Business Decision Making

Slides:



Advertisements
Similar presentations
Statistical Reasoning for everyday life
Advertisements

Unit 16: Statistics Sections 16AB Central Tendency/Measures of Spread.
SUMMARIZING DATA: Measures of variation Measure of Dispersion (variation) is the measure of extent of deviation of individual value from the central value.
Descriptive Statistics
Measures of Dispersion or Measures of Variability
Calculating & Reporting Healthcare Statistics
B a c kn e x t h o m e Parameters and Statistics statistic A statistic is a descriptive measure computed from a sample of data. parameter A parameter is.
Analysis of Research Data
Intro to Descriptive Statistics
Central Tendency and Variability Chapter 4. Central Tendency >Mean: arithmetic average Add up all scores, divide by number of scores >Median: middle score.
Measures of Central Tendency
Descriptive Statistics Used to describe the basic features of the data in any quantitative study. Both graphical displays and descriptive summary statistics.
May 06th, Chapter - 7 INFORMATION PRESENTATION 7.1 Statistical analysis 7.2 Presentation of data 7.3 Averages 7.4 Index numbers 7.5 Dispersion from.
Chapter 3 – Descriptive Statistics
© Copyright McGraw-Hill CHAPTER 3 Data Description.
Statistics Recording the results from our studies.
Measures of Variability OBJECTIVES To understand the different measures of variability To determine the range, variance, quartile deviation, mean deviation.
Measures of Central Tendency and Dispersion Preferred measures of central location & dispersion DispersionCentral locationType of Distribution SDMeanNormal.
1 PUAF 610 TA Session 2. 2 Today Class Review- summary statistics STATA Introduction Reminder: HW this week.
Descriptive Statistics
TYPES OF STATISTICAL METHODS USED IN PSYCHOLOGY Statistics.
UTOPPS—Fall 2004 Teaching Statistics in Psychology.
INVESTIGATION 1.
1 Descriptive statistics: Measures of dispersion Mary Christopoulou Practical Psychology 1 Lecture 3.
Numerical Measures of Variability
Measures of Spread Chapter 3.3 – Tools for Analyzing Data Mathematics of Data Management (Nelson) MDM 4U.
Chapter 5: Measures of Dispersion. Dispersion or variation in statistics is the degree to which the responses or values obtained from the respondents.
1.  In the words of Bowley “Dispersion is the measure of the variation of the items” According to Conar “Dispersion is a measure of the extent to which.
Variability Introduction to Statistics Chapter 4 Jan 22, 2009 Class #4.
1 STAT 500 – Statistics for Managers STAT 500 Statistics for Managers.
Descriptive Statistics(Summary and Variability measures)
CCGPS Coordinate Algebra Unit 4: Describing Data.
Educational Research Descriptive Statistics Chapter th edition Chapter th edition Gay and Airasian.
Introduction Dispersion 1 Central Tendency alone does not explain the observations fully as it does reveal the degree of spread or variability of individual.
Virtual University of Pakistan Lecture No. 11 Statistics and Probability by Miss Saleha Naghmi Habibullah.
The pictures of Statistics.  Central Tendencies -  Mean –  Median –  Mode -  Statistics -
Descriptive statistics
Descriptive Statistics ( )
Measures of Dispersion
Different Types of Data
SPSS CODING/GRAPHS & CHARTS CENTRAL TENDENCY & DISPERSION
Descriptive Statistics
Descriptive Statistics
Measures of dispersion
Measures of Dispersion
Describing Distributions Numerically
Mathematical Presentation of Data Measures of Dispersion
Measures of Position & Exploratory Data Analysis
Teaching Statistics in Psychology
Introductory Mathematics & Statistics
Univariate Statistics
CHAPTER 3 Data Description 9/17/2018 Kasturiarachi.
Numerical Measures: Centrality and Variability
Descriptive Statistics
Description of Data (Summary and Variability measures)
Measures of Central Tendency and Dispersion
Analyzing One-Variable Data
Chapter 3 Describing Data Using Numerical Measures
Numerical Descriptive Measures
MEASURES OF CENTRAL TENDENCY
DAY 3 Sections 1.2 and 1.3.
Histograms: Earthquake Magnitudes
Numerical Descriptive Measures
Numerical Descriptive Statistics
“Teach A Level Maths” Statistics 1
Measures of Dispersion
“Teach A Level Maths” Statistics 1
MBA 510 Lecture 2 Spring 2013 Dr. Tonya Balan 4/20/2019.
Presentation transcript:

Business Decision Making Measures of Dispersion & Skewness LSBM 1

Learning Outcomes Evaluate various measures of dispersion. By the end of this session, students should be able to: Evaluate various measures of dispersion. Understand standard deviation, its significance & interpretation. Discuss Skewness of a distribution and calculate the coefficient of skewness. LSBM

Measures of Dispersion Obtaining the average value for representation of set of data, logical question evolves – To what extent does this single value represent the whole set? Measure of Dispersion signifies the degree to which the values (data) in the distribution are ‘spread out’ OR ‘squashed’ together – the degree of spread among those values. LSBM 3 3

Measures of Dispersion Range: It is the difference between the highest and lowest values in a distribution. Range = Highest Value – Lowest Value As it ignores all but the two extreme values of a distribution, what has happened in the middle is not accounted for by this measure. Just like mode, range is only useful when we want a quick idea of the variability in a set of data without having to go to the trouble of doing any calculations. (Morris 2000) LSBM 4 4

Measures of Dispersion Quartile: Overcoming the criticism of range about ignoring the middle values, Quartile is utilised, which looks at the range, but not among all 100% of the data, but only among the central 50% of the distribution. (Morris 2000) The spread between the values 25% of the way and 75% of the way through a distribution are examined; respectively called the first or lower, quartile Q1 and the third or upper, quartile Q3. What about the Middle one?? They are respectively 1/4 (one quarter) & 3/4 (three quarters) of the way through the distribution. LSBM 5 5

Measures of Dispersion Quartile Deviation: This measure reveals the spread of the both upper (Q3) and lower (Q1) with respect to the Median (M). As Q3 – Q1 gives us the Interquartile Range (Semi-interquartile range = [(Q3 – Q1)/2]) the differences (Q3 – M) & (M – Q1) would reveal their distances from the Median, thus informing us the idea of the general shape of the distribution. LSBM 6 6

Measures of Dispersion Standard Deviation (SD): It is a “measure that tells us how near, on the whole, the values in the data are to the mean.” (Morris 2000) An easy example of understanding calculation of SD: Consider a set of numbers 1, 2, 3, 5, 9. The mean of this set is 4. 1 2 3 5 9 - 3 - 2 4 25 40 LSBM 7 7

Measures of Dispersion Henceforth, the average squared deviation of each values if 40/5 = 8, which is called the ‘Variance’. However, for different sets of data units, this may not deliver much meaning. For instance, lengths, areas, percentages, etc! Therefore, we use the square-root of variance to get the SD; i.e. sq. root of 8 = 2.828. Symbolically, we use: where: Grouped Data: 8 LSBM 8

Measures of Dispersion- Standard Deviation Recall the height distribution of employees: 9 LSBM 9

Measures of Dispersion- Standard Deviation LSBM 10 10

Measures of Dispersion- Coefficient of Variance Coefficient of Variance is a statistical measure of the dispersion of data points in a data series around the mean. It is calculated as the ratio of standard Deviation to mean. It is useful when comparing the degree of variation from on data series to another, even if the means are quite different from each other. Look at the example: LSBM 11 11

Measures of Dispersion- Coefficient of Variance Government statistics on the basic weekly wages of workers in 2 counties of London show following figures: Can we conclude that county V has wider spread of basic weekly wages? Solution: Simple observation of ‘’ may suggest a positive answer. However, using coefficient of variance,  / shows following: Coefficient of variation of wages in county V = 55/120 = 45.8% Coefficient of variation of wages in county W = 50/90 = 55.6% Which shows, in fact, that it is country ‘W’ that has a higher variability in basic weekly wages. County V County W LSBM 12 12

Example for you to workout! Calculate the standard deviation for following set of distribution for a factory that produces ‘Q’s every day. Formula: Output product Q No. of days 350 – under 360 360 – 370 370 – 380 380 – 390 390 – 400 4 6 5 3 Ans: 13.02 13 LSBM 13

Skewness Skewness signifies asymmetry or unequal distribution! If items in a distribution are equally dispersed on each side of the mean, they are said to be ‘symmetrical’ distribution, as shown in the figure. LSBM 14 14

Skewness When distribution is not symmetrically dispersed on each side of the mean, then they are said to be skewed distribution or asymmetric. There can be 2 skew distribution as shown. (a) Positively Skewed & (b) Negatively Skewed Such distribution can have same mean & same standard deviation but differently skewed? 15 LSBM 15

Skewness Information that skewness delivers: - Positive skewness: Expect unusually high values in the distribution. - Negative skewness: Expect unusually low values in the distribution. Symmetrical Distribution has its Mean, Median & Mode all on the same point as shown on 13th Slide. (on the dotted line) For skewed distribution, they lie at different place with Mean on the tail side with median followed by mode at tallest point, for both positive & negative skewed. LSBM 16 16

Skewness For most skewed distributions (except those with long tails) following relationship holds: Mean – Mode = 3 (Mean – Median) More skewed the distribution, more spread out these measures of location; therefore the amount of spread can be utilised to calculate the skewness of distribution. LSBM 17 17

Coefficient of Skewness Usually, the skewness is calculated by; Pearson’s First Coefficient of Skewness = As mode not always very easy to ascertain, equivalent formula can be used: Pearson’s Second Coefficient of Skewness = Candidates should be careful while subtracting ‘mode’ or ‘median’ from ‘mean’ as (+) or (-) sign indicate Positive Or Negative skewness. 18 LSBM 18