Measure & scaling
Download as PPTX, PDF0 likes307 views
The document discusses various concepts related to measurement and scaling in research. It defines measurement as assigning numbers or symbols to characteristics of objects based on rules. Scaling is locating measured objects on a continuum according to these rules. There are four main types of measurement scales discussed - nominal, ordinal, interval, and ratio scales - which differ in the meanings assigned to numbers. The document also covers topics like variables, constructs, indexes, types of scales like comparative and non-comparative, and decisions to consider when constructing scales.
Measure & scaling
- 2. The Learners Serial Name Roll 01 Atiullah Akond 21-070 02 Ripon Miya 21-077 03 Umar Khaled 21-098 04 Md. Sakil Ahmed 21-106 05 Al Mamun 21-127 06 Md. Abdur Rahim 21-202
- 3. Measurements & Scaling Measurement Measurement refers to assigning numbers and symbols to the characteristics of the object as per the specified rules. It’s actually the use of a yardstick to determine or judge some features of a physical or abstract objects or concepts (eg. weight, height , motivation, love etc.).
- 4. Measurements & Scaling (cont.) Scaling the procedure of measuring and assigning the objects to the numbers according to the specified rules. Locating the measured objects on the continuum.
- 5. Measurements & Scaling (cont.) Example Consider a scale from 1 to 10 for locating consumer characteristics (preference for the product). Each respondent is assigned a number from 1 to 10 denoting the degree of unfavourableness for the product, with ‘1’ indicating extremely unfavorable and ’10’ indicating extremely favorable. Here, the Measurement is... the process of assigning the actual number from 1 to 10 to each respondent. And the Scaling is… placing respondents on a continuum with respect to their preference for the product.
- 6. Concepts To understand and communicate information about objects and events, there must be a common ground on which to do it. Concepts serve this purpose. A concept is a generally accepted collection of meanings or characteristics associated with certain events, objects, conditions, situations, and behaviors. For example, we see a man passing and identify that he is running, walking, skipping, crawling, or hopping. These movements all represent concepts.
- 7. Constructs Constructs are mental abstractions that we used to express the ideas, people, organizations, events and/objects/things. Examples: morality, depression, air pollution, height, secularism etc. constructs are mental abstractions because seldom are constructs directly observable (e.g., we cannot directly observe depression, even though we may associate depression with signs such as a person that often cries, engages in self-harm, has mood swings, and so forth).
- 8. Variables When we operationalized a concept, we are creating variables. Variables can be defined as any characteristics that varies (meaning it must have at least two variables) Examples: Height ( participant or subject variable) Stress ( response variable) Age ( participant or subject variable)
- 9. Levels of Measurement Scale Four Types Nominal scale Ordinal scale Interval scale Ratio scale
- 10. Measurement means- The process of applying numbers to objects according to a set of rules. WHY SCALING- Measurement scales are used to categorize and/or quantify variables.
- 11. NOMINAL SCALE Assign numbers to objects where different number indicates different objects. No real meanings Just differentiate between objects Example- -Football players uniform number The number provides no insights into the players position. Generally shown in pie chart.
- 12. ORDINAL SCALE Assign numbers to objects like nominal but the numbers also have meaningful order. Numbers indicate placement and order. Example- In a race - 1st, 2nd, 3rd and so on. Generally shown in Bar diagram.
- 13. INTERVAL SCALE Numbers have order like ordinal but there are also equal intervals between adjacent categories. Example- -Temperature in degrees Fahrenheit – The difference between 78 degrees and 79 degrees is the same as 45 degrees and 46 degrees. Generally shown in Histogram.
- 14. RATIO SCALE Ratio is meaningful like interval. There is a true zero point.(Absence) Regression analysis in thousands , in millions.
- 15. DIFFERENCE BETWEEN INTERVAL VS ORDINAL INTERVAL VS RATIO NOMINAL VS INTERVAL, ORDINAL, RATIO.
- 16. Mathematical and Statistical Analysis of Scales 1. Discrete Measures 2. Continuous Measures
- 17. Discrete Measures -Measures that take only one of a finite number of values. -Include any yes-or-no response, matching, color choice etc. -Do not represent intensity of measures, only membership. -Nominal and Ordinal Scales are discrete measures. Example: Student politics should be banned from Dhaka University Campus- Disagree Neutral Agree
- 18. Continuous Measures - measures that reflect the intensity of a concept by assigning values that take on any value along some scale range. - ratio measures are continuous measures. Example Strongly Disagre e Disagree Neutral Agree Strongly Agree Political turmoil is the main hindrance for launching a business in Bangladesh. 1 2 3 4 5
- 19. Index Measures - Indexes - Composites
- 20. Index Measure -assigns a value based on how much of the concept being measured is associated with an observation. -are often formed by putting several variables together. Example A researcher is interested in measuring job satisfaction and one of the key variables is job-related depression. Questions: When I think about myself and my job, I feel downhearted and blue. When I’m at work, I often get tired for no reason. When I’m at work, I often find myself restless and can’t keep still. When at work, I am more irritable than usual.
- 21. Composite Measure - assigns a value based on a mathematical derivation of multiple variables. Questions Strongly Disagree Disagree Neutral Agree Strongly Agree When I think about myself and my job, I feel downhearted and blue. 1 2 3 4 5 When I’m at work, I often get tired for no reason. 1 2 3 4 5 When I’m at work, I often find myself restless and can’t keep still. 1 2 3 4 5 When at work, I am more irritable than usual. 1 2 3 4 5
- 22. Comparative Scale A type of scale where one object is compared with another and relative measure of performance is obtained.
- 23. Types of Comparative Scaling i. Rank Order Scaling ii. Paired Comparison Scaling iii. Constant Sum Scaling iv. Sorting
- 24. Rank Order Scaling A rank order scale gives the respondent a set of items and ask them to put the items in some form of order. Example: Brand Rank Pepsodent 1 Colgate 2 Whiteplus 3
- 25. Paired Comparison Scaling The paired comparison scaling is a comparative scaling technique wherein the respondent is shown two objects at the same time and is asked to select one according to the defined criteria.
- 26. Example of Paired Comparison 10 pairs of soft drink brand out of 5 brands and respondents are asked to indicate the one they prefer: Brand Coke Sprite Pepsi Mojo Dew No. of time preferre d Coke 0 0 1 0 3 Sprite 1 0 1 0 2 Pepsi 1 1 1 1 0 Mojo 0 0 0 0 4 Dew 1 1 0 1 1 No. of time preferred 3 2 0 4 1 1=column brand is preferred to the row brand 0= row brand is preferred to the column brand
- 27. Constant Sum Scaling Respondents are presented with a list of object and asked to allocate a constant sum of points with respect to some criterion. Example: Allocating 100 points among 4 attributes of Attributes Point Hassle free ride 20 Saving time 30 Reasonable fare 40 Availability 10 Total 100
- 28. Sorting Respondents are required to indicate their attitudes by sorting object with respect to some criterion. Example: suppose the respondents are given 100 motivational statements on individual cards and are asked to place these in 11 piles, ranging from the “most agreed with” to the “least agreed with”. Generally, the most agreed statement is placed on the top while the least agreed statement at the bottom.
- 29. Non-comparative Scales 1) Continuous Rating Scale 2) Itemized Rating Scale Likert Semantic Differential Stapel
- 30. Continuous Rating Scale It’s a scale where respondents rate the objects by placing a mark at the appropriate position on a line that runs from one extreme to another. For example: How would you rate ‘’Bata’’ as a brand? 1) Extremely Favoured ---------------------------------------------------------- Extremely Unfavoured. 2) Extremely Favoured ---------------------------------------------------------- Extremely Unfavoured. 0 10 20 30 40 50 60 70 80 90 100
- 31. Likert Scale It requires the respondents to indicate a degree of agreement or disagreement about a series of statements related to particular object. Strongly agree Strongly Disagree Example: statements Strongly Disagree Disagree Neither disagree nor agree Agree Strongly Agree Advertisements create a sense of deprivation 1 2 3 4 5 Advertisements augment sales revenue 1 2 3 4 5 Advertisements aid to increase market share 1 2 3 4 5 Advertisements create positive perception . 1 2 3 4 5
- 32. Semantic Differential It is a seven point rating scale with end points associated with bipolar labels that have semantic meanings. Here, respondents are asked to rate a products, service or organizations with multi-point questions with bipolar adjectives. Example: If you want to rate Walton BD Ltd. , you may use multi-point questions. 1) Low cost products Unlikely ---:---:---:---:---:---:---:--- Likely 2) How is its service? Unattractive ---:---:---:---:---:---:--- Attractive 3) Customer perception Bad ---:---:---:---:---:---:--- Good
- 33. Stapel Scale It’s a unipolar scale with 10 categories from -5 to +5 without any neutral point. Respondents are asked to indicate how accurately the term (pole) describes the objects. The higher the positive number, the more accurately the term describes the objects. The lower the negative values, the more inaccurately the term describes the object. Example: Rating a bank. +5 +5 +4 +4 +3 +3 +2 +2 +1 +1 Friendly Personnel Lower interest -1 -1 -2 -2 -3 -3 -4 -4 -5 -5
- 34. For well constructing itemized scale six decisions must be made: 1.Number of a scale categories to use: -The greater the number of classes, the more the discrimination among stimulus object is possible. -The more the number of classes, the greater is the problem for respondents to handle. - The appropriate number of classes: 5 -10. Example: 1.Strongly agree 2.Somewhat agree 3.Neither 4.Somewhat disagree 5.Strongly disagree
- 35. 2. Balanced versus unbalanced scale: Balanced scale means: Number of favorable categories =Number of unfavorable categories. Unbalanced scale means: Number of favorable categories ≠ Number of unfavorable categories. Balanced scale Unbalanced scale Extremely good Extremely Good Very good Very Good Good Good Bad Somewhat Good Very bad Bad Extremely bad Very bad
- 36. 3. Odd or even number of categories: In an odd number there is a neutral point in the middle -If there are a lot of possible neutral answers then it should be provided. 4. Forced versus non forced scale: The question is whether there should be any option for no opinion response category. -Depends on the possibility of whether there could be some or more respondents with no opinion.
- 37. 5. Nature and degree of category label: The scales may have verbal labels, numerical labels or may be unlabeled. Example: verbal label Strongly disagree Disagree Neither Agree Strongly agree Example: numerical labels Strongly disagree 1 2 3 4 5 Strongly agree Example: Unlabeled Strongly disagree............. Strongly agree
- 38. 6. Physical form or configuration: There could be a number of options with respect to form of configuration of a scale. -A scale may be presented vertically or horizontally. -Response may be positive negative or both. -There can be number or without number is category may be specified. -There may be box or without box.