Measures of Central Tendency: Averages or other measures of “location” that find a single number that reflects the middle of the distribution of scores—

Slides:



Advertisements
Similar presentations
Quantitative Methods in HPELS 440:210
Advertisements

Measures of Central Tendency.  Parentheses  Exponents  Multiplication or division  Addition or subtraction  *remember that signs form the skeleton.
DESCRIBING DATA: 2. Numerical summaries of data using measures of central tendency and dispersion.
Variability Measures of spread of scores range: highest - lowest standard deviation: average difference from mean variance: average squared difference.
PPA 415 – Research Methods in Public Administration Lecture 4 – Measures of Dispersion.
Biostatistics Unit 2 Descriptive Biostatistics 1.
Measures of Variability
Measures of Variability. Why are measures of variability important? Why not just stick with the mean?  Ratings of attractiveness (out of 10) – Mean =
Edpsy 511 Homework 1: Due 2/6.
As with averages, researchers need to transform data into a form conducive to interpretation, comparisons, and statistical analysis measures of dispersion.
Central Tendency and Variability
Chapter 4 SUMMARIZING SCORES WITH MEASURES OF VARIABILITY.
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
Lecture 4 Dustin Lueker.  The population distribution for a continuous variable is usually represented by a smooth curve ◦ Like a histogram that gets.
Describing Data: Numerical
BIOSTAT - 2 The final averages for the last 200 students who took this course are Are you worried?
Descriptive Statistics Anwar Ahmad. Central Tendency- Measure of location Measures descriptive of a typical or representative value in a group of observations.
 IWBAT summarize data, using measures of central tendency, such as the mean, median, mode, and midrange.
Chapter 3 Descriptive Measures
Measures of Central Tendency and Dispersion Preferred measures of central location & dispersion DispersionCentral locationType of Distribution SDMeanNormal.
8.3 Measures of Dispersion  In this section, you will study measures of variability of data. In addition to being able to find measures of central tendency.
1 Review Mean—arithmetic average, sum of all scores divided by the number of scores Median—balance point of the data, exact middle of the distribution,
Chapter 3 Central Tendency and Variability. Characterizing Distributions - Central Tendency Most people know these as “averages” scores near the center.
Statistics 11 The mean The arithmetic average: The “balance point” of the distribution: X=2 -3 X=6+1 X= An error or deviation is the distance from.
Worked examples and exercises are in the text STROUD PROGRAMME 27 STATISTICS (contd)
DATA ANALYSIS n Measures of Central Tendency F MEAN F MODE F MEDIAN.
Dr. Serhat Eren 1 CHAPTER 6 NUMERICAL DESCRIPTORS OF DATA.
 IWBAT summarize data, using measures of central tendency, such as the mean, median, mode, and midrange.
Basic Measurement and Statistics in Testing. Outline Central Tendency and Dispersion Standardized Scores Error and Standard Error of Measurement (Sm)
Chapter 5 Measures of Variability. 2 Measures of Variability Major Points The general problem The general problem Range and related statistics Range and.
Chapter 3 For Explaining Psychological Statistics, 4th ed. by B. Cohen 1 Chapter 3: Measures of Central Tendency and Variability Imagine that a researcher.
Measures of Variability. Why are measures of variability important? Why not just stick with the mean?  Ratings of attractiveness (out of 10) – Mean =
Practice Page 65 –2.1 Positive Skew Note Slides online.
Measures of Dispersion. Introduction Measures of central tendency are incomplete and need to be paired with measures of dispersion Measures of dispersion.
Chapter 3: Averages and Variation Section 2: Measures of Dispersion.
Central Tendency & Dispersion
Sociology 5811: Lecture 3: Measures of Central Tendency and Dispersion Copyright © 2005 by Evan Schofer Do not copy or distribute without permission.
MEASURES OF VARIATION OR DISPERSION THE SPREAD OF A DATA SET.
Part II Sigma Freud and Descriptive Statistics Chapter 3 Vive La Différence: Understanding Variability.
Lecture 4 Dustin Lueker.  The population distribution for a continuous variable is usually represented by a smooth curve ◦ Like a histogram that gets.
6/13/2006Practical Research for Learning Communities Data Collection & Descriptive Statistics Kate Cerri Lynn Robinson Julie Thompson mmmmmm.
Chapter 5: Measures of Dispersion. Dispersion or variation in statistics is the degree to which the responses or values obtained from the respondents.
Comparing the Mode, Median, and Mean Three factors in choosing a measure of central tendency 1.Level of measurement –Nominal –Ordinal –Interval/Ratio 2.Shape.
Introduction to statistics I Sophia King Rm. P24 HWB
Chapter 3.4 Measures of Central Tendency Measures of Central Tendency.
Variability Introduction to Statistics Chapter 4 Jan 22, 2009 Class #4.
CHAPTER 2: Basic Summary Statistics
Averages and Variability
Bio-Statistic KUEU 3146 & KBEB 3153 Bio-Statistic Data grouping and presentations Part II: Summarizing Data.
Measures of Variation. Range, Variance, & Standard Deviation.
Chapter 2 The Mean, Variance, Standard Deviation, and Z Scores.
Data Descriptions.
Measures of Central Tendency.  Number that best represents a group of scores  Mean  Median  Mode  Each gives different information about a group.
Measures of Central Tendency
Practice Page Practice Page Positive Skew.
Central Tendency and Variability
Descriptive Statistics: Presenting and Describing Data
Numerical Measures: Centrality and Variability
Summary descriptive statistics: means and standard deviations:
MEASURES OF CENTRAL TENDENCY
Theme 4 Describing Variables Numerically
Chapter 3.
Chapter 3 Variability Variability – how scores differ from one another. Which set of scores has greater variability? Set 1: 8,9,5,2,1,3,1,9 Set 2: 3,4,3,5,4,6,2,3.
Summary descriptive statistics: means and standard deviations:
Numerical Descriptive Measures
CHAPTER 2: Basic Summary Statistics
Lecture 4 Psyc 300A.
The Mean Variance Standard Deviation and Z-Scores
Presentation transcript:

Measures of Central Tendency: Averages or other measures of “location” that find a single number that reflects the middle of the distribution of scores— ”the average score”

You know it better as the “average” Total/n = mean = 48/6 = 8 cups per person How many cups of coffee (x) Joe12 James10 Jane10 Chris8 Fred5 Christina3 TOTAL (n=6 students surveyed)48

Summation Symbol: Σ Σx: sum of x Σx/n = mean = 48/6 = 8 cups per person How many cups of coffee (x) Joe12 James10 Jane10 Chris8 Fred5 Christina3 TOTAL (n=6 students surveyed)48

Σx/n = x-bar (a.k.a ) = mean Σx/n = mean = 48/6 = 8 cups per person How many cups of coffee (x) Joe12 James10 Jane10 Chris6 Fred5 Christina5 TOTAL (n=6 students surveyed)48

The ungrouped frequency distribution for our raw collected data: BEWARE!! Averaging number of cups is not as simple with frequency distributions… How many cups of coffee (x)f = n =6

The ungrouped frequency distribution for our raw collected data: For ungrouped frequency distributions, Σfx/n = Σfx/Σf = 48/6 = 8 How many cups of coffee (x)f =fx = = n = Σf48 = Σfx

Checking your work: Σ(x – xbar) = 0 How many cups of coffee (x) xbarx-xbar Joe1284 James1082 Jane1082 Chris68-2 Fred58-3 Christina58-3 TOTAL (n=6 students surveyed) 48

A value in which there are as many scores greater than the median as there are scores less than the median First, order the raw scores from highest to lowest Second, find the median position (or median subject) by using this formula: median position = (n + 1)/2 Third, find the median score associated with that position What is the median value of these raw scores: 12, 12, 10, 10, 6, 5, 5

median position = (n + 1)/2 = (7 + 1)/2 = 4  If done properly, should be able to count from bottom or top and get same value How many cups of coffee (x) Joe12 Jessica12 James10 Jane10 Chris6 Fred5 Christina5

median position = (n + 1)/2 = (7 + 1)/2 = 4 th person (or i=4)  Median value = value of x at median position Person Interviewed or Studied (i) How many cups of coffee (x)

Using our original example, we have 6 people studied, which leads to an added complication in our median calculation median position = (n + 1)/2 = (6 + 1)/2 = 3.5 th person (or i=3.5) In this case, you take the value at 3 rd position and the value at the 4 th position and take the midpoint between: i=3 gives you 10 and i=4 gives you 8, midpoint would be 9 Person Interviewed or Studied (i) How many cups of coffee (x)

The mean is influenced by extreme values while the median is not The median is still 9 in this example, but the mean would be more than two trillion! Person Interviewed or Studied (i) How many cups of coffee (x) 112,000,000,000,

The grouped frequency distribution for our raw collected data:  Remember to find the median position: = (n + 1)/2 We know that for grouped frequency distributions, n = Σf Therefore, (n + 1)/2 = (Σf + 1)/2 = (9 + 1)/2 = 5 How many cups of coffee (x)f = = n = Σf

Mean of frequency data: Σfx/n = Σfx/Σf = 62/17 = 3.65 Possible # of cups of coffee (x) # of people who had that many cups (f) # of cups (fx)Cumulative frequency (cf) Σf = 17Σfx = 62

Median position of frequency data: (n+1)/2 = (Σf + 1)/2 = 18/2 = 9. The subject with median of 9 enters when x=4. Median = 4 Possible # of cups of coffee (x) # of people who had that many cups (f) # of cups (fx)Cumulative frequency (cf) n = Σf = 17Σfx = 62 

The mode: a category of a variable that contains more cases than either of the adjacent categories The mode is not influenced by extreme values (just like the median), but modal categories may disappear as sample size increases. Possible # of cups of coffee (x) # of people who had that many cups (f)  

Measures of Central Tendency: Averages or other measures of “location” that find a single number that reflects the middle of the distribution of scores— ”the average score”—mean, median, mode Measures of Dispersion: measures concerning the degree that the scores under study are dispersed or spread around the mean—”variability” Range, mean deviation, variance, standard deviation

As we’ve discussed with the means and medians, there are two different approaches to calculating the dispersion (i.e., variability around a mean) for raw scores and frequency data!

The range compares highest score and the lowest score for a given set of scores. It is the simplest of all dispersion measures. Example: We calculated an average of 8 cups of coffee per student with our survey of 48 students. The reported number of cups ranged from 0 to 12. Not terribly useful because the measure is HEAVILY influenced by extreme values without regard to all other numbers.

Just as the range only measures the extreme ends and ignores all other values in the data, the mean deviation is actually sensitive to all values in the dataset. Essentially, it measures 1) how different each value in a dataset deviates from the mean, 2) sums up all these differences across all observed values to get the total amount of deviation, 3) and dividing this sum of deviations by the total number of scores in dataset to get an average deviation. The mean deviation: an average distance that a score deviates from mean

Σx/n = x-bar ( ) = mean Σx/n = mean = 48/6 = 8 cups per person How many cups of coffee (x) x - Joe1284 James1082 Jane1082 Chris68-2 Fred58-3 Christina58-3 TOTAL (n=6 students surveyed) 48

MD=( )/6 = 16/6 = 2.67 MD= Σ |x- | n How many cups of coffee (x) x - Joe1284 James1082 Jane1082 Chris68-2 Fred58-3 Christina58-3 TOTAL (n=6 students surveyed) 48

The variance (s 2 ) is an “average” or mean value of the squared deviations of the scores from the mean Computationally, the equation is very similar to the mean deviation except instead of absolute values the variance considers the true values and squares them Variance= s 2 = Σ (x- ) 2 n The variance is usually much larger than the mean deviation because we are taking the squares of the deviations MD= Σ |x- | n

Variance= s 2 = Σ (x- ) 2 = 46/6 = 7.67 n How many cups of coffee (x) x -(x- ) 2 Joe James10824 Jane10824 Chris68-24 Fred58-39 Christina58-39 TOTAL (n=6 students surveyed) 4846

Since the variance (s 2 ) is usually larger than the mean deviation because we take the squares of the deviations in the calculations, another method for calculating the variability around a mean is used to “standardize” the variance—the standard deviation (s) Essentially, the standard deviation is the same as the variance except we take the square root of the variance estimate to calculate it: Standard Deviation= s = This estimate aims to provide a measure of dispersion closer in size to the mean deviation than the variance MD= Σ |x- | n

Standard deviation= s = square root of (Σ (x- ) 2 n 7.67 = s 2 s = square root of 7.67 = 2.77 How many cups of coffee (x) x -(x- ) 2 Joe James10824 Jane10824 Chris68-24 Fred58-39 Christina58-39 TOTAL (n=6 students surveyed) 4846

Remember for raw scores, we calculated the variance as: (raw scores) Variance= For frequency data, the equation is adjusted so that we multiply each squared deviation by the frequency of that particular value of x: (frequency data) Variance = The standard deviation is simply the square root of that variance MD= Σ |x- | n

How many cups of coffee (x) f =fx = x- (x- ) 2 (x- ) 2 X f = n = Σf 48 = Σfx 46 (frequency data) Variance = = s 2 = 46/6 = 7.67 (frequency data) St. Dev = s= square root of 7.67 = 2.77