WELCOME TO STT 231 • INSTRUCTOR: DR. Elijah E. DIKONG • VISITING PROFESSOR • CLASS WEBSITE: – http://www.stt.msu.edu 1 EXTRA CREDIT NUMBER 1 RECOMMENDED READING COURSEPACK PAGES 2 – 9 EXERCISES 2.9 Page 9 QUESTIONS 1, 3, 4, and 5 Due: Wednesday May 27, 2015 2 What Is Statistics? Statistics: Two Different Meanings: (a) IN PLURAL SENSE, STATISTICS MEANS A SET OF OBSERVATIONS, USUALLY COLLECTED BY MEASUREMENTS OR COUNTING, COLLECTIVELY KNOWN AS DATA. (b) IN SINGULAR SENSE, STATISITICS REFERS TO A GROUP OF SCIENTIFIC METHODS USED TO * collecting data * interpreting and analyzing data * making conclusions or inferences. 3 IN SUMMARY • STATISTICS IS THE ART AND SCIENCE OF DESIGNING STUDIES AND ANALYZING THE DATA THAT THOSE STUDIES PRODUCE. ITS ULTIMATE GOAL IS TRANSLATING DATA INTO KNOWLEDGE AND UNDERSTANDING OF THE WORLD AROUND US. IN SHORT, STATISTICS IS THE ART AND SCIENCE OF LEARNING FROM DATA. 4 THREE MAIN ASPECTS OF STATISTICS • DESIGN: PLANNING HOW TO OBTAIN DATA TO ANSWER THE QUESTIONS OF INTEREST (DATA COLLECTION) • DESCRIPTION: EXPLORING AND SUMMARIZING PATTERNS IN THE DATA (DATA ANALYSES) • INFERENCE: MAKING DECISIONS AND PREDICTIONS BASED ON THE DATA. TO INFER MEANS TO ARRIVE AT A DECISION OR PREDICTION BY REASONING FROM KNOWN EVIDENCE 5 TYPES OF STATISTICS DESCRIPTIVE STATISTICS INFERENTIAL STATISTICS STATISTICAL PROCEDURES 1.UNDERSTANDING 3.PLANNING 5.CHECKING 4.EXECUTING 2.ANALYZING 6.REPORTING 6 DESCRIPTIVE STATISTICS • DEFINED AS THOSE METHODS INVOLVING THE COLLECTION, PRESENTATION, AND CHARACTERIZATION OF A SET OF DATA IN ORDER TO DESCRIBE PROPERLY THE VARIOUS FEATURES OF THAT SET OF DATA. TO ACHIEVE THESE, STATISTICIANS USE TABLES – EITHER FREQUENCY OR CONTIGENCY; BAR AND PIE CHARTS; STEM-AND-LEAF DISPLAYS; BOX-AND-WHISKER PLOTS; PARETO DIAGRAMS; HISTOGRAMS. • ALSO DEFINED AS THAT BRANCH OF STATISTICS THAT INVOLVES IN THE ORGANIZING, DISPLAYING, AND DESCRIBING OF DATA. • INFERENTIAL STATISTICS IS THE BRANCH OF STATISTICS THAT INVOLVES DRAWING CONCLUSIONS ABOUT A POPULATION BASED ON INFORMATION CONTAINED IN A SAMPLE FROM THAT POPULATION 7 SOME RELEVANT STATISTICAL TERMINOLOGIES 8 POPULATION VERSUS SAMPLE • A POPULATION IS THE TOTAL GROUP OF INDIVIDUALS ABOUT WHOM YOU WANT TO MAKE CONCLUSIONS. • A POPULATION IS THE TOTAL OBJECTS THAT ARE OF INTEREST IN A STATISTICAL STUDY. • EXAMPLE: ALL CURRENTLY REGISTERED STUDENTS AT A PARTICULAR COLLEGE FORM A POPULATION. 9 POPULATION VERSUS SAMPLE • A SAMPLE IS A REPRESENTATIVE SUBSET OF A POPULATION, EXAMINED IN HOPE OF LEARNING ABOUT THE POPULATION. • ILLUSTRATION: POT OF CHICKEN SOUP 10 EXAMPLE: IDENTIFY THE POPULATION AND THE SAMPLE • A QUESTION POSTED ON THE LYCOS WEBSITE IN THE USA ON 18 JUNE 2000 ASKED VISITORS TO THE SITE TO SAY WHETHER THEY THOUGHT MARIJUANA SHOULD BE LEGALLY AVAILABLE FOR MEDICINAL PURPOSES. • THE GALLUP POLL INTERVIEWED 1007 RANDOMLY SELECTED U.S. ADULTS AGED 18 AND OLDER, MARCH 23 – 25, 2007. GALLUP REPORTS THAT WHEN ASKED IF EVER, THE EFFECTS OF GLOBAL WARMING WILL BEGIN TO HAPPEN, 60% OF THE RESPONDENTS SAID THE EFFECTS HAD ALREADY BEGUN. ONLY 11% THOUGHT THAT THEY WOULD NEVER HAPPEN. 11 PARAMETER VERSUS STATISTIC • PARAMETER (POPULATION PARAMETER): A PARAMETER IS A NUMERICAL SUMMARY OF THE POPULATION. • STATISTIC (SAMPLE STATISTIC) – A STATISTIC IS A NUMERICAL SUMMARY OF A SAMPLE TAKEN FROM THE POPULATION. 12 EXAMPLE • ONE YEAR THE GENERAL SOCIAL SURVEY (GSS) ASKED, “ABOUT HOW MANY GOOD FRIENDS DO YOU HAVE?” OF THE 819 PEOPLE WHO RESPONDED, 6% REPORTED HAVING ONLY 1 GOOD FRIEND. IDENTIFY • (A) THE SAMPLE, • (B) THE POPULATION, AND • (C) THE STATISTIC REPORTED (POPULATION PARAMETER OR SAMPLE STATISTICS) 13 DATA: SYSTEMATICALLY RECORDED INFORMATION, WHETHER NUMBERS OR LABELS, TOGETHER WITH ITS CONTEXT CONTEXT TELLS WHO, WHAT, WHEN, WHERE, HOW and WHY IS BEING MEASURED. CONTEXT WHERE PLACE E.G. CITY WHAT WH0 CHARACTERISTICS RECORDED ABOUT EACH INDIVIDUAL (VARIABLES) INDIVIDUALS ABOUT WHOM DATA ARE COLLECTED(PARTICIPANTS, RESPONDENTS, SUBJECTS, EXPERIMENTAL UNITS, RECORDS, CASES WHEN TIME[DAYS, YEARS, ETC.] WHY PURPOSE OF STUDY HOW METHOD OF COLLECTING DATA. E.G. SURVEY 14 EXAMPLE • BECAUSE OF THE DIFFICULTY OF WEIGHING A BEAR IN THE WOODS, RESEARCHERS CAUGHT AND MEASURED 54 BEARS, RECORDING THEIR WEIGHT, NECK SIZE, LENGTH, AND SEX. THEY HOPED TO FIND A WAY TO ESTIMATE THE WEIGHT FROM THE OTHER, MORE EASILY DETERMINED QUANTITIES. IDENTIFY THE W’S. 15 Raw Data • Raw data are for numbers and category labels that have been collected but have not yet been processed in any way. • Example list of questions and raw data for a student: 16 Raw Data • An observation is an individual entity in a study. • Sample data are collected from a subset of a larger population. • Population data are collected when all individuals in a population are measured. • A statistic is a summary measure of sample data. • A parameter is a summary measure of population data. 17 DATA TABLE – AN ARRANGEMENT OF DATA IN WHICH EACH ROW REPRESENTS A CASE[AN INDIVIDUAL ABOUT WHOM OR WHICH WE HAVE DATA] AND EACH COLUMN REPRESENTS A VARIABLE. NAME CATHY AGE (YR) 22 NEAREST STUDIUM CATALOG NUMBER TIME (DAYS) AREA CODE 130 312 ALI Y 7TY73 MASS INTERNET PURCHASE ARTIST SAM 24 18 305 LINCO N CKJ24 BOST CHRIS 43 368 610 VET Y JKN23 FLORI 5 413 SPAR Y 7O28Y APRIL LINDA 35 18 VARIABLES DEFINITION: THE CHARACTERISTICS RECORDED ABOUT EACH INDIVIDUAL (SUBJECT) ARE CALLED VARIABLES. TYPES OF VARIABLES CATEGORICAL OR (QUALITATIVE) QUANTITATIVE OR (NUMERICAL) 19 Types of Variables • Raw data from categorical variables consist of group or category names that don’t necessarily have a logical ordering. Examples: eye color, country of residence. • Categorical variables for which the categories have a logical ordering are called ordinal variables. Examples: highest educational degree earned, tee shirt size (S, M, L, XL). • Raw data from quantitative variables consist of numerical values taken on each individual. Examples: height, number of siblings. 20 TWO TYPES OF QUANTITATIVE VARIABLES • DISCRETE QUANTITATIVE VARIABLE: A VARIABLE IS DISCRETE IF IT TAKES ITS VALUE FROM A COUNTABLE SET OF NUMBERS LIKE {0, 1, 2, 3, 4, … } OR FROM A FINITE SET OF NUMBERS. • CONTINUOUS QUANTITATIVE VARIABLE: A VARIABLE IS CONTINUOUS IF IT TAKES ITS POSSIBLE VALUES FROM AN INTERVAL OR A CONTINUUM LIKE [2, 7], (- 5, 10), OR THE ENTIRE NUMBER LINE, R. 21 MORE EXAMPLES: WHAT TYPE OF VARIABLE? • THE NUMBER OF INCOMING PEOPLE IN THE BANK BETWEEN 12:00 NOON AND 1:00P.M. ON FRIDAY • YOU ROLL TWO DICE AND RECORD WHETHER OR NOT THE RESULTING VALUES ON THE TWO DICE MATCHED. • A WOMAN IS SELECTED AT RANDOM FROM A CITY. YOU RECORD WHETHER OR NOT THE SELECTED WOMAN HAS BREAST CANCER. • THE AMOUNT OF RAINFALL FOR A SEASON IN A CITY 22 QUANTITATIVE AND QUALITATIVE(CATEGORICAL) DATA • DATA COLLECTED FROM A QUANTITATIVE VARIABLE IS CALLED QUANTITATIVE DATA. • EXAMPLES INCLUDE HEIGHT, WEIGHT, OF STUDENTS. TIME TO COMPLETE DIFFERENT TASKS. • DATA COLLECTED FROM A CATEGORICAL VARIABLE IS CALLED CATEGORICAL DATA. 23 EXAMPLE IN JUNE 2003 CONSUMER REPORTS PUBLISHED AN ARTICLE ON SOME SPORT UTILITY VEHICLES THEY HAD TESTED RECENTLY. THEY REPORTED SOME BASIC INFORMATION ABOUT EACH OF THE VEHICLES AND THE RESULTS OF SOME TESTS CONDUCTED BY THEIR STAFF. AMONG OTHER THINGS, THE ARTICLE TOLD THE BRAND OF EACH VEHICLE, ITS PRICE, AND WHETHER IT HAD A STANDARD OR AUTOMATIC TRANSMISSION. THEY REPORTED THE VEHICLE’S FUEL ECONOMY, ITS ACCELERATION(NUMBER OF SECONDS TO GO FROM ZERO TO 60MPH), AND ITS BRAKING DISTANCE TO STOP FROM 60MPH. THE ARTICLE ALSO RATED EACH VEHICLE’S RELIABILITY BETTER THAN AVERAGE, AVERAGE, WORSE, OR MUCH WORSE THAN AVERAGE. IDENTIFY THE W’S. LIST THE VARIABLES. INDICATE WHETHER EACH VARIABLE IS CATEGORICAL OR QUANTITATIVE. IF THE VARIABLE IS QUANTITATIVE, TELL THE UNITS. 24 EXAMPLE IN JUNE 2000, A HOMEOWNER IN TUSCOLA, ILLINOIS, WANTED TO DETERMINE IF GENERIC FERTILIZER AND WEED KILLER IS AS EFFECTIVE AS THE MORE EXPENSIVE NAME BRAND PRODUCT. AFTER THE SPRING RAINS AND EARLY SUMMER WARMTH, HE COUNTED THE NUMBER OF WEEDS AND DENSITY OF GRASS BLADES. IDENTIFY WHO, WHERE, WHEN, AND WHY FOR THE SITUATION DESCRIBED. A. A HOMEOWNER; TUSCOLA, ILLINOIS, JUNE 2000, COMPARE PRODUCTS. B. TWO PATCHES OF LAWN; TUSCOLA, ILLINOIS; JUNE 2001; COMPARE PRODUCTS. C. TWO PATCHES OF LAWN; ARCOLA, ILLINOIS; JUNE 2000; COMPARE PRODUCTS. D. A HOMEOWNER; ARCOLA, ILLINOIS; JUNE 2000; COMPARE PRODUCTS. E. TWO PATCHES OF LAWN; TUSCOLA, ILLINOIS; 25 JUNE 2000; COMPARE PRODUCTS. EXAMPLE AN ADMINISTRATOR IN A SCHOOL DISTRICT WITH SEVERAL FIFTH GRADE CLASSROOMS OF ESSENTIALLY THE SAME SIZE COLLECT DATA ON THE VARIOUS CLASSES. AMONG THE VARIABLES WERE THE NUMBER OF SINGLE PARENT FAMILIES, AVERAGE FAMILY INCOME, STRUCTURE OF SCHOOL(K-5, 5-8, K-8), NUMBER ELIGIBLE FOR FREE/REDUCED LUNCH, MAJORITY BRING/BUY LUNCH(YES/NO), AVERAGE DISTANCE TO SCHOOL, AND NUMBER OF PARENTAL VISITS TO SCHOOL. SELECT THE STATEMENT THAT CLASSIFIES THE VARIABLES IN ORDER WITH Q REPRESENTING A QUANTITATIVE VARIABLE AND C REPRESENTING A CATEGORICAL VARIABLE. (A) (B) (C) (D) (E) C,Q,C,Q,C,Q,Q Q,C,Q,C,Q,C,C Q,Q,C,Q,C,Q,C, C,C,Q,C,Q,C,C. Q,Q,C,Q,C,Q,Q. 26 MEASURES OF CENTER OF QUANTITATIVE DATA • THE CENTER IS A VALUE THAT ATTEMPTS THE IMPOSSIBLE BY SUMMARIZING THE ENTIRE DISTRIBUTION OR DATA SET WITH A SINGLE NUMBER, A “TYPICAL” VALUE. MEASURES OF CENTER INCLUDE THE MEAN AND THE MEDIAN. 27 DEFINITION • MEAN: THE MEAN IS THE SUM OF THE OBSERVATIONS DIVIDED BY THE NUMBER OF OBSERVATIONS. • MEDIAN: THE MEDIAN IS THE MIDPOINT OF THE OBSERVATIONS WHEN THEY ARE ORDERED FROM THE SMALLEST TO THE LARGEST (OR FROM THE LARGEST TO SMALLEST). 28 Measures of Central Location The Mean x x i n where xi means “add together all the values” The Median If n is odd: M = middle of ordered values. Count (n + 1)/2 down from top of ordered list. If n is even: M = average of middle two ordered values. Average values that are (n/2) and (n/2) + 1 down from top of ordered list. 29 EXAMPLE • FIND THE MEAN AND MEDIAN OF THE SET OF OBSERVATIONS: 7, 1, 5, 3, 4. • FIND THE MEAN AND MEDIAN OF 4, 2, 8, 6. 30 Measures of Central Location Cont’d • THE MODE OR SAMPLE MODE: is the most frequent value in a data set. • EXAMPLE: Find the mode of the following data set: - 1, 0, 2, 0 • SOLUTION: The value 0 is most frequently observed and therefore the mode is 0 31 CHALLENGE QUESTION • PROFESSOR DIKONG GAVE HIS FIRST TEST TO HIS STT 200 STUDENTS. HIS COLLEAGUE IS INTERESTED HOW HIS STUDENTS PERFORMED IN THE TEST. • HOW SHOULD PROFESSOR DIKONG ANSWER IN ORDER TO GIVE HIS COLLEAGUE A BETTER IDEA OF HOW HIS STUDENTS PERFORMED IN THE TEST? 32 Key Takeaway • THE MEAN, THE MEDIAN, AND THE MODE EACH ANSWER THE QUESTION “WHERE IS THE CENTER OF THE DATA SET?” 33 OUTLIERS • OUTLIERS ARE UNUSUAL OR EXTREME VALUES THAT DO NOT APPEAR TO BELONG WITH THE REST OF THE DATA, THAT IS, AN OUTLIER IS A DATA POINT THAT IS NOT CONSISTENT WITH THE BULK OF THE DATA. • SUCH STRAGGLERS STAND OFF AWAY FROM THE BODY OF THE DISTRIBUTION OF DATA SET. • OUTLIERS CAN AFFECT MANY STATISTICAL ANALYSES, SO YOU SHOULD ALWAYS BE ALERT FOR THEM. 34 ILLUSTRATION • MSU SPARTANS VERSUS • UNIVERSITY OF MICHIGAN WOLVORINES 35 The Influence of Outliers on the Mean and Median Larger influence on mean than median. High outliers will increase the mean. Low outliers will decrease the mean. If ages at death are: 76, 78, 80, 82, and 84 then mean = median = 80 years. If ages at death are: 46, 78, 80, 82, and 84 then median = 80 but mean = 74 years. 36 MEASURES OF SPREAD OF QUANTITATIVE DATA • A MEASURE OF SPREAD IS A NUMERICAL SUMMARY OF HOW TIGHTLY THE VALUES ARE CLUSTERED AROUND THE CENTER. • MEASURES OF SPREAD ARE: – STANDARD DEVIATION – INTERQUARTILE RANGE (IQR) – RANGE 37 RANGE = (MAXIMUM OBSERVATION) – (MINIMUM OBSERVATION) • EXAMPLE: FIND THE RANGE OF THE DATA SET: 45, 46, 49, 35, 76, 80, 89, 94, 37, 61, 62, 64, 68, 56, 57, 57, 71, 72 • MAXIMUM OBSERVATION = 94 • MINIMUM OBSERVATION = 35 • RANGE = MAX – MIN = 94 – 35 = 59 38 VARIANCE AND STANDARD DEVIATION • THE RANGE USES ONLY THE LARGEST AND SMALLEST OBSERVATIONS. THE MOST POPULAR SUMMARY OF SPREAD USES ALL THE DATA. IT IS CALLED THE STANDARD DEVIATION. 39 Steps in Calculating Standard Deviation Step 1: Calculate x, the sample mean. Step 2: For each observation, calculate the difference between the data value and the mean. Step 3: Square each difference in step 2. Step 4: Sum the squared differences in step 3, and then divide this sum by n – 1. Step 5: Take the square root of the value in step 4. 40 COMPUTING THE MEASURES OF SPREAD – VARIANCE AND STANDARD DEVIATION n VAR( X ) x i i 1 x 2 n 1 SD ( X ) VAR( X ) n where x x i 1 i n 41 ILLUSTRATION • HERE ARE THE AGES FOR A SAMPLE OF N = 5 CHILDREN: 1, 3, 5, 7, 9. FIND THE STANDARD DEVIATION FOR THIS DATA SET WITHOUT USING A CALCULATOR. 42 FIND THE VARIANCE AND STANDARD DEVIATION OF THE BATCH OF VALUES 4, 3, 10, 12, 8, 9, AND 3. VALUES DEVIATIONS SQ. DEVIATIONS 4 4–7=-3 9 3 3–7=-4 16 10 10 – 7 = 3 9 12 12 – 7 = 5 25 8 8–7=1 1 9 9–7=2 4 3 3–7=-4 16 43 Example Cont’d SUM OF SQUARED DEVIATION n xi x 80 2 i 1 80 80 VAR( X ) 13.33 7 1 6 SD( X ) 13.33 3.65 44 EXAMPLE and Step 1 • Consider four pulse rates: 62, 68, 74, 76 62 68 74 76 280 x 70 4 4 45 Steps 2 and 3 46 Step 4 120 2 s 40 4 1 47 Step 5 s 40 6.3 48 Describing Spread With Standard Deviation Standard deviation measures variability by summarizing how far individual data values are from the mean. Think of the standard deviation as roughly the average distance values fall from the mean. 49 INTERQUARTILE RANGE (IQR) • WE SHALL CONSIDER THE FOLLOWING DATA SET TO ILLUSTRATE INTERQUARTILE RANGE (IQR) DATA: 45, 46, 49, 35, 76, 80, 89, 94, 37, 61, 62, 64, 68, 56, 57, 57, 59, 71, 72. SORTED DATA: 35, 37, 45, 46, 49, 56, 57, 57, 59, 61, 62, 64, 68, 71, 72, 76, 80, 89, 94. 50 NOTATION • INTERQUARTILE RANGE (IQR) = Q3 – Q1 Q3 = UPPER QUARTILE = MEDIAN OF UPPER HALF OF ORDERED DATA Q1 = LOWER QUARTILE = MEDIAN OF LOWER HALF OF ORDERED DATA NOTE: INCLUDE MEDIAN IN THE UPPER AND LOWER HALF OF THE DATA IF THE DATA SET HAS ODD NUMBER OF OBSERVATIONS OR DATA VALUES. 51 Quartiles EXAMPLE: (odd number of observations, 19) Median = 61 UPPER HALF 35 37 45 46 49 56 57 57 59 [61 62 64 68 71 72 76 80 89 94] Q3 = (71 +72) / 2 = 71.5 LOWER HALF [35 37 45 46 49 56 57 57 59 61] 62 64 68 71 72 76 80 89 94 Q1 = (49 + 56) / 2 = 52.5 IQR = 71.5 – 52.5 = 19 Note: Include the median in the calculation of both quartiles IF n = ODD 52 Quartiles EXAMPLE: (even number of observations, n = 18) 35 37 45 46 49 56 57 57 59 61 62 64 68 71 72 76 80 89 Median = (59+61)/2 = 60 DO NOT INCLUDE MEDIAN IN THE LOWER AND UPPER HALF OF THE DATA. UPPER HALF 35 37 45 46 49 56 57 57 59 [61 62 64 68 71 72 76 80 89 ] Q3 = 71 LOWER HALF [35 37 45 46 49 56 57 57 59 ] 62 64 68 71 72 76 80 89 94 Q1 = 49 IQR = 71 – 49 = 42 53 EXAMPLE • 1. Here are costs of 10 electric smooth-top ranges rated very good or excellent by Consumers Reports in August 2002. • 850 • 1000 • • • • 900 750 1400 1250 1200 1050 1050 565 Find the following statistics by hand: a) mean b) median and quartiles c) range and IQR 54 SOLUTION • Step 1: Sort Data: 565 750 850 900 1000 1050 1050 1200 1250 1400 Mean = 1001.5 Median =1025 Q1=850 Q3=1200 Range = 835 IQR= 350 55 5 – NUMBER SUMMARY • THE 5-NUMBER SUMMARY OF A DISTRIBUTION REPORTS ITS MEDIAN, QUARTILES, AND EXTREMES(MINIMUM AND MAXIMUM) • MAX = 94 • Q3 = 71.5 • MEDIAN = 61 • Q1 = 52.5 • MIN=35 OUTLIERS: DATA VALUES WHICH ARE BEYOND FENCES IQR = Q3 – Q1 = 19 UPPER FENCE = Q3 + 1.5IQR = 71.5 + 1.5x19 = 100 LOWER FENCE = Q1 – 1.5IQR = 52.5 – 1.5x19 = 24 56 DISPLAYING QUANTITATIVE DATA WHY DISPLAY DATA? DATA TABLES DO NOT OFTEN HELP US SEE (APPRECIATE) WHAT IS GOING ON. WE NEED WAYS TO SHOW THE DATA SO THAT WE CAN SEE • • • • PATTERNS RELATIONSHIPS TRENDS EXCEPTIONS. 57 BOXPLOTS WHENEVER WE HAVE A 5-NUMBER SUMMARY OF A (QUANTITATIVE) VARIABLE, WE CAN DISPLAY THE INFORMATION IN A BOXPLOT. • THE CENTER OF A BOXPLOT IS A BOX THAT SHOWS THE MIDDLE HALF OF THE DATA, BETWEEN THE QUARTILES. • THE HEIGHT OF THE BOX IS EQUAL TO THE IQR. • IF THE MEDIAN IS ROUGHLY CENTERED BETWEEN THE QUARTILES, THEN THE MIDDLE HALF OF THE DATA IS ROUGHLY SYMMETRIC. IF IT IS NOT CENTERED, THE DISTRIBUTION IS SKEWED. • THE MAIN USE FOR BOXPLOTS IS TO COMPARE GROUPS. 58 How to Draw a Boxplot and Identify Outliers Step 1: Label either a vertical axis or a horizontal axis with numbers from min to max of the data. Step 2: Draw box with lower end at Q1 and upper end at Q3. Step 3: Draw a line through the box at the median M. Step 4: Calculate IQR = Q3 – Q1. Step 5: Draw a line from Q1 end of box to smallest data value that is not further than 1.5 IQR from Q1. Draw a line from Q3 end of box to largest data value that is not further than 1.5 IQR from Q3. Step 6: Mark data points further than 1.5 IQR from either edge of the box with an asterisk. Points represented with asterisks are considered to be outliers. 59 Histogram (Minitab Commands) • Open Minitab • Click on Graph Histogram SimpleOk • Click on C1Select • Click on Labels Title (Write the title of your histogram) • Click Ok Click Ok 60 BOXPLOT OF THE PREVIOUS EXAMPLE Boxplot of C1 100 90 80 C1 70 60 50 40 30 61 Boxplots: Picturing Location and Spread for Group Comparisons 62 Boxplots: Picturing Location and Spread for Group Comparisons • Box covers the middle 50% of the data • Line within box marks the median value • Possible outliers are marked with asterisk • Apart from outliers, lines extending from box reach to min and max values. 63 Comparing Groups 64 Comparing Groups • • • • Q1: Which one has the larger median? Q2: Which one has the larger IQR? Q3: Which one has the larger range? Q4: What is your general comment? Are U.S. cars less efficient? 65 HISTOGRAMS A HISTOGRAM IS A SUMMARY GRAPH SHOWING A COUNT OF THE DATA FALLING IN VARIOUS RANGES OR CLASSES OR GROUPS. PURPOSE: TO GRAPHICALLY SUMMARIZE AND DISPLAY THE DISTRIBUITION OF A PROCESS DATA SET. 66 HISTOGRAM • It is particularly useful when there are a large number of observations. • The observations or data sets for which we draw a histogram are QUANTITATIVE variables. 67 Creating a Histogram Step 1: Decide how many equally spaced (same width) intervals to use for the horizontal axis. Between 6 and 15 intervals is a good number. Step 2: Decide to use frequencies (count) or relative frequencies (proportion) on the vertical axis. Step 3: Draw equally spaced intervals on horizontal axis covering entire range of the data. Determine frequency or relative frequency of data values in each interval and draw a bar with corresponding height. Decide rule to use for values that fall on the border between two intervals. 68 69 Histograms • Example : THE WEIGHTS OF 23 “THREE-POUND” BAGS OF APPLES ARE GIVEN AS FOLLOWS: • 3.26 3.62 3.39 3.12 3.53 3.30 3.10 3.26 3.19 3.22 3.14 3.39 3.31 3.49 3.41 3.02 3.17 3.20 3.12 3.42 3.36 3.21 3.26 • USE THESE DATA TO CONSTRUCT A HISTOGRAM FOR THE WEIGHT DATA 70 GROUP FREQUENCY DISTRIBUTION FOR WEIGHTS OF 3 LB APPLE BAGS WITH BIN = 0.1 BINS FREQUENCY 2.95 TO 3.05 1 3.05 TO 3.15 4 3.15 TO 3.25 5 3.25 TO 3.35 5 3.35 TO 3.45 5 3.45 TO 3.55 2 3.55 TO 3.65 1 71 Histogram Histogram of Weights of 3 lb Apple Bags 5 Frequency 4 3 2 1 0 3.0 3.1 3.2 3.3 C1 3.4 3.5 3.6 72 Histogram EXAMPLE 2. -4.50, -3.25, -1.75, -1.59, -1.44, -1.22, -1.16, -0.88, -0.75, -0.72, -0.69, -0.50, -0.50, -0.38, -0.28, -0.22, -0.16, 0.03, 0.12, 0.34, 0.47, 0.62, 0.69, 0.75, 0.78, 0.81, 1.16, 1.47, 2.06, 2.22, 2.44, 3.28, 3.34, 4.12, 4.31, 5.62 , 5.85 73 FREQUENCY DISTRIBUTION OF CLASS DATA CLASSES -4.5 TO -3.5 -3.5 TO -2.5 FREQUENCY 1 1 -2.5 TO -1.5 -1.5 TO -0.5 -0.5 TO 0.5 2 7 10 0.5 TO 1.5 1.5 TO 2.5 2.5 TO 3.5 3.5 TO 4.5 7 3 2 2 4.5 TO 5.5 5.5 TO 6.5 2 74 Histogram Histogram of class data 10 Frequency 8 6 4 2 0 -4 -2 0 2 4 6 C1 75 DESCRIBING THE DISTRIBUTION OF A QUANTITATIVE VARIABLE FROM HISTOGRAMS • WHEN YOU DESCRIBE THE DISTRIBUTION OF A [QUANTITATIVE] VARIABLE, YOU SHOULD ALWAYS TELL ABOUT FOUR THINGS: • • • • SHAPE CENTER SPREAD UNUSUAL FEATURES OR OUTLIERS 76 THE SHAPE OF A DISTRIBUTION 1. DOES THE HISTOGRAM HAVE A SINGLE, CENTRAL HUMP OR SEVERAL SEPERATED HUMPS? THESE HUMPS ARE CALLED MODES. A HISTOGRAM WITH ONE PEAK IS DUBBED UNIMODAL; HISTOGRAMS WITH TWO PEAKS ARE CALLED BIMODAL, AND THOSE WITH THREE OR MORE PEAKS ARE CALLED MULTIMODAL. A HISTOGRAM THAT DOESN’T APPEAR TO HAVE ANY MODE AND IN WHICH ALL THE BARS ARE APPROXIMATELY THE SAME HEIGHT IS CALLED UNIFORM. 77 UNIMODAL, BIMODAL, MULTI-MODAL, UNIFORM HISTOGRAMS 78 2. IS THE HISTOGRAM SYMMETRIC? • CAN YOU FOLD THE HISTOGRAM ALONG A VERTICAL LINE THROUGH THE MIDDLE AND HAVE THE EDGES MATCH PRETTY CLOSELY, OR ARE MORE OF THE VALUES ON ONE SIDE? • THE (USUALLY) THINNER ENDS OF A DISTRIBUTION ARE CALLED TAILS. IF ONE TAIL STRETCHES OUT FARTHER THAN THE OTHER, THE HISTOGRAM IS SAID TO BE SKEWED TO THE SIDE OF THE LONGER TAIL. • A “SKEWED RIGHT” DISTRIBUTION IS ONE IN WHICH THE TAIL IS ON THE RIGHT SIDE. • A “SKEWED LEFT” DISTRIBUTION IS ONE IN WHICH THE TAIL IS ON THE LEFT SIDE. 79 Skewed Right; Skewed Left 80 RIGHT-SKEWED HISTOGRAM 81 SYMMETRIC HISTOGRAM 82 BELL-SHAPED (SYMMETRIC) HISTOGRAM 83 LEFT-SKEWED HISTOGRAM 84 3. DO ANY UNUSUAL FEATURES STICK OUT? • UNUSUAL FEATURES OR OUTLIERS ARE EXTREME VALUES THAT DO NOT APPEAR TO BELONG WITH THE REST OF THE DATA. SUCH STRAGGLERS STAND OFF AWAY FROM THE BODY OF THE DISTRIBUTION. OUTLIERS CAN AFFECT MANY STATISTICAL ANALYSES, SO YOU SHOULD ALWAYS BE ALERT FOR THEM. 85 Illustration 86 Illustration of Possible Outliers 87 Illustration of a Possible Outlier 88 Some Remarks Symmetric: mean = median Skewed Left: mean < median Skewed Right: mean > median 89 EXAMPLE 90 More Remarks • FOR SYMMETRIC DISTRIBUTIONS, REPORT THE MEAN AS A MEASURE OF CENTER AND THE STANDARD DEVIATION AS A MEASURE OF SPREAD. • FROM SKEWED DISTRIBUTIONS, REPORT THE MEDIAN AS A MEASURE OF CENTER AND THE INTERQUARTILE RANGE AS A MEASURE OF SPREAD 91 EXAMPLE 92 STEM AND LEAF DISPLAY • HISTOGRAMS PROVIDE AN EASY-TOUNDERSTAND SUMMARY OF THE DISTRIBUTION OF A QUANTITATIVE VARIABLE, BUT THEY DON’T SHOW THE DATA VALUES THEMSELVES. • A STEM AND LEAF DIAGRAM IS AN EXPLORATORY DATA-ANALYSIS TECHNIQUE THAT ALLOWS US TO GROUP DATA WITHOUT LOSING THE ORIGINAL DATA. WE USE THE LEADING DIGIT(S) AS THE “STEM” AND THE TRAILING DIGIT(S) AS THE “LEAVES,” SO THAT THE NUMBERS THEMSELVES BECOME A GRAPH OF THE 93 DATA. Creating Stem-and-Leaf Plots Step 1: Determine stem values. The “stem” contains all but the last of the displayed digits of a number. Stems should define equally spaced intervals. Step 2: For each individual, attach a “leaf” to the appropriate stem. A “leaf” is the last of the displayed digits of a number. Often leaves are ordered on each stem. Note: More than one way to define stems. Can use split-stems or truncate/round values first. 94 Stem-and-Leaf Plot • STEM-AND-LEAF DISPLAYS CONTAIN ALL THE INFORMATION FOUND IN A HISTOGRAM AND, WHEN CAREFULLY DRAWN, SATISFY THE AREA PRINCIPLE AND SHOW THE DISTRIBUTION. IN ADDITION, STEM-AND-LEAF DISPLAYS PRESERVE THE INDIVIDUAL DATA VALUES. • UNLIKE A HISTOGRAM, STEM-AND-LEAF DISPLAYS ALSO SHOW THE DIGITS IN THE BINS, SO THEY CAN REVEAL UNEXPECTED PATTERNS IN THE DATA. 95 EXAMPLE : CONSIDER THE SORTED AND ROUNDED DATA BELOW. -4.5, -3.3, -2.0, -1.8, -1.6, -1.4, -1.2, -0.9, -0.9, -0.8, -0.7, -0.7, -0.5, -0.5, -0.4, -0.3, -0.2, -0.2, 0.0, 0.1, 0.3, 0.5, 0.6, 0.7, 0.8, 0.8, 0.8, 1.2, 1.5, 2.1, 2.2, 2.4, 3.3, 3.3, 4.1, 4.3, 5.6 STEM LEAVES -4 5 -3 3 -2 0 -1 8642 -0 99877554322 0 013567888 1 25 2 124 3 33 4 13 5 6 96 EXAMPLE : USING THE WEIGHTS OF THE BAGS OF APPLES GIVEN IN THE EXAMPLE OF SLIDE 68, CONSTRUCT A STEM-AND-LEAF DIAGRAM. STEM 3.0 3.1 3.2 3.3 3.4 3.5 3.6 LEAVES 2 209472 6621016 90916 912 3 2 THE WEIGHTS OF THE BAGS RANGE FROM 3.02 TO 3.62, SO CAN USE AS STEMS THE VALUES 3.0 – 3.6. THE LEAVES ARE DETERMINED BY THE DIGIT FOUND IN THE HUNDRED’S PLACE OF THE ORIGINAL DATA. 97 DOTPLOTS • A DOTPLOT GRAPHS A DOT FOR EACH CASE AGAINST A SINGLE AXIS. • IT IS LIKE A STEM-AND-LEAF DISPLAY, BUT WITH DOTS INSTEAD OF DIGITS FOR ALL THE LEAVES. • SOME DOTPLOTS STRETCH OUT HORIZONTALLY, WITH THE COUNTS ON THE VERTICAL AXIS, LIKE A HISTOGRAM. OTHERS RUN VERTICALLY, LIKE A STEMAND-LEAF DISPLAY. 98 Creating a Dotplot • Draw a number line (horizontal axis) to cover range from smallest to largest data value. • For each observation, place a dot above the number line located at the observation’s data value. • When multiple observations with the same value, dots are stacked vertically 99 Example THE DATA BELOW GIVE THE NUMBER OF HURRICANE THAT HAPPENED EACH YEAR FROM 1944 THROUGH 2000 AS REPORTED BY SCIENCE MAGAZINE. • 3,2,1,2,4,3,7,2,3,3,2,5,2,2,4,2,2,6,0, 2,5,1,3,1,0,3,2,1,0,1,2,3,2,1,2,2,2,3, 1,1,1,3,0,1,3,2,1,2,1,1,0,5,6,1,3,5,3 100 Frequency Table of Hurricanes # OF HURRICANES/YEAR FREQUENCY OR COUNT 0 4 1 14 2 17 3 12 4 2 5 4 6 2 7 1 101 Dot Plot For Hurricane Data Dot plot for hurrican data 0 1 2 3 4 5 6 7 C6 102 DESCRIPTION OF THE DISTRIBUTION • EACH DOT REPRESENTS A YEAR IN WHICH THERE WERE THAT MANY HURRICANES. • THE DISTRIBUTION OF THE NUMBER OF HURRICANES PER YEAR IS UNIMODAL • SKEWED TO THE RIGHT • WITH CENTER AROUND 2 HURRICANES PER YEAR. • THE NUMBER OF HURRICANES PER YEAR RANGES FROM 0 TO 7. • THERE ARE NO OUTLIERS. 103 Right Handspan of College Students 104 Right Handspan of College Students • Majority of females had handspans between 19 and 21 cm, and many males had handspans between 21.5 and 23 cm. • Two females with unusually small handspans. 105 Interpreting Histograms, Stem-plots, and Dot-plots 106 Comparing Histograms and Boxplots 107 DISPLAYING CATEGORICAL DATA • THE BAR CHART • THE PIE CHART 108 EXAMPLE: CONSIDER THE TITANIC • WHO: THE 2201 PEOPLE ON THE TITANIC; • WHAT (VARIABLES): – – – – – – SURVIVAL STATUS (DEAD OR ALIVE); TICKET CLASS (FIRST, SECOND, THIRD, CREW); GENDER (MALE OR FEMALE); WHEN APRIL 14, 1912; WHERE NORTH ATLANTIC; HOW A VARIETY OF SOURCES AND INTERNET SITES; – WHY HISTORICAL INTEREST. 109 ONE VARIABLE ANALYSIS WHO: THE 2201 PEOPLE ON THE TITANIC WHAT: TICKET CLASS DISTRIBUTION FREQUENCY TABLE: A FREQUENCY TABLE LISTS THE CATEGORIES IN A CATEGORICAL VARIABLE AND GIVES THE COUNT OR PERCENTAGE OF OBSERVATIONS OF EACH CATEGORY. CLASS COUNT OR FREQU ENCY % OR RELATI VE FREQU ENCY FIRST 325 285 706 14.766 12.949 32.076 885 2201 40.209 100 SECOND THIRD CREW TOTAL 110 DISTRIBUTION OF A VARIABLE * GIVES THE POSSIBLE VALUES OF THE VARIABLE, AND * THE RELATIVE FREQUENCY OF EACH VALUE. GRAPHICAL DISPLAY OF A DISTRIBUTION OF CATEGORICAL DATA BAR CHART (A BAR CHART DISPLAYS THE DISTRIBUTION OF A CATEGORICAL VARIABLE, SHOWING THE COUNTS FOR EACH CATEGORY NEXT TO EACH OTHER FOR EASY COMPARISON.) PIE CHART PIE CHARTS SHOW THE WHOLE GROUP OF CASES AS A CIRCLE. THEY SLICE THE CIRCLE INTO PIECES WHOSE SIZE IS PROPORTIONAL TO THE FRACTION OF THE WHOLE IN EACH CATEGORY. 111 BAR CHART OF THE PEOPLE(WHO) ON THE TITANIC WITH TICKET CLASS DISTRIBUTION(WHAT) 900 800 700 600 500 400 300 200 100 0 FIRST SECOND THIRD CREW 112 PIE CHART OF PEOPLE ON THE TITANIC(WHO) WITH TICKET CLASS DISTRIBUTION(WHAT) 15% 40% 13% FIRST SECOND THIRD CREW 32% 113 THE AREA PRINCIPLE: THE AREA OCCUPIED BY A PART OF THE GRAPH SHOULD CORRESPOND TO THE MAGNITUDE OF THE VALUE IT REPRESENTS. TIPS • FIRST RULE OF DATA ANALYSIS IS ‘MAKE A PICTURE.’ • BEFORE YOU MAKE A BAR CHART OR A PIE CHART, ALWAYS CHECK THE CATEGORICAL DATA CONDITION. THE DATA ARE COUNTS OR PERCENTAGES OF INDIVIDUALS IN CATEGORIES. • IF YOU WANT TO MAKE A RELATIVE FREQUENCY BAR CHART OR PIE CHART, YOU’LL NEED TO ALSO MAKE SURE THAT THE CATEGORIES DON’T OVERLAP, SO NO INDIVIDUAL IS COUNTED TWICE. 114