Page 1

• Data analysis includes the attribute salary

  • Values for salary: 30, 36, 47, 50, 52, 52, 56, 60, 63, 70, 70, 110

• Mean: 58

• Median: 54

• Mode: 52

• Midrange: 140 - 30 = 110

• First Quartile (Q1): 48.5

• Third Quartile (Q3): 66

• Boxplot: 30, 48.5, 54, 66.5

Page 3

• Data collection is gathering information about a subject

• Importance of complete and ethical data collection for accurate analysis

Page 4

• Primary data: collected firsthand, costly, through observations, surveys, etc.

• Secondary data: already collected, affordable, from various sources, may not meet current research purpose

Page 6

• Data collection methods include surveys with unbiased questions

• Types of surveys: online, face-to-face

• Questionnaire administration methods: mailed, collective

Page 8

• Questionnaire types: closed-ended, open-ended

• Forms of questions in a questionnaire

• Advantages and disadvantages of questionnaires

Page 10

• Data collection methods: Transactional Tracking, Interviews, Focus Groups

• Transactional Tracking for targeted marketing decisions

• Interviews and Focus Groups for qualitative and quantitative data

Page 11

• Data collection methods: Observation, Online Tracking, Forms

• Observation for real-time user interaction insights

• Online Tracking for behavioral data gathering

Page 12

• Observational methods involve looking and listening carefully

• Types of observation: Structured, Unstructured, Participant, Non-participant

Page 13

• Structured Observation: planned in advance, useful for large-scale studies

• Example: patient reaction to hospital in different phases

• Advantages and disadvantages of Structured Observation

Page 15

• Unstructured Observation: no advance design, observer decides on the spot

• Example: observing a child playing with a new toy

• Strengths and weaknesses of Unstructured Observation

Page 16

• Participant Observation

  • Observer is actively present in the observed setting.

  • Advantage: Allows for clarification and interaction with people.

  • Disadvantage: Inexperienced observer may miss relevance and influence behavior.

Page 17

• Non-participant Observation

  • Observer remains detached and only observes.

  • Strength: Collects information without being influenced.

  • Example: Plainclothes policemen at public events.

Page 18

• Sampling

  • Primary data collection when secondary data are unavailable.

  • Population Method (Census Method) vs. Sample Method.

  • Population classified as Finite or Infinite, Real or Hypothetical.

Page 19

• Classification of Population

  • Finite Population: Countable elements.

  • Infinite Population: Uncountable elements.

  • Real vs. Hypothetical Population.

Page 20

• Merits and Demerits of Census Method

  • Data from every unit of the population.

  • Representative and reliable data.

  • Intensive study possible.

  • Time-consuming and costly.

  • Not suitable for all research types.

Page 21

• Sampling Population

  • Learning about the population through a sample.

  • Steps in sampling framework for making inferences.

Page 22

• Sampling Frame

  • Certain groups of interest within the population.

  • Relationship between Population, Sampling Frame, and Sample.

Page 23

• Methods of Sampling

  • Statistical data collection through various methods.

  • Includes Convenience, Simple Random Sampling, Cluster Sampling, etc.

Page 24

• Probability Sampling Methods

  • Every member has a chance of selection.

  • Used in quantitative research to eliminate bias.

Page 25

• Simple Random Sampling

  • Every item in the population has an equal chance of selection.

  • Steps for minimizing biases in the sampling process.

Page 26

• Simple Random Sampling Example

  • Steps for obtaining a simple random sample for outcomes in trauma hospitals.

Page 27

• Cluster Sampling

  • Dividing the population into clusters based on demographic parameters.

  • Random selection of clusters for effective survey results.

Systematic Sampling

• Definition: Choosing sample members at regular intervals

• Process: Selection of a starting point, sample size, and regular intervals

  • Example: Selecting every 10th individual from a population of 5000 to form a sample of 500

Stratified Random Sampling

• Definition: Dividing the population into non-overlapping groups

• Purpose: Representing the entire population accurately

  • Example: Creating strata based on annual income divisions for targeted analysis

Probability Sampling Advantages

• Benefits:

  • Reduce sample bias

  • Ensure diverse population representation

  • Create an accurate sample for well-defined data collection

Non-Probability Sampling

• Definition: Sample selection based on researcher's discretion

• Usage: Preliminary research stages or cost constraints

  • Output may lead to skewed results in some cases

Convenience Sampling

• Dependence: Ease of access to subjects

• Example: Surveying customers at a mall or passers-by on a busy street

  • Commonly used in resource-limited situations like startups or NGOs

Judgmental or Purposive Sampling

• Definition: Samples formed based on researcher's discretion

• Criteria: Selection based on the purpose of the study and target audience understanding

Snowball Sampling

• Usage: When subjects are difficult to trace

• Example: Applied in sensitive topics like HIV/AIDS surveys

Quota Sampling

• Selection: Based on pre-set standards

• Purpose: Rapid method of collecting samples with specific attributes

Advantages of Non-Probability Sampling

• Usage:

  • Create hypotheses with limited prior information

  • Conduct exploratory research or pilot studies

  • Address budget and time constraints for preliminary data collection

Differences between Probability and Non-Probability Sampling

• Probability Sampling:

  • Randomly selected samples

  • Used to reduce sampling bias

• Non-Probability Sampling:

  • Subjective judgement of researchers

  • Useful in specific environments with similar characteristics among