Download as PPS, PDF, TXT or read online from Scribd
Download as pps, pdf, or txt
You are on page 1/ 47
Quality
Management
Dr. S.M. Khan
Scientist, RDSO Talk Includes Organizing, presenting and summarizing data Measures of Central Tendency and dispersion Concept of distributions Concept of sampling distributions Hypothesis testing Acceptance sampling – Attribute Characteristics Single and double sampling plans and OC curves Correlation and Regression Analyses Statistical designs of experiments for product quality improvement Talk Contd….
Introduction to Quality Quality of Design vs Conformance Cost of Quality Investigational methods Quality Assurance Functions and their evaluation Process and product check-Inspections, Quality control and testing schemes Organization of Quality Control, Quality Audit, Quality Circles ISO 9000 Measures of Central Tendency Today’s Questions
How can we summarize a
distribution of scores efficiently using quantitative (as opposed to graphical) methods? Summary Measures
Summary Measures
Central Tendency Quartile Variation
Mean Mode Median Range Coefficient of Variation Variance
Standard Deviation Mean: The arithmetic mean of a sample (or simply the sample mean) of n observations is computed as: Sample Size n
x1 x2 ... xn i 1x i x x = an individual score n n n = the number of scores Sigma or = take the sum Mean: The population mean is defined by the formula:
N Population Size x i Sumof thevalues of allobservatio nsin populatio n i 1 N Total numberof observatio ns in populatio n
x = an individual score N = the number of scores Sigma or = take the sum (Contd..)
The Most Common Measure of Central
Tendency Can Be Affected by Extreme Values (Outliers) (Try -10, 3, 5, 7, 20)
1 Mean A fx N A= Assumed Mean x = an individual score f = frequency of the class N = the number of scores Sigma or = take the sum Mean
In the stress example, the sum of all the scores is 975. 975 / 157 = 6.2 Thus, the average score is 6.2, on a 0 to 10 scale. Other Means
Geometric Mean Harmonic Mean Trimmed Mean Winsorized Mean Walsh and Wilcoxon Statistic W Advantages
It is based on all observations
It is a measure that can be calculated and is unique Least affected by fluctuations of sampling It is useful for performing statistical procedures such as comparing the means from several data sets. Suitable for algebraic treatment Disadvantages It cannot be calculated for qualitative data It is affected by extreme values that are not representative of the rest of the data. Consider 7 observations: 4.2, 4.3, 4.7, 4.8, 5.0, 5.1, 9.0. Indeed, if in the above example we compute the mean of the first 6 numbers and exclude the 9.0 value, then the mean is 4.7. The one extreme value 9.0 distorts the value we get for the mean. It would be more representative to calculate the mean without including such an extreme value. Measures of Central Tendency
Central Tendency
Mean Median Mode
n
X i X i 1 n N
X i i 1 N Median The median m of a sample of n observations: Set all the terms in ascending or descending order of magnitude. The middle number that divides the data set into two equal halfs: one half of the items lie above this point, and the other half lie below it.
x k if n 2k 1 ( n is odd) m Median 1 x k x k 1 if n 2k ( n is even 2 Exercise: Find the median of the data set consisting of the observations 7, 4, 3, 5, 6, 8, 10.
Solution: First, we arrange the data set in ascending order 3 4 5 6 7 8 10. Since the number of observations is odd, n = 2 x 4 - 1, then median m = x4 = 6. We see that a half of the observations, namely, 3, 4, 5 lie below the value 6 and an another half of the observations, namely, 7, 8 and 10 lie above the value 6. Example: Suppose we have an even number of the observations 7, 4, 3, 5, 6, 8, 10, 1. Find the median of this data set.
Solution: First, we arrange the data set in ascending order 1 3 4 5 6 7 8 10. Since the number of the observations n = 2 x 4, then by Definition Median = (x4+x5)/2 = (5+6)/2 = 5.5 Median The Midpoint or the 50th percentile of a distribution.
Odd Number of Measurements
x=[1234567] Median = 4 Even Number of Measurements x=[12345678] Median = (4+5)/2= 4.5 2. Median: the value at which 1/2 of the ordered scores fall above and 1/2 of the scores fall below
12345 1234
Median = 3 Median = 2.5
Median: For Grouped Data N F Median l 2 h f Where N = Total Cases l = lower limit of the median class f = frequency of the median class h = size of the class interval F = Cumulative frequency before the median class Advantages
It is easy to understand and readily
calculated It gives best results in qualitative measurements It eliminates the effects of extreme values In most of the cases it can be found tentatively Disadvantages
It requires considerable work
It cannot give correct total when multiplied by the number of items Not suitable for algebraic treatment Advantage of the median over the mean: Extreme values in data set do not affect the median as strongly as they do the mean. Indeed, in a series 4.2, 4.3, 4.7, 4.8, 5.0, 5.1, 9.0. Mean = 5.3, Median = 4.8. The extreme value of 9.0 does not affect the median. Mode
The mode of a data set is the
value that occurs with the greatest frequency, i.e., is repeated most often in the data set. Example: Find the mode of the data set in the following Table.
Quantity of glucose (mg%) in blood of 25 students:
70 88 95 101 106
79 93 96 101 107
83 93 97 103 108
86 93 97 103 112
87 95 98 106 115 Solution: First we arrange this data set in the ascending order
70 88 95 101 106 This data set contains 25 numbers. 79 93 96 101 107 We see that, the value of 93 is 83 93 97 103 108 repeated most often. Therefore, the mode 86 93 97 103 112
of the data set is 93.
87 95 98 106 115 Mode: most frequently occurring score
Mode = 7 Mode
Most frequently occurring score or group
of scores in a set. Mode: For Grouped Data f f 1 Mode l1 h 2 f f 1 f 1 Where: f = Maximum frequency l1 = lower limit of the corresponding model class f-1 = Preceeding frequency f1 = Succeeding frequency h = Class Interval Advantage:
Easily located, merely by inspection
Based on all values Like the median, the mode is not unduly affected by extreme values. Even if the high values are very high and the low value is very low, we choose the most frequent value of the data set to be the mode value. We can use the mode no matter how large, how small, or how spread out the values in the data set happen to be. Disadvantages: The mode is not used as often to measure central tendency as are the mean and the median. Too often, there is no modal value because the data set contains no values that occur more than once. Other times, every value is the mode because every value occurs the same number of times. Clearly, the mode is a useless measure in these cases. When data sets contain two, three, or many modes, they are difficult to interpret and compare. When the distribution of scores is normal, the Mean mode = median = mean Median Mode Mode = 2 Median = 2.5 Mean = 2.7
When scores are When scores are
positively skewed, negatively skewed, mean is dragged in mean is dragged in direction of skew and direction of skew and mode < median < mean mode > median > mean Empirical Relationship
Mean – Median = 1/3 (Mean – Mode) or
Mode = 3 Median – 2 Mean
Which is best? MCT Advantages Disadvantages
Mean Takes all Can be affected by
numbers into outliers (very small or account. large numbers). Median Fairly easy to Tedious to find for a calculate. Half of large set of numbers the scores lie or for a set that is not above the in order. median. Mode Quick and easy to May not be calculate. representative of the whole sample Quartiles Split Ordered Data into 4 Quarters
Data in Ordered Array: 11 12 13 16 16 17 18 21 22
25% 25% 25% 25%
Q1 Q2 Q3
i n 1 Qi 4 EX. Evaluate the values of mean, mode and median for the following grouped data: No. of days absent No. of students 5 29 10 124 15 349 20 442 25 478 30 487 35 493 40 497 45 500 Contd.. No. of Mid Value X f Cum f a=22.5 fx days d=x-a
1 Mean A fx N Mean = 13.523 Median: For Grouped Data N F Median l 2 h Where f N = Total Number l = lower limit of the median class f = frequency of the median class h = size of the class interval F = Cumulative frequency before the median class Contd.. No. of Mid Value X f Cum f a=22.5 fx days d=x-a
Where, N = 500 l = 10 f = 225 h=5 F = 124 Median = 12.8 Mode: For Grouped Data
f f 1 Mode l1 h 2 f f 1 f1 Where: f = Maximum frequency l1 = lower limit of the corresponding model class f-1 = Preceding frequency f-2 = Succeeding frequency h = Class Interval Contd.. No. of Mid Value X f Cum f a=22.5 fx days d=x-a
