Displaying data – shape of distributions. Week 3 (1) презентация

Histogram of employee completion times Numerical data DR

Слайд 1BBA182 Applied Statistics Week 3 (1) Displaying data – shape of distributions


DR SUSANNE HANSEN SARAL
EMAIL: SUSANNE.SARAL@OKAN.EDU.TR
HTTPS://PIAZZA.COM/CLASS/IXRJ5MMOX1U2T8?CID=4#
WWW.KHANACADEMY.ORG

DR SUSANNE HANSEN SARAL


Слайд 2 Histogram of employee completion times

Numerical data

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM



Слайд 3 Numerical data

Employee completion time Cumulative frequency

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 4 Bar Chart – categorical data
DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Hospital Number
Unit of Patients

Cardiac Care 1,052
Emergency 2,245
Intensive Care 340
Maternity 552
Surgery 4,630



Слайд 5 Describing distributions

Once we have made a

picture of our numerical data, the histogram, what can we say about it’s shape?

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 6 Describing distributions – what to pay attention to!

Pay attention to:

its’

shape
its’ center
Its’ spread


DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 7 Describing the shape of distributions

We describe the shape of a distribution

in terms of:

Modes
Symmetry
Gaps or outlying values


DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 8

Mode


Does the distribution have one peak (mode) or several peaks (several modes)?

Uni-modal: one mode
Bi-modal: Two modes
Multi-modal: More than two modes

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 9

Symmetry


If we can make a mirror image of the distribution, we have a symmetric distribution

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 10 Skewed distribution
The thinner parts of a distribution are called tails.
A

distribution is skewed, or asymmetric, if one tail stretches farther out on one side than on the other side of the center.

A right skewed distribution has a tail that extends farther to the right.
A left skewed distribution has a tail that extends farther to the left.

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 11 Right skewed distributions Examples

Employee salaries in a company
Waiting times

in a line

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 12 Left skewed distributions Example

Time to finish an exam
Employees going

home after work
Customers going shopping in a shopping center on a Saturday


DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 13

Outliers


Outliers are extreme data points in a data set that are not close to the majority of the other data points

Example:
Age of 10 people in a restaurant:

24 19 21 65 20 21 23 20 24 25



DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 14

Outliers


If you are studying the personal wealth of Americans in 2010 and you have Bill Gates (Founder of Microsoft) in your sample.

How would the personal wealth of Bill Gates affect the distribution of personal wealth of Americans in the sample?




DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 15

Outliers

Outliers will affect the shape of a distribution:


DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 16

Outliers


Outliers can affect almost every statistical method we use in Statistics.

Therefore we need to look out for them.

An outlier can be the most informative part in your data or it may just be an error.
No matter what it is, you need to look at it critically and judge if it is important for our analysis.


DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 17 Graphs to Describe Time-Series Data

A histogram can provide information

about the distribution of a variable, but it cannot show any pattern of the data over time.

Sometimes we need to analyze data over time.

A graph of values against time is called a times series plot

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 18 Graphs to Describe Time-Series Data

A time-series plot is used

to show the values of a variable ordered over time.

Time is measured on the horizontal axis
The variable of interest is measured on the vertical axis

Used to monitor the evolution of a certain item of interest, such as evolution of the price of gas, annual interest rates, daily closing prices for shares of common stock, evolution of home prices in a certain region, exchange rates (Euro-TL, TL-$), etc.

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 19 Line Chart (time series plot) One variable
DR SUSANNE HANSEN SARAL,

SUSANNE.SARAL@GMAIL.COM

Слайд 20 Line Chart (time series plot)

Two variables

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 21 Line Chart (time series plot)

Two variables

DR SUSANNE HANSEN SARAL, SUSANNE.SARAL@GMAIL.COM


Слайд 22 Presenting statistical charts and graphs

When presenting data for an audience or

a manager your charts and graphs MUST give as clear and accurate picture of the data as possible.

The graphs and charts must be:
Convincing
Clear
Truthful

DR SUSANNE HANSEN SARAL


Слайд 23 Manipulation of data


Data can be manipulated in graphical techniques in such

a way that they look more/less favorable than they are in reality. This gives misleading information about the data.

You need to be critical whenever you are presented a graph, pie-chart, histogram, etc.

You should also be careful not to construct misleading information with graphical techniques.


2/15/2017



Слайд 24 Manipulation of data
DR

SUSANNE HANSEN SARAL

Слайд 25 Identical data - different graph How is

this possible?

DR SUSANNE HANSEN SARAL


Слайд 26

Manipulation of data

DR SUSANNE HANSEN SARAL


Слайд 27 Manipulation of data
DR SUSANNE HANSEN SARAL


Слайд 28 Manipulation of data

What does this graph say about the data?

DR SUSANNE HANSEN SARAL


Слайд 29 Manipulation of

data

DR SUSANNE HANSEN SARAL


Слайд 30Histogram with equal interval width


Слайд 31 Data

Presentation Errors

Do not make a histogram of categorical data
Unequal histogram interval widths
Label the x-axis and y-axis clearly (identify
variables clearly)
Compressing or distorting the vertical axis
Do not calculate numerical summaries of categorical data, such as code, telephone numbers, etc.

DR SUSANNE HANSEN SARAL


(continued)


Слайд 32 Contingency table

Class exercise

A survey of the entering MBA students at a university in the US reported the following data on the gender of their students in their two MBA programs:
What are the two variables under study?


Слайд 33 Contingency table

How many students are surveyed?

A) How many of all MBA students are women?
B) How many of Two-year MBAs are women?
C) How many of Evening MBAs are men?
D) How many of all MBAs are men?


Слайд 34 Contingency table

How many students are surveyed?

 


Слайд 35 Contingency table in percent
A) What percent of all MBA students are

women?
B) What percent of Two-year MBAs are women?
C) What percent of Evening MBAs are men?
D) What percent of all MBAs are men?

 


Слайд 36 Contingency table
A) What percent of all MBA students

are women?
B) What percent of Two-year MBAs are women?
C) What percent of Evening MBAs are men?
D) What percent of all MBAs are men?

Слайд 37 Displaying categorical data -exercise
Softdrink

market share
A local survey company conducted a survey on the consumption of soft drinks its region of operations. The results of the survey were summarized in the following pie-chart:

A) Which soft-drink brand has the highest consumption?
B) Is this a good method to display this data?

Слайд 38 Displaying categorical data -exercise
Softdrink

market share ( same data as in the preceding slide)
A local survey company conducted a survey on the consumption of soft drinks its region of operations. The results of the survey were summarized in the following pie-chart:

A) Compared to the pie chart in the preceding slide, which
chart is better for displaying the relative proportion (per-
cent) of market share
B) Which chart gives the best visual picture of the data?

Слайд 39In this situation-beverage marketshare Which of the two graphs gives the best

picture of the data?

Слайд 40 Are there any

outliers in the following data sets?


If yes, explain:

A) 15 21 20 54 18 17 22 22

B) 345 340 339 344 338 341 343

C) – 21 -23 -25 -18 -20 -63 -19 -22


Слайд 41 How would the

outliers affect the mean of the data set?


Would the outlier increase or decrease the mean of the respective datasets?

A) 15 21 20 54 18 17 22 22

B) 345 340 339 344 338 341 343

C) – 21 -23 -25 -18 -20 -63 -19 -22


Обратная связь

Если не удалось найти и скачать презентацию, Вы можете заказать его на нашем сайте. Мы постараемся найти нужный Вам материал и отправим по электронной почте. Не стесняйтесь обращаться к нам, если у вас возникли вопросы или пожелания:

Email: Нажмите что бы посмотреть 

Что такое ThePresentation.ru?

Это сайт презентаций, докладов, проектов, шаблонов в формате PowerPoint. Мы помогаем школьникам, студентам, учителям, преподавателям хранить и обмениваться учебными материалами с другими пользователями.


Для правообладателей

Яндекс.Метрика