International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169

Volume: 2 Issue: 5 1188– 1190

_______________________________________________________________________________________________

Data Analysis of Students Marks with Descriptive Statistics

Dr. Manju Kaushik #1, Bhawana Mathur #2
Associate Professor #1, Research Scholar #2
Department of Computer Science#1, Department of Computer Science #2
JECRC University, jaipur#1, JECRC University, jaipur#2
India#1, India #2
1
manju.kaushik@jecrcu.edu.in,
2
bhawanamathur19@gmail.com

Abstract— Improving student’s academic performance is not an easy task for the academic community of higher learning. Descriptive
statistics is the discipline of quantitatively describing the main features of a collection of information, or the quantitative description itself.
We will be collecting the marks of 100 Students as population and here only marks of 20 students are shown as a sample and apply some
measures that can be used like are commonly used to describe a data set. There are different measures of central tendency and measures of
variability and dispersion. Measures of central tendency include the mean, median and mode, while measures of variability include the standard
deviation (or variance), the minimum and maximum values of the variables, kurtosis and skewness.

Keywords— Descriptive statistics, central tendency, measures of variability, dispersion, kurtosis and skewness.
__________________________________________________*****_________________________________________________
I. INTRODUCTION (e) Qualitative variable - A variable differing in quality is
Descriptive statistics provide simple summaries about the called a qualitative variable or attribute, for example, the color,
sample and about the observations that have been made. Such the degree of damage of a car in an accident.
summaries may be either quantitative, i.e. Summary statistics, (f) Discrete variable - A discrete variable is one which no
or visual, i.e. Simple-to-understand graphs. These summaries value may be assumed between two given values, for example,
may either form the basis of the initial description of the data as the number of children in a family.
part of a more extensive statistical analysis, or they may be (h) Continuous variable - A continuous variable is one which
sufficient in and of themselves for a particular investigation. any value may be assumed between two given values, for
Statistics is concerned with the scientific method by which example, the time for 100-meter run.
information is collected, organized, analyzed and interpreted
for the purpose of description and decision making.
Examples using statistics are: Hang Seng Index, Life or car
insurance rate, Unemployment rate, Consumer Price Index, etc.
There are two subdivisions of statistical method.
(a) Descriptive Statistics - It deals with the presentation of
numerical facts, or data, in either tables or graph form, and with
the methodology of analyzing the data.
(b) Inferential Statistics - It involves techniques for making
inferences about the whole population on the basis of
observations obtained from samples.
Fig.1 Major divisions in the field of Statistics
Some Basic Definitions
(a) Population - A population is the group from which data are
2. LITERATURE REVIEW
to be collected.
Experiential learning philosophy underlies simulation
(b) Sample - A sample is a subset of a population.
education, in which students are able to develop and refine
(c) Variable - A variable is a feature characteristic of any
knowledge. Simulation debriefing guides students through a
member of a population differing in quality or quantity from
reflection on what occurred during a simulation scenario, with
one member to another.
the goal of developing the knowledge and skills [12] (Mark A.
(d) Quantitative variable - A variable differing in quantity is
Neill, Karen Wotton).
called quantitative variable, for example, the weight of a person,
number of people in a car.
Studies have shown (demos, Garfield, Ooms, and Chance 2007)
that students’ abilities to describe and interpret a variable’s
distribution from a histogram, in the context of the data, is
1188
IJRITCC | May 2014, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169
Volume: 2 Issue: 5 1188– 1190
_______________________________________________________________________________________________
quite high even before taking a first course in statistics. While  Cross-tabulations and contingency tables
qualitative descriptions of a Distribution are helpful for  Graphical representation via scatter plots
summarizing a data set, students eventually will be asked to use  Quantitative measures of dependence
statistics to numerically describe a distribution in terms of  Descriptions of conditional distributions
center, variability, and shape. Without difficulty, they can see The main reason for differentiating univariate and bivariate
how the mean, median, and mode can indicate the center, and analysis is that bivariate analysis is not only simple descriptive
how standard deviation and range can describe variability. But analysis, but it also describes the relationship between two
the terms skewness and kurtosis are non-intuitive. Worse, different variables. [5]
skewness and kurtosis statistics and formulas are opaque to the 3. Advantages of Descriptive statistics
average student, and lack concrete reference points. Descriptive statistics is a powerful beast of burden:
A word about kurtosis is in order. Horswell and Looney (1993, (1) It collects and summarizes vast amounts of data and
p. 437) note that ―The performance of skewness tests is shown information in a manageable and organized manner,
to be very sensitive to the kurtosis of the underlying (2) A fairly straightforward process that can easily translate
distribution.‖ Few instructors say much about kurtosis, partly into results in a distribution of frequency, percents and overall
because it is difficult explains, but also because it is difficult to averages.
judge from histograms. Kurtosis is essentially a property of (3) Establishes standard deviation,
symmetric distributions (Balanda and MacGillivray 1988). (4) It's used when it may not be desirable to develop a complex
Data sets containing extreme values will not only be skewed, Research models,
but also generally will be leptokurtic. We cannot therefore (5) Deals with immediate data and single variables rather than
speak of non-normal Skewness as if it were separable from trying
non-normal kurtosis. The best we can do is to focus on the to establish conclusions,
skewness statistic simply as one test for departure from the (6) Can identify further ideas of research,
symmetric normal (7) A good primer to learn about statistical processes, and
Distribution. (8) Can lay the groundwork for more complex statistical
Cobb and Moore (1997, p. 803) note that ―In data analysis, analysis.
context provides meaning.‖ Realizing this, over the past several TABLE I:
decades, more and more instructors are using sample data FROM 100 STUDENTS MARKS AS A POPULATION, HERE
arising from real (or realistic) scenarios. One result is that ONLY MARKS OF 20 STUDENTS SAMPLE
students are learning that perfectly symmetrical graphical
displays are hard to find. Even with the ability to verbally
describe a distribution from a visual display, researchers have Case Students Marks (20)
found (delMas et al. 2007) that students cannot translate their
1 20
understanding of shape when asked to compare numerical
2 19
statistics such as the mean and median.
3 17
Hence, measures of skewness are becoming more important
(although many instructors may reasonably conclude that 4 18
kurtosis does not deserve extended discussion in a basic 5 17
statistics class) 6 17
3. Proposed Approach 7 17
1. Univariate Analysis 8 17
We will use Univariate analysis which is involves describing 9 17
the distribution of a single variable, including its central 10 18
tendency (including the mean, median, and mode) and 11 18
dispersion (including data-set, and measures of spread such as 12 19
the variance and standard deviation). The shape of the 13 17
distribution may also be described via indices such as 14 19
skewness and kurtosis. Characteristics of a variable's 15 18
distribution may also be depicted in graphical or tabular format, 16 17
including histograms and stem-and-leaf display. 17 19
2. Bivariate Analysis 18 18
When a sample consists of more than one variable, descriptive 19 19
statistics may be used to describe the relationship between pairs 20 16.8
of variables. In this case, descriptive statistics include:
1189
IJRITCC | May 2014, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169
Volume: 2 Issue: 5 1188– 1190
_______________________________________________________________________________________________
Analyze -> Descriptive Statistics -> Descriptives

Fig.2 Descriptives

Analyze - > Descriptive Statistics - > Frequencies

Fig.5 Histogram: Students Marks vs Frequency
TABLE III
Mean and Standard Deviation and Number of Students
Mean Std. Deviation N
89.45 4.893 20
TABLE IIIII
Frequencies of 20 Students Results

Mean 89.45

Std. Error of Mean 1.094

Median 88.85
Mode 85
Std. Deviation 4.893

Variance 23.945
Skewness 0.580
Standard Error of Skewness 0.512
Kurtosis -0.874
Standard Error of Kurtosis 0.992
Fig.3 Frequencies
Range 16
Minimum 84

Maximum 100

RESULT
Measures of central tendency include the mean is
89.45, median is 88.85 and mode are 85, while measures of
variability include the standard deviation is 4.893 and the
variance is 23.945, the minimum is 84 and maximum values of
the variables are 100, kurtosis are -0.874 and skewness. are
Fig.4 Students Marks
0.580

1190
IJRITCC | May 2014, Available @ http://www.ijritcc.org
_______________________________________________________________________________________
International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169
Volume: 2 Issue: 5 1188– 1190
_______________________________________________________________________________________________
CONCLUSIONS AND FUTURE WORK [10] T.P. Hettmansperger, and R. H. Randles,‖ A practical new
In this study, we make use of descriptive statistics in the equivalent multivariate median‖, Journal of Biometrika,
student’s database this technique to predict the student’s Vol. 89, pp. 851-860, 2002.
learning activities. The information generated after the [11] R. A. Johnson, and D. W. Wichern, Applied Multivariate
implementation of descriptive statistical technique may be Statistical Analysis, 4th Ed., Upper Saddle River, New
helpful for the instructor as well as for the students. This work Jersey: Prentice Hall, 2002.
may improve student’s performance; reduce failing ratio by [12] Mark A. Neill, ― High-Fidelity Simulation Debriefing in
taking appropriate steps at the right time to improve the quality Nursing Education: A Literature Review‖, Clinical
of education. Simulation in Nursing, Volume 7, Issue 5, Pages e161–
For future work, we will refine our technique in order to get e168, September 2011
more valuable and accurate outputs that would be, useful for [13] A Haarala-Muhonen, M Ruohoniemi, ”Comparison of
instructors to improve the students learning outcomes. students’
REFERENCES Perception of their teaching –learning environment in
[1] R. Serfling, "Robust, Affine Invariant, Computationally three professional
Easy Nonparametric Multivariate Outlyingness Academic disciplines: A valuable tool for quality
Functions", Session on "Data Depth Methods in Data enhancement-
Mining, Clustering, and Beyond", International Learning Environments ―, International Journal of
Conference on Nonparametric Statistics and Statistical Springer, 2011.
Learning, Ohio State University, May 2010. [14] David P. Doane, Lori E. Seward, ―Measuring Skewness:
[2] L Hartling, A. Chisholm, D. Thomson, DM Dryden, ―A A Forgotten
Descriptive Statistic‖, Journal of Statistics Education, Volume 19,
Analysis of Overviews of Reviews ―, Health Care Number 2, 2011,
Literature, Published
between 2000 and 2011.
[3] A. Field Miles, J., & Z. Field, ―Discovering statistics
using R.‖,
American Psychological Association, Washington, DC,
2012.
[4] De Veaux, RD, Velleman, PF & Bock, DE, Intro Stats,
th
4 edn, Pearson
Addison Wesley, Boston. , 2009.
[5] Argyrous, G. Statistics for Research: With a Guide to
SPSS, SAGE,
London, ISBN 1-4129-1948-7, 2005
[6] R. Levesque, SPSS Programming and Data Management:
A Guide for SPSS and SAS Users, Fourth Edition, SPSS
Inc., Chicago, Ill. ISBN 1-56827-390-8, 2007.
[7] SPSS 15.0 Command Syntax Reference, SPSS Inc.,
Chicago, Ill, 2006.
[8] Wellman, B. "Doing It Ourselves: The SPSS Manual as
Sociology's Most Influential Recent Book." pp. 71–78
in Required Reading: Sociology's Most Influential Books,
edited by Dan Clawson. Amherst: University of
Massachusetts Press, ISBN 978-1-55849-153-3, 2006.
[8] R. Serfling, "Advances in Nonparametric Multivariate
Statistics in Bootstrap and Data Depth", International
Indian Statistical Association (IISA) Conference,
Riverside, July 2014
[9] J. B. Davis, and J. W. McKean, ―Rank based methods for
multivariate linear models‖, Journal of the American
Statistical Association, Vol. 88, pp. 245-251, 1993.

1191
IJRITCC | May 2014, Available @ http://www.ijritcc.org
_______________________________________________________________________________________