Inferential statistics
Download as PPT, PDF10 likes9,779 views
The document discusses inferential statistics and its applications. It defines statistics as dealing with collecting, classifying, presenting, comparing, and interpreting numerical data to make inferences about a population. Inferential statistics help decision makers present information, draw conclusions from samples, seek relationships between variables, and make reliable forecasts. The document also distinguishes between descriptive statistics, parametric inferential statistics that assume normal distributions, and non-parametric inferential statistics that make no distribution assumptions.
Inferential statistics
- 1. Inferential Statistics Applications & Usefulness
- 2. Definitions • Statistics is the science which deals with the methods of collecting, classifying, presenting, comparing and interpreting numerical data collected to have some inference regarding the real aspects. Highlights: (i) Aggregates of facts. (ii) Effected to a marked extent by multiplicity of causes. (iii) Numerically Expressed. (iv) Estimated as per reasonable standards of accuracy. (v) Collected in as systematic manner for a pre- determined purpose.
- 3. Reasons for Learning Statistics It enables the decision-maker to understand how to : (i) present and describe information (data) so as to improve decisions. (ii) draw conclusions about the large population based upon information obtained from samples. (iii) seek out relationship between pair of variables to improve processes. (iv) obtain reliable forecasts of statistical variables of interest.
- 4. Statistical Thinking and Analysis Statistical thinking can be defined as the thought process that focuses on ways to identify, control and reduce variations present in all phenomena. Management Philosophy Statistical Methods Behavioral Tools Quality Improvement Process Model Management Philosophy acts as a guide for laying a solid foundation for total quality improvement efforts. However, Behavioral Tools such as brainstorming, team-building & Group Decision making, & Statistical Methods like tables, control-charts and descriptive statistics are proved to be as pillars for quality improvement.
- 5. Types of Statistical Methods • Descriptive statistics - Graphical Presentations like Bar charts, line , pie charts, frequency distribution. – Measures of Central Tendency ( Mean , Median , Mode). – Measures of Dispersion ( Range, Quartile, Mean Deviation, Standard Deviation). • Inferential statistics - Statistical Methods to estimate the characteristics of the population based on sample results.
- 6. Inferential Statistics • Can be categorized as: - Parametric - Non- Parametric Parametric - Assumed that the drawn sample is normally distributed. - Data collection takes place on an interval or ratio scale. Non-Parametric - Makes no explicit assumption regarding the normality. - Data collection takes place on an nominal or ordinal scale.
- 7. Need of Data • To provide necessary inputs to a given phenomenon or situation under study. • To measure performance in an ongoing process such as production, service and so on. • To enhance the quality of decision-making by enumerating various options. • To satisfy the desire to understand an unknown phenomenon. • To assist in guessing the causes and probable effects of certain characteristics in given situations.
- 8. Types of Data • Categorical – Do you practice Yoga? Yes No • Numerical - Discrete - How many books are there in library? Exact Number - No of Students in the class? (Integer) - Continuous - What is your height? Centimeters or Inches - What is the temperature? Degree or Fahrenheit
- 9. Types of Scales • Nominal Scale • Ordinal Scale • Interval Scale • Ratio Scale
- 10. Nominal Scale • A scale of measurement for a variable that uses a label (or name) to identify an attribute of an element of the data set. e.g. Each of the respondent has to fit into following category: - Indian - Sri Lankan - Nepalese - Bhootanis - Pakistanis - Others Other Examples: Grouping of Individuals or objects. Your gender : Male Female Your place of work : Production Finance Sales
- 11. Ordinal Scale • A scale of measurement for a variable that is used to rank (or order) observations in the data set. e.g. Ranking of the items, say from 10 to 1, depending of their usage. Specifically, if particular system is not used at all in your office, put a less figure against it. IBM/AT Compaq IBM/XT AT&T Apple II Tandy 2000 Macintosh Zenith HCL
- 12. Interval Scale • A scale of measurement for a variable in which the interval between observations is expressed in terms of a fixed standard unit of measurement. e.g. when we measure temperature, the distance from 30-40 is same as distance from 70-80.
- 13. Ratio Scale • A scale of measurement for a variable that has interval which is measurable in standard unit of measurement and a meaningful zero, i.e. the ratio of two values is meaningful.