Types of Statistics.pptx
- 1. Types of Statistics Descriptive Statistics Inferential Statistics Describe something, e.g., group of students, characteristics of certain products etc. (height/weight/marks) To get some inferences or drawing conclusions on the basis of descriptive statistics is called inferential statistics i.e. drawing conclusions about a large group of individuals based on the subset of the large group Methods-Central tendency, dispersion, skewness etc. Estimation, Hypothesis Testing, Regression, ANOVA etc. Collect data- e.g. Survey Summarize/Present- e.g., Line Graphs and Tables Analyze and Describe- e.g. Sample mean Estimation- e.g., Estimate the population mean weight using the sample mean weight Hypothesis testing- e.g., Test the claim that the population mean is 110 pounds.
- 2. What is better sampling or complete enumeration? Its totally depend on the size of population. For small population a complete enumeration can be done. For large population, sample is better • Less time • Less expensive • Efficient for making relevant decision on time • If the item/product is destructive in nature
- 3. Why to collect data? A marketing research analyst needs to assess the effectiveness of a new television advertisement A pharmaceutical manufacture needs to determine whether a new drug is more effective than the current one in use An operations manager wants to monitor the manufacturing process to find out whether the quality of the products being manufactured is according to standard of the company An auditor wants to review the financial transactions of a company in order to determine if the company is in compliance with the generally accepted accounting principles.
- 4. Who collects data? • Teachers • Counsellors • Consultants • Managers • Administrators • Industrialists • Parents, and • Students, need to seek information to perform their jobs
- 5. Types of variables Categorical /qualitative/non-numerical variables have values that can only be placed into categories say “yes” or “no”, Male or Female, • E.g., heavy coffee drinkers, Excellent people Quantitative/numerical variables have values that represent quantities Data Quantitative Discrete Continuous Qualitative Examples: Number of children Complaints per day (counted items) Examples: Marital Status Political party Race etc (defined categories) Examples: Weight Voltage (measured characteristics)
- 6. Scales of Measurements • Nominal Categorical Scales • Ordinal • Interval • Ratio Numerical Scales Nominal: Data are labels or names used to identify an attribute of the element. A numeric label or numeric code may be used. • Example-Students of a university are classified by the school in which they are enrolled using a non numeric label like Business, Humanities, Education etc. Alternatively, a numeric code could be used for the school variable (e.g., 1 for Business, 2 for Humanities, 3 for Education and so on)
- 7. Ordinal: The data have the properties of nominal data and order or rank of the data is meaningful. Used to measure qualitative phenomenon that exists with varying degrees such as intelligence, beauty, satisfaction etc. • A non numeric label or numeric code may be used e.g. product 1 is better than product 2 in some sense. Interval: The data have the property of ordinal data and the interval between observations is expressed in terms of a fixed unit of measure. E.g. • Example-Melvyn has a SAT score of 1205, while Kevin has SAT score of 1100, and so Melvyn score 105 points more than Kevin Strongly disagree(SDA) disagree (DA) neutral (N) agree (A) strongly agree(SA) 1 2 3 4 5
- 8. Ratio: The data have the properties of interval data and the ratio of two values is meaningful • Variables such as distance, height, weight, income, time etc use the ratio scale. • This scale must contain a zero value, nothing exists for the variable at zero point. • Melvyn’s college report shows 36 credit hours earned, while Kevin’s record shows 72 credit hours earned, means Kevin has twice as many credit hours than Melvyn.
- 9. Qualitative Data • Labels or names used to identify attribute of each elements • Often referred to as categorical data • Use either the nominal or ordinal scale of measure • Can be either numeric or non numeric • Appropriate statistical analyses are limited. Quantitative Data • Quantitative data represent how many or how much; • Discrete, if counting how many, and • Continuous, if measuring how much • Quantitative data are always numeric • Ordinary arithmetic operations are meaningful for quantitative data
- 10. Cross Sectional Data • Cross sectional Data are collected at the same or approximately same point of time • Example: Data detailing the number of building permits issued in the month of May 2020 in each of the districts of India. Time Series data • Data collected over several time periods • Example-Data detailing the number of building permits issued in month of May from 2010 to 2020. or say number of building permits in last 60 months etc.
- 11. Statistical Studies • In Experimental Studies the variables of interest are first identified. Then one or more factors are controlled so that data can be obtained how the factors influenced the variables. • In Observational(non experimental) studies no attempt is made to control or influence the variables-e.g. survey Data Acquisition Considerations Time Requirement Information may be no longer useful by the time it is available Searching for information can be time consuming Cost of Acquisition Organisations often charge for information even when it is not their primary business activity Data Errors Using any data that happens to be available or that were acquired with little care can lead to poor or misleading information
- 12. Descriptive Statistics • Descriptive Statistics are the tabular, graphical and numerical methods used to summarize the data Example: Hudson Auto Repair The manager of the Hudson would like to have a better understanding of the cost of parts used in engine tune ups performed in the shop. He examined 50 customer invoices for tune ups. The cost of parts rounded to the nearest Rupees are listed
- 13. Descriptive Statistics 91 78 93 57 75 52 99 80 97 62 71 69 72 89 66 75 89 75 72 76 104 74 62 68 97 105 77 65 80 109 85 97 88 68 83 68 71 69 67 74 62 82 98 101 79 105 79 69 62 73 Tabular Summary: Frequency and Percentage Frequency Parts cost (Rs) Parts Frequency Percent Frequency 50-59 2 4 60-69 13 26 70-79 16 32 80-89 7 14 90-99 7 14 100-109 5 10 50 100 4% 26% 32% 14% 14% 10% % Frequency 50-59 60-69 70-79 80-89 90-99 100-109
- 14. Numerical Descriptive Statistics • The most common descriptive statistics is the mean or the average • Hudson’s average cost of parts based on 50 tune ups studied is Rs 79, the mean. • We infer using a sample of 50 cars.
Editor's Notes
- #3: Destructive-Lets say you have a firm for manufacturing bricks and you are supplying them to some supplier/contractor, one cannot crush all the bricks to test the strength of the bricks.
- #8: Ordinal example-Suppose in a class there are 50 students and appeared in 5 papers of exam each of 100 marks. The highest marks obtained in 495 by some student X. Thus X is ranked as number 1 and so on. So the last student will have rank 50. By this way, we order the students and have the ordinal scale The draw back of this is that, we don’t know how better or what is difference in rank 30 and rank 10 students as we just have ranking not the actual marks Interval-We have the distance or difference between ordinal data. E.g. distance between SA and A is 1 and that for SA and DA is 3.
- #10: E.G we can not find mean of qualitative data, such as red and blue
- #14: From chart, one can conclude that the average cost should be somewhere between 70-79