Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
19 views

BSGPT Notes

Uploaded by

Tushar Mehta
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
19 views

BSGPT Notes

Uploaded by

Tushar Mehta
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Sure, let's clarify cluster sampling and stratified random sampling with examples:

### Cluster Sampling


**Definition**: Cluster sampling involves dividing the population into clusters (usually based
on geography or other natural groupings) and then randomly selecting entire clusters. All
individuals within the chosen clusters are sampled.

**Example**:
Imagine you want to survey the academic performance of high school students in a large city.
You divide the city into different neighborhoods (clusters). Instead of selecting students from the
entire city, you randomly select a few neighborhoods and survey all the students within those
neighborhoods.

**Steps**:
1. **Divide the population into clusters**: Neighborhoods in a city.
2. **Randomly select clusters**: Randomly choose a few neighborhoods.
3. **Survey all individuals within the selected clusters**: Survey all high school students in
those selected neighborhoods.

### Stratified Random Sampling


**Definition**: Stratified random sampling involves dividing the population into strata (distinct
subgroups) based on specific characteristics. Then, a random sample is taken from each stratum.

**Example**:
Suppose you want to study the dietary habits of adults in a country. You divide the population
into strata based on age groups (e.g., 18-30, 31-50, 51-70, 71+). Then, you randomly select
individuals from each age group to ensure representation from all age categories.

**Steps**:
1. **Divide the population into strata**: Age groups (18-30, 31-50, 51-70, 71+).
2. **Randomly sample from each stratum**: Randomly select individuals from each age group.

### Comparison

**Cluster Sampling**:
- Used when the population is naturally divided into clusters.
- More cost-effective and practical for large, geographically dispersed populations.
- Example: Surveying students from selected neighborhoods in a city.

**Stratified Random Sampling**:


- Ensures representation from all subgroups (strata) in the population.
- More precise and reduces sampling error by considering specific characteristics.
- Example: Surveying adults from different age groups to study dietary habits.

In summary, cluster sampling is useful for geographically dispersed populations and practical
constraints, while stratified random sampling is ideal for ensuring all subgroups are
proportionally represented.

-Sure! Let's go through a real-life example with data to illustrate the concept of an estimator in
statistics.

### Scenario

Suppose we want to estimate the average amount of time people spend on social media per day
in a particular city. To do this, we conduct a survey and collect data from a random sample of
residents.

### Data Collection


We survey 10 residents and record the following amounts of time (in minutes) they spend on
social media per day:

\[ \text{Sample data: } [120, 150, 80, 200, 90, 160, 110, 140, 130, 100] \]

### Estimator: Sample Mean

To estimate the population mean (average time spent on social media per day by all residents in
the city), we use the sample mean as our estimator.

#### Calculation of Sample Mean

The sample mean \( \bar{x} \) is calculated as:

\[ \bar{x} = \frac{1}{n} \sum_{i=1}^n x_i \]

where \( n \) is the sample size, and \( x_i \) represents each observation in the sample.

For our data:

\[ n = 10 \]
\[ \sum_{i=1}^{10} x_i = 120 + 150 + 80 + 200 + 90 + 160 + 110 + 140 + 130 + 100 = 1280 \]

So,

\[ \bar{x} = \frac{1280}{10} = 128 \text{ minutes} \]


The sample mean \( \bar{x} = 128 \) minutes is our estimate for the average time spent on social
media per day by residents in the city.

### Properties of the Estimator

Let's discuss some properties of the sample mean as an estimator for the population mean:

1. **Unbiasedness**: The sample mean is an unbiased estimator of the population mean. This
means that, on average, the sample mean equals the population mean. If we were to take many
samples and calculate their means, the average of those sample means would be the true
population mean.

2. **Consistency**: As the sample size increases, the sample mean becomes closer to the
population mean. With a larger sample, our estimate becomes more reliable.

3. **Efficiency**: Among all unbiased estimators of the population mean, the sample mean has
the smallest variance, making it the most efficient.

### Estimator: Sample Proportion

Suppose we also want to estimate the proportion of residents who spend more than 100 minutes
per day on social media. In our sample, we count how many residents spend more than 100
minutes per day.

#### Calculation of Sample Proportion

The sample proportion \( \hat{p} \) is calculated as:

\[ \hat{p} = \frac{x}{n} \]
where \( x \) is the number of successes (residents who spend more than 100 minutes per day),
and \( n \) is the sample size.

From our data:

\[ \text{Residents spending more than 100 minutes: } [120, 150, 200, 160, 110, 140, 130] \]

Number of successes \( x = 7 \)

So,

\[ \hat{p} = \frac{7}{10} = 0.70 \]

The sample proportion \( \hat{p} = 0.70 \) is our estimate for the proportion of residents who
spend more than 100 minutes per day on social media.

### Summary

- **Estimator**: A rule or function used to estimate a population parameter based on sample


data.
- **Sample Mean (\( \bar{x} \))**: An estimator for the population mean. In our example, \( \
bar{x} = 128 \) minutes is the estimate for the average time spent on social media.
- **Sample Proportion (\( \hat{p} \))**: An estimator for the population proportion. In our
example, \( \hat{p} = 0.70 \) is the estimate for the proportion of residents spending more than
100 minutes per day on social media.

By using these estimators, we can make informed inferences about the population based on our
sample data.3

You might also like