Slide 1: Introduction
"Hello everyone! Today, we’re discussing populations, samples, and sampling distributions,
essential concepts in statistics that allow us to make inferences about large groups based on
smaller samples. By understanding sampling, we can collect representative data efficiently and
accurately."
Slide 2: Population vs. Sample
"In statistics, the population refers to the entire group of individuals or observations of interest.
The sample is a smaller group selected from this population, representing its characteristics. For
example, if our population is all high school students in a city, a sample could be 200 students
randomly chosen from different schools in that city. This method saves time and resources
compared to studying every individual in the population."
Slide 3: Sampling Methods
"There are two main types of sampling methods: Probability Sampling and Non-Probability
Sampling.
Probability Sampling allows for random selection, giving every individual an equal
chance to be part of the sample. It’s ideal for making statistically reliable inferences.
Non-Probability Sampling is based on ease and accessibility, often used in exploratory
research.
Each has specific types suited to different scenarios, which we’ll discuss next."
Slide 4: Probability Sampling Types
"In probability sampling, there are four main types:
1. Simple Random Sampling: Here, each individual has an equal chance. For example, if
we want a sample of 100 from 1,000 students, we might randomly select names from a
list.
2. Systematic Sampling: In this method, individuals are selected at regular intervals. For
example, selecting every 10th student from a list of 1,000.
3. Stratified Sampling: This involves dividing the population into subgroups and sampling
each group. If studying mental health among youths, we could divide by age group, then
randomly sample within each group.
4. Cluster Sampling: We divide the population into clusters and randomly select some
clusters for study. For instance, if studying youth in different schools, we might randomly
select five schools and survey all students within those schools."
Slide 5: Non-Probability Sampling Types
"Non-probability sampling includes five main types:
1. Convenience Sampling: Selecting individuals who are easy to access, such as students
attending a program regularly.
2. Voluntary Response Sampling: Participants self-select, like in a survey where people
choose to respond.
3. Purposive Sampling: Targeted selection based on specific criteria. For instance,
selecting only homeless youth aged 16-18 for a mental health study.
4. Snowball Sampling: Participants recruit others, useful in hard-to-reach populations, like
homeless youth.
5. Quota Sampling: Setting quotas to ensure representation of specific characteristics, such
as 50 boys and 50 girls from different backgrounds."
Slide 6: Sampling Distribution
"A sampling distribution is the probability distribution of a statistic (like a mean) obtained
through repeated sampling. For example, if we repeatedly sample groups of 100 people and
calculate each group's average income, the distribution of these averages is our sampling
distribution. It helps us estimate the population’s characteristics accurately."
Slide 7: Step-by-Step Sampling Distribution Creation
"Creating a sampling distribution involves these steps:
1. Define Sample Size: Let’s sample 100 individuals from a population of 1,000.
2. Stratify the Sample by Gender: If we have 400 males and 600 females, we could
sample proportionally—40 males and 60 females.
3. Random Sampling within Strata: Use random selection to choose individuals from
each group.
4. Calculate the Mean Income: After sampling, let’s say the average income is $28,000.
5. Repeat Sampling and Calculate Mean: By repeating and averaging, we obtain multiple
means to form our sampling distribution."
Slide 8: Conclusion
"To conclude, sampling and sampling distributions enable us to gather insights about populations
cost-effectively. By carefully choosing our sampling method and understanding sampling
distributions, we can draw valid conclusions that inform research and decision-making."
Slide 9: Application in Social Work
"In social work, sampling methods are invaluable. For instance, stratified sampling and sex-
disaggregated data help agencies study gender-specific issues. A social work agency, for
example, could analyze how intimate partner violence affects different genders, creating targeted
programs based on data from proportionate samples of men, women, and non-binary
individuals."
Slide 1: Introduction
"Hello everyone! Today, we’re talking about populations, samples, and sampling
distributions. These are important ideas in statistics, helping us study a large group by only
looking at a smaller part of it. Understanding sampling lets us collect useful data without
spending tons of time and resources."
Slide 2: Population vs. Sample
"A population is the entire group of people or items we’re interested in studying. For example,
if we want to study all high school students in a city, they’re the population.
A sample is just a smaller group we pick from that population to study. So, if we choose 200
students from different schools, that’s our sample. This smaller group should represent the larger
group, so we don’t need to study everyone to learn something meaningful."
Slide 3: Sampling Methods
"There are two main ways to get a sample:
1. Probability Sampling: This is when we randomly choose people, so everyone has a fair
chance to be selected. This method helps us get results that represent the whole
population.
2. Non-Probability Sampling: Here, we choose people based on convenience, meaning we
pick whoever is easiest to reach. This is faster but may not represent everyone equally."
Slide 4: Types of Probability Sampling
"Probability sampling includes different ways to randomly select people. Let’s go over each one:
1. Simple Random Sampling: Here, every person has an equal chance of being chosen.
Imagine writing everyone’s name on slips of paper, mixing them up, and drawing names.
o Example: Out of 1,000 students, we pick 100 names randomly.
2. Systematic Sampling: We pick people at regular intervals. If we list 1,000 students, we
could choose every 10th person until we have 100 people.
3. Stratified Sampling: We split the population into groups, or strata, based on certain
traits (like age or gender) and then sample from each group. This helps make sure all
groups are represented.
o Example: If we want to study students’ mental health by age, we might group
them by age range and pick from each group.
4. Cluster Sampling: We split the population into clusters that each look like a small
version of the population, then randomly pick whole clusters instead of individuals.
o Example: To study high school students, we could choose five schools and
survey all students in those schools."
Slide 5: Types of Non-Probability Sampling
"In non-probability sampling, we don’t pick randomly. We often choose people based on who’s
easiest to reach:
1. Convenience Sampling: We choose people who are easy to access.
o Example: Surveying students who come to an after-school program because
they’re already there.
2. Voluntary Response Sampling: We let people volunteer to be part of the study. This can
be biased since only certain people may want to participate.
o Example: Putting up flyers for a survey and only getting responses from those
interested.
3. Purposive Sampling: We specifically pick people who meet certain criteria for our
study.
o Example: Choosing only homeless youth aged 16-18 to learn about their
experiences.
4. Snowball Sampling: We start with a few people, and they refer others to us, helping us
reach more people over time.
o Example: Interviewing homeless youth and asking them to introduce us to others
in similar situations.
5. Quota Sampling: We set quotas to make sure we have enough people from each group
we want to study.
o Example: Making sure we have 50 boys and 50 girls from different backgrounds
for a balanced view."
Slide 6: What is a Sampling Distribution?
"A sampling distribution is like a collection of averages. Imagine you take multiple samples
and calculate the average for each. When you plot these averages, you get a sampling
distribution.
Example: If we take 100 samples of 100 people each and calculate the average income in
each sample, the plot of those averages shows the sampling distribution. This helps us
estimate the overall average for the whole population."
Slide 7: How to Create a Sampling Distribution (Step-by-Step)
"To create a sampling distribution, here’s what you do:
1. Choose Sample Size: Decide how many people you’ll sample. Let’s pick 100 people
from a population of 1,000.
2. Divide by Groups: If we want to see results by gender, we split our population (say 400
men and 600 women) and sample 40 men and 60 women.
3. Random Selection: Within each group, pick randomly.
4. Calculate the Average: For each sample, calculate the average (e.g., income).
5. Repeat: Do this multiple times, each time getting a new sample and calculating a new
average.
6. Create the Distribution: With all these averages, we can create a sampling distribution."
Slide 8: Conclusion
"In summary, sampling lets us understand a big group by studying a smaller one. Sampling
distributions help us make good guesses about the whole population. Choosing the right method
helps us get accurate, useful results in our research."
Slide 9: Application in Social Work
"In social work, sampling is very helpful. For example, if we want to study how domestic
violence affects people of different genders, we can use stratified sampling to make sure men,
women, and non-binary people are all represented. Then, we can see the different ways they’re
affected and create targeted support programs."
