Data Collection Methods (Statistics)
Data collection is the process of gathering information for analysis and decision-making.
1. Primary Data Collection
Data collected first-hand by the researcher.
• Surveys / questionnaires
• Interviews
• Observations
• Experiments
Example: A teacher collecting students’ marks through a class test.
2. Secondary Data Collection
Data collected from existing sources.
• Books
• Government reports
• Websites
• Research papers
Example: Using Kenya National Bureau of Statistics (KNBS) population data.
Sampling Methods (Overview)
Sampling is selecting a subset of a population to represent the whole.
• Simple Random Sampling
• Systematic Sampling
• Cluster Sampling
• Stratified Sampling
Stratified Sampling (Important Topic)
Definition
Stratified sampling is a method where the population is divided into homogeneous groups
(strata), and samples are taken from each group proportionally.
Why use it?
• Ensures fair representation of all groups
• Reduces bias
• Improves accuracy
Steps in Stratified Sampling
1. Divide population into strata (groups)
2. Determine proportion of each group
3. Take random samples from each stratum
Formula (Proportional Allocation)
𝑁𝑖
𝑛𝑖 = ×𝑛
𝑁
Where:
• 𝑛𝑖 = sample from stratum
• 𝑁𝑖 = population in stratum
• 𝑁= total population
• 𝑛= total sample size
Solved Example 1
Question:
A school has:
• Form 1: 200 students
• Form 2: 300 students
• Form 3: 500 students
A sample of 100 students is required using stratified sampling. Find how many students to select
from each form.
Solution:
Total population:
𝑁 = 200 + 300 + 500 = 1000
Form 1:
200
𝑛1 = × 100 = 20
1000
Form 2:
300
𝑛2 = × 100 = 30
1000
Form 3:
500
𝑛3 = × 100 = 50
1000
Final Answer:
• Form 1 → 20 students
• Form 2 → 30 students
• Form 3 → 50 students
Solved Example 2
Question:
A company has 80 male and 120 female employees. A sample of 50 is required.
Solution:
Total:
𝑁 = 80 + 120 = 200
Males:
80
𝑛𝑚 = × 50 = 20
200
Females:
120
𝑛𝑓 = × 50 = 30
200
Final Answer:
• Males = 20
• Females = 30