Sampling Methods

Simple Random Sample (SRS)

No selection bias, chosen regardless of place

Should produce unbiased results, and each sample has an equal chance of occuring (every result has an equal probability of occuring). But more difficult to access (more itme, money, effort), not pratical for large populations.

Qualitative Data

Unique to population. Descriptive information focused on concepts and characteristcs, rather than numbers and stats. Collected through interviews, focus groups, observations

Quantitative Data

Universal. Information that be measured numerically and factual based.

Reliable data

You can repeat data collection process and obtain similar results

Sufficient data

There is enough data to support conclusions

Discrete Data

Fixed to certain values; no gaps between data value

Continuous data

Not fixed to certain values; can occupy a continuous range

Population

The entire group that you want to draw conclusions about

Stratified Sampling (SRS)

divided into sub groups proportional to their size in the whole population (ex: age group and randomly select based on age group)

Pros: Guaranetes every subgroup is included and reduce sampling bias.
Cons: More technical analysis, effort, and requires detailed population info

Systematic Sampling

- Not random

- Select participants at a regular interval (ex: every 10th person)

Pros: evenly distributed, less manipulation and money

Cons: Big populations effective only, patterns can be predicted which can cause bias, unequal selection possible

Convenience Sampling

Selection by availability

Pro: Less time and effort and money. Immediate daa

Cons: Produces the most bias because limited generalizing, inaccurate representation, researcher bias

Quota Sampling

Divide population into subgroups proportional in size to the whole population (ex: ppopulation 60% male and 40% female than sample size also 60% male, 40% female).

Pros: Representative of subgroups, demographic representation.
Cons: Potential for bias since it’s not random and more complex

Bimodal

2 modes

Percentile

indicating the percentage of the dataset with a lesser value. For example, a data point that falls at the 80th percentile has a value greater than 80 percent of the data points within the dataset.

Variance

measures how spread out or dispersed a set of data points are from their mean (average). Average of the squared differences from the mean. 

Standard deviation

how far individual points in a dataset are dispersed/spread out from the mean of that set.

Bivariate data

data that involves two variables and explores the relationship between them, often visualized using scatter plots