding out whether an
independent variable predicts a given dependent
variable
• Simple regression is used when one is dealing with only
one independent variable and one dependent variable
• Multiple regression attempts to determine whether a
group of variables predict a dependent variable
* 34
Regression analysis
• Regression analysis yields a statistic called coefficient
of determination (R2)
• R2 refers to the amount of variation explained by the
independent variable or variables
• For example if R2 is calculated to be 0.54, it means
that 54% of the variation in a given dependent variable
is explained or predicted by the independent variable
and 46% is explained by other unknown factors
* 35
3. Chi-Square Test of Independence
1. Used to determine whether there is an association between categorical variables
(i.e., whether the variables are independent or related).
* 37
1. One-Way ANOVA
• One-Way ANOVA tests if the means on a metric variable for
two or more populations are all equal.
• The populations are identified in the sample by a categorical
variable.
• It determines whether there is statistical evidence that the
associated population means are significantly different
Levels of data analysis in quantitative analysis
Univariate Data Analysis
• Univariate data analysis-explores one variable at a time
• Serves as a good method to check the quality of the data
• Inconsistencies or unexpected results should be investigated using the
original data as the reference point
• Frequencies can tell you if many study participants share a
characteristic of interest (age, gender, etc.)
• Graphs and tables can be helpful
39
Univariate Data Analysis (cont.)
• Examining continuous variables can give you important
information:
• Do all subjects have data, or are values missing?
• Are most values clumped together, or is there a lot of variation?
• Are there outliers?
• Do the minimum and maximum values make sense, or could there
be mistakes in the coding?
40
Univariate Data Analysis (cont.)
• Commonly used statistics with univariate analysis of continuous
variables:
• Mean – average of all values of this variable in the dataset.
• Median – the middle of the distribution, the number where half of
the values are above and half are below.
• Mode – the value that occurs the most times.
• Range of values – from minimum value to maximum value.
• Standard deviation. – how the values deviate from the central
value(mean).
41
Bi- variate Analysis
• This analysis considers two variables at a time.
Techniques used include
1. Correlation analysis techniques i.e. Persons product moment
correlation coefficient, spearman's rank correlation coefficient
and Kendal rank correlation coefficient.
2. Cross tabulations. This will lead test like chi square, t-test,
ANOVA- one way analysis of variance etc
42
Multivariate Analysis
• Here you are looking at what is termed as dependent variable to be
explained by a series of independent variables.
E.g. Y=a+b1X1+b2X2+b3X3+…+bnXn
The use of each technique depends on data type I.e. it depends on the data
you have.
Data types include:
• Numeric
• Categorical. This is grouped data.
• Ordinal data
43
Thank You
Jah Bless
44