Quantitative Research Methods Overview

Flashcards on Quantitative Research Methods Overview

Correlation

Two variables are related but one does not necessarily cause the other.

Causation

One variable directly influences another, demonstrated via controlled studies.

Confounding Variable

A hidden factor that explains the apparent relationship.

Descriptive Research

Observes and describes phenomena (no causal claims).

Correlational Research

Examines relationships between variables.

Experimental Research

Involves manipulation of the IV, random assignment, and control groups—can establish causation.

Quasi-Experimental Research

Lacks full control or random assignment—limited causal claims.

Hypothesis

A testable statement predicting a relationship between variables.

Independent Variable (IV)

What the researcher manipulates or categorizes.

Dependent Variable (DV)

What the researcher measures.

Operationalization

Translating abstract concepts into measurable indicators.

Conceptualization

Defining all the variables/concepts in the hypothesis.

Sampling

Selecting a subset of a population to make generalizations.

Sampling Distribution

Distribution of a statistic across all possible samples.

Standard Error

Indicates the precision of a sample statistic.

Simple Random Sampling (SRS)

Equal chance for every individual.

Stratified Sampling

Population divided into subgroups, then sampled.

Cluster Sampling

Entire clusters are randomly selected.

Systematic Sampling

Select every kth individual after a random start.

Selection Bias

The sample doesn't represent the population due to how participants are chosen.

Undercoverage

Some groups are left out of the sampling frame entirely.

Nonresponse

When selected individuals don't participate.

Voluntary Response

When only those with strong opinions choose to participate.

Convenience Sampling

Comes from selecting participants who are easiest to reach.

Survivorship Bias

Results from analyzing only 'successful' cases and ignoring failures.

Measurement Bias

When data collection methods favor certain outcomes or mislead participants.

Survey Design Principle: Avoid jargon

Ensure the language is easy to understand for a broad audience.

Survey Design Principle: Avoid Leading Questions

Make sure your questions don't imply a preferred answer.

Survey Design Principle: Tailor questions

Ask questions that are relevant to your target audience.

Survey Design Principle: Avoid skewed options

Make sure the scale is balanced, with an equal number of positive and negative responses.

Survey Design Principle: Be Specific

Be specific about the type of information you're looking for to get accurate and usable responses.

Survey Design Principle: Mutually Exclusive and Exhaustive

Ensure that response options don't overlap, and provide enough options to cover all possible responses.

Pilot Testing (Pre-Testing)

Before launching your survey on a larger scale, always conduct a pilot test with a small group of people from your target population.

Survey Distribution Method

Different methods of distributing the survey (e.g., email, in-person, online platforms, social media) may affect how respondents engage with the survey and their answers.

Mean

Average.

Median

Middle value.

Mode

Most frequent value.

Range

Max - Min.

Variance

Average squared deviation from the mean.

Standard Deviation (SD)

Spread around the mean.

Interquartile Range (IQR)

Middle 50% (Q3 - Q1).

Descriptive Statistics Importance

Provide a quick summary of large datasets, identify patterns, trends, and anomalies, help inform decision-making before moving to inferential statistics, serve as a foundation for hypothesis testing and data analysis.

Normal Distribution

Symmetrical bell curve.

Right-Skewed Distribution

Long tail to the right.

Left-Skewed Distribution

Long tail to the left.

Uniform Distribution

All values are equally likely.

Bimodal Distribution

Two peaks.

Exponential Distribution

Many small values, few large ones.

Log-normal Distribution

Skewed, log transformation normalizes.

Data Visualization Purpose

To detect patterns, identify anomalies, and communicate data effectively.

Histogram

A common visual for distributions.

Bar Chart

A common visual for comparisons.

Scatterplot

A common visual for relationships.

Pie Chart

A common visual for compositions.

Hypothesis Testing Steps

1. State H€ (null) and H• (alternative). 2. Set ± (ypically 0.05). 3. Collect data. 4. Perform the t-test. 5. Calculate the p-value. 6. Make a decision: Reject or fail to reject H€.

T-test

A tool we use to compare the averages (means) of two groups to see if they are different in a meaningful way.

p-value

Tells you the probability that the observed difference is due to chance.

One-Sample T-Test

Compare sample to known value.

Two-Sample (Independent) T-Test

Compare two groups.

Paired T-Test

Compare before-and-after for one group.

One-tailed Test

Predicts direction.

Two-tailed Test

Any difference.

Validity

Are you measuring what you intend to?

Reliability

Are your measurements consistent?

Triangulation

Using multiple methods, data sources, or theories to enhance reliability and depth.

Benefits of Triangulation

Boosts credibility, reduces bias, exposes contradictions, deepens insight.