Scribd
Upload
46 views8 pages

Descriptive Statistics - Wikipedia

Uploaded by

nikhil.rajput08012004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
46 views8 pages

Descriptive Statistics - Wikipedia

Uploaded by

nikhil.rajput08012004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

Descriptive statistics

A descriptive statistic (in t he count noun sense) is a summary st at ist ic t hat quant it at ively
describes or summarizes feat ures from a collect ion of informat ion,[1] while descriptive
statistics (in t he mass noun sense) is t he process of using and analysing t hose st at ist ics.
Descript ive st at ist ics is dist inguished from inferent ial st at ist ics (or induct ive st at ist ics) by it s
aim t o summarize a sample, rat her t han use t he dat a t o learn about t he populat ion t hat t he
sample of dat a is t hought t o represent .[2] This generally means t hat descript ive st at ist ics, unlike
inferent ial st at ist ics, is not developed on t he basis of probabilit y t heory, and are frequent ly
nonparamet ric st at ist ics.[3] Even when a dat a analysis draws it s main conclusions using inferent ial
st at ist ics, descript ive st at ist ics are generally also present ed.[4] For example, in papers report ing
on human subject s, t ypically a t able is included giving t he overall sample size, sample sizes in
import ant subgroups (e.g., for each t reat ment or exposure group), and demographic or clinical
charact erist ics such as t he average age, t he proport ion of subject s of each sex, t he proport ion
of subject s wit h relat ed co-morbidit ies, et c.

Some measures t hat are commonly used t o describe a dat a set are measures of cent ral
t endency and measures of variabilit y or dispersion. Measures of cent ral t endency include t he
mean, median and mode, while measures of variabilit y include t he st andard deviat ion (or variance),
t he minimum and maximum values of t he variables, kurt osis and skewness.[5]
Use in statistical analysis
Descript ive st at ist ics provide simple summaries about t he sample and about t he observat ions
t hat have been made. Such summaries may be eit her quant it at ive, i.e. summary st at ist ics, or
visual, i.e. simple-t o-underst and graphs. These summaries may eit her form t he basis of t he init ial
descript ion of t he dat a as part of a more ext ensive st at ist ical analysis, or t hey may be sufficient
in and of t hemselves for a part icular invest igat ion.

For example, t he shoot ing percent age in basket ball is a descript ive st at ist ic t hat summarizes
t he performance of a player or a t eam. This number is t he number of shot s made divided by t he
number of shot s t aken. For example, a player who shoot s 33% is making approximat ely one shot
in every t hree. The percent age summarizes or describes mult iple discret e event s. Consider also
t he grade point average. This single number describes t he general performance of a st udent
across t he range of t heir course experiences.[6]

The use of descript ive and summary st at ist ics has an ext ensive hist ory and, indeed, t he simple
t abulat ion of populat ions and of economic dat a was t he first way t he t opic of st at ist ics
appeared. More recent ly, a collect ion of summarisat ion t echniques has been formulat ed under
t he heading of explorat ory dat a analysis: an example of such a t echnique is t he box plot .

In t he business world, descript ive st at ist ics provides a useful summary of many t ypes of dat a.
For example, invest ors and brokers may use a hist orical account of ret urn behaviour by
performing empirical and analyt ical analyses on t heir invest ment s in order t o make bet t er
invest ing decisions in t he fut ure.

Univariate analysis
Univariat e analysis involves describing t he dist ribut ion of a single variable, including it s cent ral
t endency (including t he mean, median, and mode) and dispersion (including t he range and
quart iles of t he dat a-set , and measures of spread such as t he variance and st andard deviat ion).
The shape of t he dist ribut ion may also be described via indices such as skewness and kurt osis.
Charact erist ics of a variable's dist ribut ion may also be depict ed in graphical or t abular format ,
including hist ograms and st em-and-leaf display.

Bivariate and multivariate analysis


When a sample consist s of more t han one variable, descript ive st at ist ics may be used t o
describe t he relat ionship bet ween pairs of variables. In t his case, descript ive st at ist ics include:

Cross-tabulations and contingency


tables
Graphical representation via scatterplots
Quantitative measures of dependence
Descriptions of conditional distributions
The main reason for different iat ing univariat e and bivariat e analysis is t hat bivariat e analysis is not
only a simple descript ive analysis, but also it describes t he relat ionship bet ween t wo different
variables.[7] Quant it at ive measures of dependence include correlat ion (such as Pearson's r when
bot h variables are cont inuous, or Spearman's rho if one or bot h are not ) and covariance (which
reflect s t he scale variables are measured on). The slope, in regression analysis, also reflect s t he
relat ionship bet ween variables. The unst andardised slope indicat es t he unit change in t he
crit erion variable for a one unit change in t he predict or. The st andardised slope indicat es t his
change in st andardised (z-score) unit s. Highly skewed dat a are oft en t ransformed by t aking
logarit hms. The use of logarit hms makes graphs more symmet rical and look more similar t o t he
normal dist ribut ion, making t hem easier t o int erpret int uit ively.[8]: 47
References

1. Mann, Prem S. (1995). Introductory


Statistics (2nd ed.). Wiley. ISBN 0-471-
31009-3.

2. "Drawing Conclusions From Data:


Descriptive Statistics, Inferential Statistics,
and Hypothesis Testing" (https://dx.doi.org/
10.4135/9781506304144.n6) , Interpreting
and Using Statistics in Psychological
Research, Thousand Oaks, CA: SAGE
Publications, Inc, pp. 145–183, 2017,
doi:10.4135/9781506304144.n6 (https://d
oi.org/10.4135%2F9781506304144.n6) ,
ISBN 978-1-5063-0416-8, retrieved
2021-06-01
3. Dodge, Y. (2003). The Oxford Dictionary of
Statistical Terms (https://archive.org/detail
s/oxforddictionary0000unse) . OUP.
ISBN 0-19-850994-4.

4. "Drawing Conclusions From Data:


Descriptive Statistics, Inferential Statistics,
and Hypothesis Testing" (https://dx.doi.org/
10.4135/9781506304144.n6) , Interpreting
and Using Statistics in Psychological
Research, Thousand Oaks, CA: SAGE
Publications, Inc, pp. 145–183, 2017,
doi:10.4135/9781506304144.n6 (https://d
oi.org/10.4135%2F9781506304144.n6) ,
ISBN 978-1-5063-0416-8, retrieved
2021-06-01

5. Investopedia, Descriptive Statistics Terms


(http://www.investopedia.com/terms/d/des
criptive_statistics.asp#axzz2DxCoTnMM)

6. Trochim, William M. K. (2006). "Descriptive


statistics" (http://www.socialresearchmetho
ds.net/kb/statdesc.php) . Research
Methods Knowledge Base. Retrieved
14 March 2011.

7. Babbie, Earl R. (2009). The Practice of


Social Research (https://archive.org/detail
s/isbn_9780495598428) (12th ed.).
Wadsworth. pp. 436–440 (https://archive.o
rg/details/isbn_9780495598428/page/43
6) . ISBN 978-0-495-59841-1.

8. Nick, Todd G. (2007). "Descriptive


Statistics". Topics in Biostatistics. Methods
in Molecular Biology. Vol. 404. New York:
Springer. pp. 33–52. doi:10.1007/978-1-
59745-530-5_3 (https://doi.org/10.1007%2
F978-1-59745-530-5_3) . ISBN 978-1-
58829-531-6. PMID 18450044 (https://pub
med.ncbi.nlm.nih.gov/18450044) .

External links

Descriptive Statistics Lecture: University


of Pittsburgh Supercourse:
http://www.pitt.edu/~super1/lecture/lec
0421/index.htm

Portal: Mathematics

Retrieved from
"https://en.wikipedia.org/w/index.php?
title=Descriptive_statistics&oldid=1144142381"
This page was last edited on 12 March 2023, at
01:48 (UTC). •
Content is available under CC BY-SA 4.0 unless
otherwise noted.

You might also like