Data lecture
Download as PPTX, PDF2 likes1,943 views
The document defines data as facts or information used to draw conclusions. It describes two main types of data: quantitative and qualitative. Quantitative data can be numerical and classified as discrete (integer values) or continuous (any value within a range). Qualitative data groups objects into categories based on traits and can be nominal (unordered categories) or ordinal (naturally ordered categories). The document also discusses levels of measurement for data as nominal, ordinal, interval, or ratio scales, and how the appropriate scale depends on the variable's properties. Understanding data types and measurement is important for correctly analyzing and interpreting data.
Data lecture
- 2. DEFINITION Data can be defined as a collection of facts or information from which conclusions may be drawn.
- 3. TYPES OF DATA QUANTITATIVE QUALITATIVE
- 4. QUANTITATIVE DATA • Quantitative or numerical data arise when the observations are counts or measurements. • The resulting data are a set of numbers Eg: • Cholesterol level in mg/dl • Height in cms • Blood sugar in mg/dl • Number of children in family (numbers) • Number of diarrheal episodes (numbers)
- 6. Quantitative data . . . • Discrete: The data are said to be discrete if the measurements are integers • Only whole numbers are possible • There are gaps between numbers • Eg: • Number of children in family • Number of cigarettes smoked per day
- 7. • Continuous: if the measurements can take on any value, usually within some range • Theoretically, no gaps between possible values • Eg: • Cholesterol (mg/dl) • Weight (Kgs) • Blood sugar fasting (mg/dl) • Most biological variables are continuous. Quantitative data . . .
- 8. QUALITATIVE DATA • The objects being studied are grouped into categories based on some qualitative trait. • Data that is not given numerically • Eg: • Religion • Blood pressure levels • Smoking status
- 10. •Nominal data • A type of categorical data in which objects fall into unordered categories. • Nominal data have no order and thus only gives names or labels to various categories. Eg: • Color of eyes • Religion • Gender Qualitative data . . .
- 11. Ordinal data •A type of categorical data in which natural order is important. •Eg: • socio-economic status – High, Medium, Low • stage of cancer – 1,2,3,4 • exam results (grade) – C, C+, B, B+, A, A+ Qualitative data . . .
- 12. Assessment Identify the type of data Gender Exact age Number of fillings in tooth Self reported level of pain Stages of cancer Height (in cms) Qualitative nominal Quantitative discrete Quantitative discrete Qualitative ordinal Qualitative ordinal Quantitative continuous QUANTITATIVE OR QUALITATIVE DISCRETE /CONTINUOUS OR NOMINAL/ORDINAL
- 13. DATA MEASUREMENT
- 14. Measurement • Process of assigning numbers to various aspects of objects/events according to a rule. • The aim of measurement is to provide accurate, objective, sensitive and communicable descriptions of event.
- 15. Levels of measurement • Proposed by S. S. Stevens (1946) • Each scale of measurement satisfies atleast one of the four properties: • Identity – each value has a meaning • Magnitude – values have an ordered relationship to other • Equal intervals – values are spaced equally • Absolute zero – scale has a true zero point NOMINAL ORDINAL INTERVAL RATIO
- 16. Nominal scale • This scale only satisfies the identity property. • Values assigned to variables represent a descriptive category, but have no inherent numerical value with respect to magnitude. • They are usually coded • Eg: Gender, religion, political affiliation
- 17. Ordinal scale • Has both identity and magnitude • Ordinal data codes can be ranked • Distance between codes is not meaningful • Eg: Results of a running race, Staging of cancer
- 18. Interval scale • Has the properties of identity, magnitude, and equal intervals. • Data can not only be ranked, but also have meaningful intervals between scale points • Eg: Temperature in celsius and farhenheit
- 19. Ratio • Satisfies all properties of measurement • Eg: Weight of an object, temperature in kelvin • Minimum value is zero (cannot be negative)
- 21. Which scale is appropriate? • To classify and categorize subjects – NOMINAL • To rank people according to any characteristic – ORDINAL • To quantify a trait where distance between rank is same – INTERVAL • To quantify a trait which has an absolute zero - RATIO
- 22. Assessment Ordinal Identify scale of measurement Tooth mobility Temperature in kelvin Height Temperature in celsius Blood group Number in sports jersey Horse racing Time Ratio Ratio Interval Nominal Nominal Ordinal Ratio
- 23. WHY DATA IS IMPORTANT ? Qualitative and quantitative data behave differently and therefore studied differently The level of measurement helps you decide how to interpret data from that variable The level of measurement determines the type of statistics that is appropriate for its analysis Statistical analysis should be planned along with data collection procedures so that they match