lOMoARcPSD|18274273 Chapter 4 Analysis Interpretation of Assessment REsults 13B53C Secondary education (Eastern Visayas State University) StuDocu is not sponsored or endorsed by any college or university Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 CHAPTER 4 Analysis and Interpretation of Assessment Results Introduction Statistics plays a very important role in assessing the performance of students, most especially in interpreting and analyzing their scores through assessment activities. Teachers should know how to utilize these data, particularly in decision-making. Hence, a classroom teacher should have the necessary background in statistical procedures in order for him to give a correct description, and interpretation of student’s performance in a certain test. This lesson is a review of the important tools needed in describing, analyzing and interpreting assessment results. The topics discussed in this module are presentations of data through textual, tabular and graphical, measures of tendency, measures of dispersion, measures of relative positions, other measure and the level of measurement. Learning Outcomes At the end of the module, the student should be able to: a. Interpret assessment results accurately and utilize them to help learners improve their performance and achievement; and b. Utilize assessment results to make informed-decisions to improve instruction. Lesson 1 - Presentation The study of statistics begins with the collection of data or measurements. Data collected should be organized systematically for easier and faster interpretation. Data can be presented in three forms: textual, tabular, and graphical. The tabular and graphical forms are used when more detailed information about the data is to be presented. A table is used when you want to present a data in a systematic and organized manner so that reading and interpretation will be simpler and easier. A.1 Textual Presentation Ungrouped data can be presented in textual form, as in paragraph form. This involves enumerating the important characteristics, giving emphasis on significant figures and identifying important features of the data. Example 1. Below are the test scores of 50 students in Statistics: 25 30 43 18 35 17 40 50 9 12 33 37 46 28 19 27 41 10 18 28 21 36 13 31 20 31 35 28 16 42 40 48 13 40 3 39 50 32 32 26 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) 41 lOMoARcPSD|18274273 Arranging the scores from the lowest to the highest will facilitate the enumeration of important characteristics of the data. The test scores of the 50 students in Statistics arranged from lowest to highest are shown below: 3 13 32 17 35 20 40 27 43 30 9 13 18 21 28 30 33 36 40 46 10 14 18 25 28 31 34 37 40 48 10 15 19 26 28 31 35 With the data now arranged according to magnitude, we can easily see the 38 41 50 important features worth mentioning in the text. One way of describing the data using the 12 16 20 26 29 32 35 textual form is as follows: 39 42 50 The highest score obtained is 50 and the lowest is 3. Ten students got a score of 40 and above, while only 4 got ten and below. Generally, the students performed well in the test with 33 students of 66% getting a score of 25 and above. Arranging a mass of data manually is quite tedious, but using computers for this purpose is so easy. In the absence of a computer, the process is made easy by putting the data in a stem-and-leaf plot. Stem-and-leaf plot is a table which sorts data according to a certain pattern. It involves separating a number into two parts. In a two-digit number, the stem consists of the first digit, and the leaf consists of the second digit. While in a three-digit number, the stem consists of the first two digits, and leaf consists of the last digit. In a one-digit number, the stem is zero. Using the unarranged test scores in Statistics of 50 students as data, stem-and-leaf plot can be used to arrange from lowest to highest. The stems are as follows: 0, 1, 2, 3, 4, and 5, three being the lowest and 50 the highest. Table 1 Stem-and-Leaf Plot of Unarranged Test Scores in Statistics of 50 Students Stem Leaves 0 3, 9 1 0, 0, 2, 3, 3, 4, 5, 6, 7, 8, 8, 9 2 0, 0, 1, 5, 6, 6, 7, 8, 8, 8, 9 3 0, 0, 1, 1, 2, 2, 3, 4, 5, 5, 5, 6, 7, 8, 9 4 0, 0, 0, 1, 2, 3, 6, 8 5 0, 0 looking at the stem-and-leaf plot, we can easily rank the data or put them in order. Thus, the ten lowest scores are: 3, 9, 10, 10, 12, 13, 13, 14, 15, and 16, while the ten highest scores are: 40, 40, 40, 41, 42, 43, 46, 48, 50, and 50. By A. 2. Tabular Method Sometimes, we cold hardly grasp information from a textual presentation data. Thus, we may present data by using tables. By organizing the data in tables, important features about the data can be readily 42 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 understood and comparisons can be easily made. Thus, a table shows complete information regarding the data. A table has the following parts: 1. Table number : This is for easy reference to the table. 2. Table title: It briefly explains the content of the table. 3. Column header: It describes the data in each column. 4. Row classifier: It shows the classes or categories. 5. Body: This is the main part of the table. 6. Source note: This is placed below the table when the data written are not original. Below is a table with all its parts indicated: Table Number Table 2 Distribution of Students in XYZ High School According to Year Level Table Title Column Number of Students Header 300 250 Body 285 215 N = 1,050 Source Note Source: XYZ High School Registrar Year Level First Year Second Year Third Year Fourth Year Row classifier Another type of tabular presentation is the frequency table also known as a frequency distribution. It is an arrangement of the data that shows the frequency of occurrence of different values of the variables. A frequency distribution table is a table which shows the data arranged into different classes and the number of cases which fall into each class. The frequency distribution table for ungrouped data is simply an arrangement of data from lowest to highest which shows the frequency of occurrence of each value in a set. This is best used when the range of values is not too wide. Example: Table 3 Ungrouped Frequency Distribution for the Ages of 50 Students Enrolled in Statistics Age 14 15 16 17 18 18 Frequency 4 13 25 5 2 1 N = 50 1. Table number is ____. 2. Table title is Ungrouped Frequency Distribution fort he Ages of 50 Students Enrolled in Statistics 3. Column headers are: a) Age b) Frequency 4. Row classifiers: 14, 15, ..., 19 43 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Notice that the range of the ages is 5, that is subtracting 14, the lowest age, from 19, the highest age. However, if the range is more than 15, the best way is to group the data into classes using the grouped frequency distribution table. The frequency distribution for grouped data is an arrangement of data into different classes or categories. It involves counting the data which fall into each class. Below are the steps in constructing a frequency distribution table: 1. Find the range of scores: Range = Highest score - Lowest score = 99 - 67 = 32 2. Decide on the number of class interval k Maximum = 20 Minimum = 7 Ideal = 10 - 15 k n Estimate: (rounded to the nearest whole number) where n, is the total number of scores or cases k 40 6 Thus, for the above scores, or 6. 3. Determine the class size i of the interval. 44 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Range 32 i k 6 or i = 5. (An odd value of i is preferred). 4. Determine the lower limit LL and upper limit of the lowest class interval (the class interval containing the lowest score). LL = score or number closest to but less than the lowest score and preferably a multiple of the class size i. In the given set of scores, the lowest score is 67. The number closest to 67 that is divisible by the class size i = 5 is 65. Thus, LL = 65. UL = LL + (i - 1). Thus, UL = 65 + (5 - 1) = 69. 5. Determine the other class intervals by consecutively adding the class size i to LL and UL until the interval containing the highest score is contained and make a tally. Thus, Illustration: Performance ratings of government employees 76 67 99 82 86 92 85 95 86 93 87 93 79 83 98 Class Interval 95 - 99 90 - 94 85 - 89 80 - 84 75 - 79 70 - 74 65 - 69 78 91 85 87 71 87 85 81 79 81 Tally //// //// - /// //// - //// - // //// - // //// - / // / 88 79 96 92 86 85 92 75 80 80 92 82 88 74 94 f 4 8 12 7 6 2 1 The limits that define the class intervals as indicated above are called apparent limits. To reflect the continuity of scores, the true limits or class boundaries are indicated. These are obtained by adding all upper limits and subtracting all lower limits on-half of the difference between successive adjacent lower and upper limits. For this particular data, the number to be added and subtracted is 0.5 Other information usually included in a frequency distribution are: 45 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 LL U 2 X = the class mark or class midpoint of the class interval = <cf = the less than cumulative frequency = the frequency of the interval plus all frequencies below the interval >cf = the greater than cumulative frequency = the frequency of the interval plus all frequencies above the interval 46 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 rf = the relative f n Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) 47 lOMoARcPSD|18274273 frequency of the interval = The same frequency distribution with additional information as cited above is shown below: Table 4 Performance Rating of Government Employees Class Interval f X rf <cf 95 - 99 4 97 0.100 40 90 - 94 8 92 0.200 36 85 - 89 12 87 0.300 28 80 - 84 7 82 0.175 16 75 - 79 6 77 0.150 9 70 - 74 2 72 0.050 3 65 - 69 1 67 0.025 1 Remarks: 1. The class mark is assumed to be the average of the scores that fall within the interval. 2. The <cf tells the number of scores or data falling below the true upper limit of the interval. Thus, for instance, 16 scores are lower than a score of 84.5; 79.5 is the score below which we find 9 out of the 40 scores. 3. The >cf tells the number of scores or data falling above the true limit of the interval. Thus, for instance, 37 scores are higher than a score of 74.5; 84.5 is the score above which we find 24 out of the 40 scores. 4. The relative frequency tells about the proportion or percentage of cases within the class interval. Thus, 15% of all the scores are found between 75 - 79. >cf 4 12 24 31 37 39 40 A.3 Graphical Presentation A graph is a diagram which makes a systematic presentation of a class frequency distribution together with comparison and relationship of the classes. As a graph is usually perceptible, it is easily understood. There are two most common methods for graphing frequency distribution: Histogram and the frequency polygon. Histogram represents a pictorial presentation of a frequency distribution. It may be thought of as a series of rectangles and frequencies, respectively. In histogram, the bases is equal to the length of the interval, and the height is equal to the frequency. It resembles a bar graph. Frequency polygon is another method of graphing frequency distribution. It is also pictorial but it is constructed by joining with straight lines a series of points which are the midpoints of the steps as against their corresponding frequencies. It looks like a zigzag line. 48 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Lesson 2 - Quantitative Analysis and Interpretation 2.1 Levels of Measurement Statistics deals mostly with measurements. We define measurement as the assignment of symbols or numerals to objects or events according to some rules. Since different rules are used for the assignment of symbols, then this would yield different scales of measurement. There are four measurement scales, namely, nominal, ordinal, interval, and ratio. 1. Nominal Scale This is the most primitive level of measurement. The nominal level of measurement is used when we want to distinguish one object from another for identification purposes. In this level, we can say that one object is different from another, but the amount of difference between them cannot be determined. We cannot tell that one is better or worse than the other. Gender, nationality, and civil status are of nominal scale. 2. Ordinal Scale In the ordinal level of measurement, data are arranged in some specified order or rank. When objects are measured in this level, we can say that one is better or greater than the other. But we cannot tell how much more or how much less of the characteristic one object has than the other. The ranking of contestants in a beauty contest, of siblings in the family, or of honor students in the class are of ordinal scale. 3. Interval Scale If data are measured in the interval level, we can say not only one object is greater or less than another, but we can also specify the amount of difference. The scores in an examination are of the interval scale of measurement. To illustrate, suppose Maria got 50 in a Math examination while Martha got 40. We can say that Maria got higher than Martha by 10 points. 4. Ratio Scale The ratio level of measurement is like the interval level. The only difference is that the ratio level always starts from an absolute or true zero point. In addition, in the ratio level, there is always the presence of units of measure. If data are measured in this level, we can say that one object is so many times as large or as small as the other. For example, suppose Mrs. Reyes weighs 50 kg, while her daughter weighs 25 kg. We can say that Mrs. Reyes is twice as heavy as her daughter. Thus, weight is an example of data measured in the ratio scale. 2.2 Measures of Central Tendency 2.2.1 Measures of Central Tendency for Ungrouped Data 2.2.1.1 The Mean The mean (also known as the x arithmetic mean) is the most commonly used measure of central position. It is the sum of measures divided by the number of measures in a variable. It is symbolized as (read as x bar). The mean is used to describe a set of data where measures cluster or concentrate at a point. As the measure cluster around each other, a single value appears to represent distinctively the total measures. It is, however, affected by extreme measures, that is, very high or very low measures can easily change the value of the mean. To find the mean of ungrouped data, use the formula where = the summation of x (sum of the measure) N = number of values of x 49 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Example: The grades in Chemistry of 10 students are 87, 85, 85, 86, 90, 79, 82, 78, 76. What is the average grade of the 10 students? Solution: 87 84 85 85 86 90 79 82 78 76 x 10 2.2.1.2 The Weighted Arithmetic Mean 859 . xW x x W .58 x 10 81 Occasionally, we want to find the mean of a set of values wherein each value or measurement has a different weight or degree of importance. We call this the weighted mean and the formula for computing it is as follows: where: 120 123 83 162 80 127 80(1.5) 82(1.5) 83(1) 81(2) 80(1) 85 10 10 55 50 Subject Units Grade Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 2.2.1.3 The Median The median is the middle entry or term in a set of data arranged in either increasing or decreasing order. The median is a positional measure. Thus, the values of the individual measures in a set of data do not affect it. It is affected by the number of measures and not by the size of the extreme values. To find the median of a given set of data, take note of the following: 1. Arrange the data in either increasing or decreasing order. 2. Locate the middle value. If the number of cases is odd, the middle value is the median. If the number of cases is even, take the arithmetic mean of the two middle measures. Example 1: The number of books borrowed in the library from Monday to Friday last week were 58, 60, 54, 35, and 97 respectively. Find the median. Solution: Arrange the number of books borrowed in increasing order. 35, 54, 58, 60, 97 The median is 58. Example 2: Cora’s quizzes for the second quarter are 8, 7,6, 10, 9, 5, 9, 6, 10, and 7. Find the median. Solution: Arrange the scores in increasing order. 5, 6, 6, 7, 7, 8, 9, 9, 10, 10 Since the number of measures is even, then the median is the average of the two middle scores. 2.2.1.4 The Mode 7 8 Md 2 The mode is another measure of position. The mode is the measure or value which occurs most frequently in a set of data. It is the value with the greatest frequency. To find the mode for a set of data 1. select measure that appears most often in the set; 2. if two or more measures appear the same number of items, and the frequency they appear is greater than any of other measures, then each of these values is a mode; 3. if every measure appears the same number of items, then the set of data has no mode. 51 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 1 4 2 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) 52 lOMoARcPSD|18274273 Example 1: The shoe size of 10 randomly selected students in a class are 6, 5, 4, 6, , 5, 6, 7, 7 and 6. What is the mode? Answer: The mode is 6 since it is the shoe size that occurred the most number of times. Example 2: The sizes of 9 classes in a certain school are 50, 52, 55, 50, 51, 54, 55, 53 and 54. Answer: The modes are 54 and 55 since the two measures occurred the same number of times. The distribution is bimodal. 2.2.2 Measures of Central Tendency for Grouped Data 2.2.2.1 The Mean of Grouped Data Using the Class marks When the number of items in a set of data is too big, items are grouped for convenience. The manner of computing for the mean of grouped data is given by the formula: Mean ( fX f ) where: f is the frequency of each class X is the class mark of class fX f 53 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 The Greek symbol (sigma) is the mathematical symbol for summation. This means that all items having this symbol are to be added. Thus, the symbol means the sum of all frequencies, and means the sum of all the products of the frequency and the corresponding class mark. Class 46 - 50 41 - 45 36 - 40 31 - 35 26 - 30 21 - 25 16 - 20 11 -15 E es: Class 46 - 50 41 - 45 36 - 40 31 - 35 26 - 30 21 - 25 16 - 20 11 - 15 f 1 5 11 12 11 5 2 1 Frequency 1 5 11 12 11 5 2 1 X 48 43 38 33 28 23 18 13 Compute the mean of the scores of the students in a Mathematics fX 48 215 418 396 308 115 36 13 xampl test. The frequency distribution for the data is given below. The columns X and fX are added. 54 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 f 4 fX 1,5 55 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Mean 1,5 Mean 4 56 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Mean 32. The mean score is 32.27. 2.2.2.2 The Mean of Grouped Data Using the Coded Deviation An alternative formula for computing the mean of grouped data makes use of coded deviation. Mean A.M . where: A.M. is the assumed mean f is the frequency of each class d is the coded deviation from A.M. i is the class interval Any class mark can be considered as assumed mean. But it is convenient to choose the class mark with the highest frequency. The class chosen to contain A.M. is given a 0 deviation. Subsequently, consecutive positive integers are assigned to the classes upward and negative integers to the classes downward. This is illustrated in the next examples using the same data in the previous example. Examples: Compute the mean of the scores of the students in Mathematics test. Class 46 - 50 41 - 45 Frequency 1 5 57 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 36 - 40 31 - 35 26 - 30 21 - 25 16 - 20 11 - 15 11 12 11 5 2 1 The frequency distributor for the data is given below. The columns X, d and fd are added. Class 46 - 50 41 - 45 36 - 40 31 - 35 26 - 30 21 - 25 16 - 20 11 - 15 Solution: f 1 5 11 12 11 5 2 1 X 48 43 38 33 28 23 18 13 d 3 2 1 0 -1 -2 -3 -4 fd 3 10 11 0 -11 -10 -6 -4 A . M . 3 fd f 4 i 5 ,,, 58 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 fd Mean A.M . i f 33 2,750 5 30 = 2,750 5 Mean 3,3 The mean gross sale is Php3,300. 2. 2.2.3 The Median of Grouped Data The median is the middle value in a set of quantities. It separates an ordered set of data into two equal parts. Half of the quantities found above the median and the other half is found below it. In computing for the median of grouped data, the following formula is used: 59 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 where: lbmc is the lower boundary of the median class f is the frequency of each class cf is the cumulative frequency of the lower class next to the median class fmc is the frequency of the median class i is the class interval The median class is the class that median must be within the median class. f 2 contains the quantity. The computed th Examples: 1. Compute the median of the scores of the students in a Mathematics test. Class 46 - 50 41 - 45 36 - 40 31 - 35 26 - 30 21 - 25 16 - 20 11 - 15 Frequency 1 5 11 12 11 5 2 1 The frequency distribution for the data is given below. The columns for lb and “less than” cumulative frequency are added. Class 46 - 50 41 - 45 36 - 40 31 - 35 26 - 30 21 - 25 16 - 20 11 - 15 f 1 5 11 12 11 5 2 1 lb 45.5 40.5 35.5 30.5 25.5 20.5 15.5 10.5 <cf 48 47 42 31 19 8 3 1 60 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 f 2 48 24 2 24 th Since , the quantity is in the class 31 - 35. Hence, the median class is 31 - 35. 61 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 i mc5 lb 30 f 4 f mc 11 cf Solution: f Median lbmc 2 62 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 48 19 2 30.5 12 24 19 30.5 12 63 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 5 30.5 12 2 30.5 1 30.5 2.0 64 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Median 32. The median score is 32.58. 2. 2.2.4 The Mode of Grouped Data The mode of grouped data can be approximated using the following formula: D1 Mode lbmo i D1 D2 where: lbmo is the lower boundary of the modal class D1 is the difference between the frequencies of the modal class D2 is the difference between the frequencies of the modal class and the next upper class and the next lower class i is the class interval The modal class is the class with the highest frequency. If binomial classes exist, any of these classes may be considered as modal class. Examples: Compute the mode of the scores of the students in a Mathematics test. Class 46 - 50 41 - 45 36 - 40 31 - 35 26 - 30 21 - 25 16 - 20 11 - 15 Frequency 1 5 11 12 11 5 2 1 The frequency distribution for the data given below. The column for lb is added. 65 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Class 46 - 50 41 - 45 36 - 40 31 - 35 26 - 30 21 - 25 16 - 20 11 - 15 f 1 5 11 12 11 5 2 1 lb 45.5 40.5 35.5 30.5 25.5 20.5 15.5 10.5 Solution: Since class 31 - 35 has the highest frequency, the modal class is 31 - 35. lbmo = 30.5 D1 = 12 - 11 = 1 D2 = 12 - 11 = 1 i=5 D Mode lbmo D 1 30.5 1 1 66 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 1 30.5 2 30.5 30.5 2 67 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Mode 3 The mode score is 33. Measures of Central Tendency Measure Mean Common Name Arithmetic Average Median Middle score Mode Typical score When to use There are no extreme scores When the data are interval or ratio The distribution is skewed When the data are ranks When a quick estimate of the typical score is to be determined Advantage Most reliable Stable and less variable from sample to sample Easy to compute Not affected by extreme scores Easy to compute Disadvantage Affected by extreme scores Less stable from sample to sample The most unstable measure especially when the number of scores is small Source: Dr. Gabino Petilos’ Hand-out Relationship of the Three Measures of Central Tendency A. For symmetric distributions Mean = Median = Mode 68 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Source: Dr. Gabino Petilos’ Hand-out B. For skewed distributions a) Negatively skewed distributions Mean Median M Source: Dr. Gabino Petilos’ Hand-out b) Positively skewed distributions Mean Median M Source: Dr. Gabino Petilos’ Hand-out 2. 3 Measures of Dispersion The three measures of central tendencies that you have learned on the previous lesson do not give an adequate description of the data. We need to know how the observations spread out from average or mean. It is quite possible to have two sets of observations with the same mean and median that differs in the variability of their measurements about the mean. Measures of dispersion are sometimes called measures of variability. The measures of dispersion can be utilized in determining the size of the distribution of scores or a portion of it. They can be used to find the deviation of scores from the mean scores. Measures of dispersion can also be sued to establish the actual similarities or the difference(s) of the distribution. In general, these measures are employed to further characterize the distributions of scores. Consider the following measurements, in liters, for two samples of apple juice in a tetra packed by companies A and B. Sample A 0.97 1.00 Sample B 1.06 1.01 69 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 0.94 1.03 1.11 0.88 0.91 1.14 Both samples have the same mean. It is quite obvious that company A packed apple juice with a more uniform content than company B. We say that the variability or the dispersion of the observations from the mean is less for sample A than for sample B. Therefore, in buying apple juice, we would feel more confident that the tetra pack we select will be closer to the advertised mean if we buy from company A. Statistics other than the mean may provide additional information from the same data. This statistics are the measure of dispersion. Measures of dispersion or variability refer to the spread of the values about the mean. These are important quantities used by statisticians in evaluation. Smaller dispersion of scores arising from the comparison often indicates more consistency and more reliability. 2.3.1 The Range The range is the simplest measure of variability. It is the difference between the largest ad smallest measurement. where: R=H-L R = Range, H = Highest measure, L = Lowest measure The main advantage of the range is that it does not consider every measure in the data. Examples: 1. The IQs of 5 members of a family are 108, 112, 127, 118 and 113. Find the range. Solution: The range of the IQs is 127 - 108 = 19. 2. The range of each of the set of scores of the three students is as follows: Student A Student B Student C H=98 H=97 H = 97 L=92 R = 98 - 92 = 6 L=90 R = 97 - 90 = 7 L = 90 R = 97 - 90 = 7 70 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Observe that two students are “tie”. This indicates that the range is not a reliable measure of dispersion. It is a poor measure of dispersion, particularly if the size of the sample or population is large. It considers only the extreme values and tells us nothing about the distribution of numbers in between. 3. Consider the following two sets of data, both with a range of 12. In set A the mean and the median are both 8, but the numbers vary over the entire interval from 3 to 15. In set B the mean and the median are also 8, but most of the values are closer to the center of the data. Although the range fails to measure the dispersion between the upper and lower observation, it does have some useful applications. In industry the range for measurements on items coming off an assembly line might be specified in advance. As long as all measurements fall within the specified range, the process is said to be in control. Disadvantages of the Range 1. It makes use of very little information: that is, it ignores but two items only. 2. It is totally dependent on the two extremes values, so it is greatly affected by any changes in these values. 3. It should be used with caution, particularly with data that contain a single extremely large value as this value would have a considerable effect on the range. 4. It cannot identify the difference between two sets of data with the same extreme values, example, the two sets of data are 2, 4, 6, 8, 10, 12, 14, 16, 18 and 2, 2, 2, 2, 2, 2, 2, 2, 18 both have the same range 16. 2.3.2 Range of a Frequency Distribution The range of a frequency distribution is simply the difference between the upper class boundary of the top interval an lower class boundary of the bottom interval. Example: Scores in Midterm Exam of BEEd First Year Students Scores Frequency 46 - 50 1 41 - 45 10 36 - 40 10 31 - 35 16 26 - 30 9 21 - 25 4 Upper class boundary (UCB) = 50.5 Lower class boundary (LCB) = 20.5 UCB - LCB = 50.5 - 20.5 = 30 2.3.3 The Interquartile Range Another measure of dispersion is the range of scores of specified part/s of the total group usually the middle 50 percent of the cases lying between Q1 and Q2. This measure is called the interquartile range. Thus, the interquartile range is the difference between the third and the first quartiles, that is, Q 3 - Q1. 71 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Example 1: Consider the following sample raw scores of students in Statistics: 17, 17, 26, 28, 30, 30, 31, 37. Solution: nk (8)(1) 8 (2 3) th Q1 2 Q1 scores 4 4 4 2 nk (8)(3) 24 6 7 30 Q3 6 Q3 4 4 4 2 2 th I.Q.R = Q3 - Q1 = 30.5 - 21.5 = 9 Example 2: Consider the frequency distribution of test scores of 40 students in Teaching Strategies below. Calculate the interquartile range. Class interval 70 - 74 65 - 69 60 - 64 55 - 59 50 - 54 45 - 49 40 - 44 35 - 39 30 - 34 25 - 29 f 2 2 3 2 8 9 2 4 5 3 n = 40 Solution: 72 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 n = 40 k=1 nk nk (40)(1) 40F 4 4 4 Q41 LQ1 f Q1 Q1 i mQ 5 11 L 34 Ff 73 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 10 34.5 4 2 34.5 4 74 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 1 34.5 4 34.5 2 75 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Q1 3 76 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 k=3 n = 40 Median class = 50 - 54 Fm-1 = 23 fQ3 = 8 LQ3 = 49.5 i=5 nk F nk 40 3 4 120 Q3 LQ 3 f4Q1 4 4 77 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 (40)(3) 4 49.5 23 78 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 30 2 49.5 8 I.Q. R. = Q3 - Q1 = 53.88 - 37 I.Q.R. = 16.88 7 49.5 8 79 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 49.5 3 Example 1: The test scores of nine students in Educational Psychology are as follows: 15, 19, 20, 24, 28, 30, 32, 32, and 40. Compute the quartile deviation. nk 9 1 9 Q1 2.25 Q1 3rd 4 4 4 nk 9 31 27 9 Q13 26.25 .75 QQ1337rd th 4 4 44 nk 9 3 27 Q3 Q Q 6.75 Q20 3 7th 32 3 1 4 4 4 th th Q.D . nk 8 813 8 24 30 nk (2 36) 7 17 3 Q Q 2 6Q score Solution: Q3 = 49.5 + 4.38 = 53. 88 Example 1: The test scores of nine students in Educational Psychology are as 2.3.4 The follows: Quartile15, Deviation 19, 20, 24, 28, 30, 32, 32, and 40. Compute the quartile deviation. The quartile deviation (Q.D.) is another measure of dispersion that divides the difference of third and first quartiles into halves. It is the average distance from the median Solution: to the two (2) quartiles, i.e., it tells how far the quartile points (Q 1 and Q3) lie from the median, on the average. When Q.D. Is small the set of scores is more or less homogeneous but when Q.D. Is large, the set of scores is more or less heterogeneous. This measure is used when there are extremely high and low scores especially when there are big gaps between scores. It is also essentially used when the main concern is the concentration of the middle 50% of the scores around the median. Mathematically, Q.D. Q3 Q1 2 Example 2: The test scores of eight students in Statistics are as follows: 17, 17, 26, 13 44 44 4 42 1 3 2 by and Jeconi37. Joice Tanggan-Paler 28, Downloaded 30, 30, 31, Compute the(jjstanggan@usm.edu.ph) quartile deviation. 2 2 80 22 lOMoARcPSD|18274273 In interpreting the quartile deviation of any distribution of scores, the size of the value is always the indicator. That is, if the value of the quartile deviation is high, the test scores in the distribution can be interpreted as “heterogeneous” or the scores are more scattered away from the mean; if the value of the quartile deviation is low, the scores are said to be “homogeneous” or less scattered around the mean. The interpretation of the quartile deviation result can be best achieved when comparison between two quartile deviation values of any two distributions is considered. Thus, between the distributions of scores in Statistics having a Q.D. of 4.5 and Educational Psychology, Q.D. = 6, the scores in Statistics can be interpreted as less scattered around the mean (homogeneous), while scores of students in Educational Psychology are more distributed away from the mean. 81 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Example 3: The frequency distribution of 40 students in Assessment of Learning are shown below. Calculate the quartile deviation. Class Interval 70 - 74 65 - 69 60 - 64 55 - 59 50 - 54 45 - 49 40 - 44 35 - 39 30 - 34 25 - 29 f 2 2 3 2 8 9 2 4 5 3 n = 40 Solution: n = 40 k=1 nk nk (40)(1) 40F 4 4 4 Q41 LQ1 f Q1 Q1 i mQ 5 11 L 34 Ff 82 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 401 4 34.5 4 83 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 10 34.5 4 2 34.5 4 84 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 34.5 1 Q1 34.5 2.5 2.3.5 The Average Deviation The average deviation (A.D.) is a measure of absolute dispersion that is affected by every individual score. It is the mean of the absolute deviations of the individual scores from the mean of all the scores. A large average deviation would mean that a set of scores is widely dispersed about the mean, while a small average deviation would imply that the set of scores is closer 85 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 to the mean. where: A.D. = average deviation Ʃ = symbol for “summation” n = total number of scores X = individual scores Steps in determining the average deviation: 1. Compute the mean from the given scores. X X X 2. Subtract the mean from the individual scores to get the deviation. That is, . 3. Get the sum of the deviation regardless of signs and divide it by (n-1), where n is the total number of scores. The quotient is the average deviation. 86 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Example 1: The raw scores of eight students in Statistics are given as follows: 17, 17, 26, 28, 30, 30, 31, and 37. Compute the average deviation. X X X Solution: 17 -10 17 -10 26 -1 28 1 30 3 30 3 31 4 37 10 ƩX=216 X X A.D. 42 X 42 42 57 . 3 X 7 8 A . D . 9 8 A.D. 7.1 n 1 For the scores organized in the form of frequency distribution, the average deviation is computed as follows: where: A.D = average deviation Ʃ = symbol for “summation” fi = frequency of the ith class interval n = total number of scores Xi = midpoint of the ith class interval X 240 2 9 The computed average deviation (A.D.) of scores in Statistics is 6 while test scores in Psychology is 7.17. This can be interpreted as the scores in Statistics are less dispersed about the mean while the scores in Psychology are more dispersed around the mean. X In other words, the scores in Statistics having an A.D. of 6 are closely distributed near the mean (homogeneous) while the scores in Psychology having an A.D. of 7.17 are dispersed away from the mean (heterogeneous). n X A.D. X X n n 1 87 216 27 8 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 The steps in determining the average deviation from frequency distribution are as follows: 1. Find the mean of the frequency distribution. 2. Get the midpoint of each class interval. 3. Subtract the mean from the midpoint of each class interval to get the deviations and then, take their absolute values. 4. Multiply the frequency of each class f i X i X interval to the corresponding absolute deviation to get . 5. Get the sum of Step 4 and then divide it by (n - 1), where n is the total number of frequencies. The quotient is the average deviation. Example 1. Below is a frequency distribution of test scores of 40 students in Assessment of Learning. Calculate the average deviation. Class Interval 70 - 74 65 - 69 60 - 64 55 - 59 50 - 54 45 - 49 40 - 44 35 - 39 30 - 34 25 - 29 fi 2 2 3 2 8 9 2 4 5 3 n = 40 Solution: Table ____ Calculation of Average Deviation from Frequency Distribution Of the Sample Test Scores of 40 Students in Assessment of Student Learning 88 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) i Class Interval fi Xi lOMoARcPSD|18274273 fiXi fX X X i i X 70 - 74 65 - 69 60 - 64 55 - 59 50 - 54 45 - 49 40 - 44 35 - 39 30 - 34 25 - 29 2 2 3 2 8 9 72 67 62 57 52 47 144 134 186 114 416 423 2 4 5 3 n = 40 42 37 32 27 84 148 160 81 ƩfiXi= 1,890 24.75 19.75 14.75 9.75 4.75 -0.25 -5.25 49.5 39.5 44.25 19.5 38 -2.25 -10.5 -10.25 -15.25 -20.25 -41 -76.25 -60.75 f i X i X 38 89 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Solving for the mean value: X fX f A.D. Xi X n i 1 1,890 40 381.5 38 40 1 3 2.3.6 Variance and Standard Deviation Standard deviation is the most important measure of variation or dispersion. It is the average distance of all the scores that deviates from the mean value. It shows variation about the mean. It is also known as the square root of the variance. Variance is one of the most important measures of variability or dispersion. It shows variation about the mean. Population Variance Sample Variance Steps in Solving Variance of Ungrouped Data 1. Solve the mean value 2. Subtract the mean value from each score. 3. Square the difference between the mean and each score. 4. Find the sum pf step 4. 5. Solve for the population variance or sample variance using the formula of ungrouped data. Population Standard Deviation Deviation Sample Standard 90 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Steps in Solving Standard Deviation of Ungrouped Data 1. Solve for the mean value. 2. Subtract the mean value from each score. 3. Square the difference between the mean and each score. 4. Find the sum of step 4. 5. Solve for the population standards deviation or sample standard deviation using formula of ungrouped data. the Note: If the variance is already solved, take the square root of the variance to get the value of the standard deviation. Example: Below are the scores of 10 students in Mathematics quiz consists of 20 items. Compute the population and sample variance and population and sample standard deviation. Solution: 91 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) xx XX lOMoARcPSD|18274273 x 6 8 9 10 13 15 16 16 17 20 6 - 13 = -7 8 - 13 = -5 9 - 13 = -4 10 - 13 = -3 13 - 13 = 0 15 - 13 = 2 16 - 13 = 3 16 - 13 = 3 17 - 13 = 4 (-7)2 = 49 (-5)2 = 25 (-4)2 = 16 (-3)2 = 9 (0)2 = 0 (2)2 = 4 (3)2 = 9 (3)2 = 9 (4)2 = 16 20 13 = 7 (7)2 = 49 x 13 x 130 x X X n 10 2 92 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Population Variance Sample Variance 93 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 X x X 186 N1 186 10 s 2 2 10 9 94 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 s 20 18.6 186 X 186 x s N 10 4 . 3 s 4 . 5 n 1 18 10 9 X 22 2.3.7 Relative Measures of Variation Coefficient of Variation shows a variation relative to the mean. It is used to compare two or more groups of distribution of scores. Usually expressed in percent, the smaller the value of the coefficient of variation, the more homogeneous the scores are. On the other hand, the higher the value of the coefficient of variation, the more dispersed the scores are in that particular distribution. The formula in computing the coefficient of variation is, Example: Find the coefficient of variation of the given data below. 95 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Section A 10 10 10 14 14 16 17 18 18 19 19 20 Section B 10 13 15 15 15 15 16 16 16 16 17 20 Section C 10 10 11 11 12 12 12 15 17 20 20 20 x 17 18 Solution: ss 243..04 35 75 CV x 100 x 100 CVCBA 100 x 14 17 15 33 15 42x n = 12 n = 12 n = 12 CVC 28.51% CV 24 . 32 15 33 A B X 14 15.1 43 2.4 96 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Measures of Relative Positions An individual score has meaning only in relation to the rest of the scores. Thus, to interpret a score, we have to use the entire distribution as basis for interpreting individual scores. We learned that the median is that point in the distribution below which lie 50% of the scores. In exactly the same manner, we calculate the values on the scale below which lie a certain percentage of the scores. These values are called quantiles. The value that divide the distribution into 100 equal parts are called percentiles. Thus, Px = xth percentile is the value on the scale which lie x% of the scores. Examples: P90 = the 90th percentile value is the value in the distribution below which lie 90% of all the the scores In a class consisting of 50 pupils, a pupil whose final grade corresponds to P90 is said to belong to the upper 10% of the entire pupils in the class. This also means that his grade is better than 90% (50) = 45 pupils in the class. P10 = the 10th percentile value is the value below which lie 10% of all the scores in the distribution. P50 = the 50th percentile value below which lie 50% of all the other scores in the distribution. Thus, P50 is the same as the median. Other Quantiles Deciles - values on the scale that divide the distribution into ten equal parts. D1 - the first decile = the value on the scale below which lie 10% of the scores in the distribution D5 - fifth decile = P50 = Median D9 - 9th decile = P90 Quartiles - values on the scale that divide the distribution into four equal parts. Q1 - first quartile = P25 = the value on the scale below which lie 25% of the scores in the distribution. Thus, 75% of all the scores are higher than Q1. Q2 = D5 = P50 = Median Q3 = P75 97 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Computation of Quantiles for Ungrouped Data Steps: 1. Arrange the data in ascending order. 2. To determine the location of Px, we first get x% of (n+1) rounded to the next whole number if the result is not a whole number. Example 1. Find Q1 and Q3 for the following data: 95 81 59 68 100 71 88 100 94 87 Solution: 59 65 67 68 71 85 87 88 91 92 92 75 67 85 79 65 93 72 83 91 72 75 79 81 83 93 94 95 100 100 To find the Q1 which is the same as P25, we get 25%(21) = 0.25 x 21 = 5.25 Hence, Q1 is the 6th score or Q1 = 72. Similarly, to find Q3, we get 75%(20+1) = 0.75 x 21 = 15.75. Thus Q3 is the 16th score or Q3 = 93. Instead of rounding the value to the next whole number, we can get a more accurate value of quantiles through interpolation. For instance, since 25% (21) = 0.25 x 21 = 5.25, this means that Q1 is the score that is 1/4 of the way from the 5th and the 6th score. To get Q1, we add to the 5th score 1/4 of the difference between the 6th and the 5th score. Thus, Q1 = 71 + 0.25(72 - 71) + 0.25 = 71.25 Example 2. Find P11 and P93 for the data given above. Solution: Since x = 11, we get 11%(20+1) = 0.11x 21 = 2.31. The value 2.31 suggests that P11 is a value that is 0.31 of the way from the 2 nd score to the third score. To get P11, we got 0.31 of the difference between the 2 nd and 3rd score and add the result to the 2nd score. Thus we have, 0.31 (67 - 65) = 0.31 (2) = 0.62 And since the 2nd score is 65, we have P11 = 65 + 0.62 = 65.62 Similarly, 93%(20+1) = 0.93 x 21 = 19.53. P93 is the score that is 0.53 of the way from the 19th score to the 20th score. Thus, P93 = 100 + 0.53 (100-100) = 100 + 0 = 100 Computation of Quantiles for Grouped Data 98 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 The computation of quantiles for grouped data is similar to the computation of the median (P50) for grouped data. The formula for finding the median is given by Example 1. Find a) Q1 and b) Q3 for the data given below: Class Interval f <cf 95 - 99 1 30 90 - 94 4 29 85 - 89 8 25 80 84 10 17 Since Px is defined as the value below which lie x% of the total number of 75 - 79 4 7 cases, we can revised the above formula by merely changing to x% (n). Thus 70 - 74 3 3 30 where: LL = the true limit of the class interval containing Px Solution: Fb = the <cf below the interval containing Px a) Since Q1 = Pof weinterval first getcontaining 25%(n) to 25, the f = frequency Pxdetermine the interval containing Q n = 1.number of cases = 0.25 x 30 = 7.5. We next look at the <cf column. Since 7.5 is i =25%(30) class size between 7 and 17, we identify the interval 80 - 84 as containing P25. Thus, LL = 79.5 ; Fb = 7; f = 10; i=5 Therefore, x7 %( n ) F . 5 7 P LL x 79.5 5f.5 0 10 22 . 5 17 x %( n ) F 84 . 5 79 .5 Px 84 LL x 10 f 88 2 27 79 . 5 84 . 5 P 79 . 7 1 8 99 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) = 79 5 + 0 25 lOMoARcPSD|18274273 Assessment Directions: Answer the following. Show all pertinent solutions. 1. Find the mean, median, and mode/modes of each of the following sets of data: a. 103, 234, 156, 365, 234, 268, 333, 103, 256, 365 b. 18, 24, 25, 16, 35, 21, 24, 33, 34, 25, 45,33,28, 17, 18, 16, 21, 45 2.Find the range, average deviation, variance, and standard deviation of the following sets of data: a. 70, 65, 69, 73, 90, 87, 81, 89. b. 24, 27, 32, 29, 31, 35, 27, 32, 23, 25, 30, 24. 3.The salaries of all the 130 employees of a company are tabulated in a frequency distribution as shown below Salaries (in thousand pesos) Number of Workers 33 - 36 4 29 - 32 10 100 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 25 - 28 12 21 - 24 24 17 - 20 38 13 - 16 18 9 - 12 15 5-8 6 1-4 3 Find the range, average deviation, variance, and standard deviation. 5. The results of the midterm examination in Differential Calculus of BS Math Junior students were taken and are presented in a frequency distribution. Find the mean, median, and mode. Class Interval f 94- 99 2 88- 93 7 82 - 87 19 76- 81 8 70- 75 10 64- 69 28 58- 63 37 52- 57 19 46- 51 8 40- 45 1 6. The test scores of 18 students in Analytic Geometry and Calculus I are as follows: 27, 48, 33, 39, 52, 25, 50, 47, 42, 32, 21, 28, 42, 45, 55, 20, 37, and 38. Determine the following: a. Q1 b. P68 c. D6 7. The table below gives the age distribution of 100 individuals living in the vicinity of Escolta. Age Frequency 55 - 59 2 50 - 54 5 45 - 49 10 40 - 44 12 35 - 39 15 30 - 34 16 101 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 Solve for the following: a. P85 25 - 29 13 20 - 24 10 15 - 19 4 10 - 14 4 b. Q3 d. D3 Note: WRITE YOUR ANSWERS on A SHORT BOND PAPER. Compile your exercises/assessments and placed it in a short FOLDER (not sliding folder) labelled with your NAME, STUDENT NUMBER, COURSE and SECTION. References: Buendicho, Flordeliza C. (2013). Assessment of Student Learning I. Manila, Philippines: REX Book Store Christian Brothers University (2016). Wrting perfect learning outcomes. Available online: https://www.cbu.edu/assests/2091/writing_perfect_learning_outcomes.pdf Department Order No. 73, series of 2012 - Guidelines on the Assessment and Rating of Learning Outcomes under the K to 12 Basic Education Curriculum. Available online: http://www.deped. gov.ph/wp-content/uploads/2018/07/DO_s2012_73.pdf Garcia, Carlito D. (2013). Measuring and Evaluating Learning Outcomes: A Textbook in Assessment of Learning 1 & 2 2nd edition. Mandaluyong City, Philippines: Books Atbp. Publishing Corp Krathwohl, D. R. (2002). A revision of Bloom’s taxonomy: An Overview. Theory into practice, 41(4), 212-218. Retrieved from https://cmapspublic2.ihmc.us/rid=1Q2PTM7HL26LTFBX-9YN8/Krathwohl%202002.pdf Navarro, Rosita L., et.al. (2019). Assessment of Learning 4th edition. Manila, Philippines: LORIMAR Publishing, Inc.. https://www.statisticshowto.com/probability-and-statistics/coefficient-of-determination-r-squared/ https://www.statisticshowto.com/inter-rater-reliability/ https://chfasoa.uni.edu/reliabilityandvalidity.htm Prepared by: (SGD) MARIA MILAGROS D. DAIZ Asso Prof I Approved by: (SGD) ALVIN B. LACABA, Ph.D. College Dean MERRY CHRISTMAS 102 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph) lOMoARcPSD|18274273 and A PROSPEROUS NEW YEAR... KEEP SAFE... 103 Downloaded by Jeconi Joice Tanggan-Paler (jjstanggan@usm.edu.ph)