Making statistics intuitive
Undercoverage bias occurs when the population list from which the researchers select their sample (aka the sampling frame) does not include all population members. When that happens, the sample cannot contain the unlisted individuals, potentially producing a biased sample that doesn’t fully represent the population. [Read more…] about Undercoverage Bias: Definition & Examples
A matched pairs design is an experimental design where researchers match pairs of participants by relevant characteristics. Then the researchers randomly assign one person from each pair to the treatment group and the other to the control group. This type of experiment is also known as a matching pairs design. [Read more…] about Matched Pairs Design: Uses & Examples
Nonresponse bias occurs when people who do not participate in a survey or study have different characteristics or opinions than those who do participate. In this situation, the sample data overrepresent the subpopulations who tend to respond instead of reflecting the whole population. [Read more…] about Nonresponse Bias: Definition & Reducing
The slope intercept form of linear equations is an algebraic representation of straight lines: y = mx + b. [Read more…] about Slope Intercept Form of Linear Equations: A Guide
Population vs sample is a crucial distinction in statistics. Typically, researchers use samples to learn about populations. Let’s explore the differences between these concepts! [Read more…] about Population vs Sample: Uses and Examples
Calculating percentages is a standard mathematical procedure. A percent is a ratio that you write as a fraction of 100. In this article, learn why percentages are crucial summary measures and how to calculate them. [Read more…] about How to Calculate a Percentage
Principal Component Analysis (PCA) takes a large data set with many variables per observation and reduces them to a smaller set of summary indices. These indices retain most of the information in the original set of variables. Analysts refer to these new values as principal components. [Read more…] about Principal Component Analysis Guide & Example
Percent change is the relative difference between an old value and a new value. Positive values represent an increase over time, while negative numbers indicate a reduction.
For example, if the price of a candy bar changes from $1 to $1.10, it’s a 10% increase. [Read more…] about Percent Change: Formula and Calculation Steps
Simpsons Paradox is a statistical phenomenon that occurs when you combine subgroups into one group. The process of aggregating data can cause the apparent direction and strength of the relationship between two variables to change. [Read more…] about Simpsons Paradox Explained
A weighted average is a type of mean that gives differing importance to the values in a dataset. In contrast, the regular average, or arithmetic mean, gives equal weight to all observations. The weighted average is also known as the weighted mean, and I’ll use those terms interchangeably. [Read more…] about Weighted Average: Formula & Calculation Examples
Concurrent validity is the degree to which assessment scores correlate with a criterion variable when researchers measure both variables at approximately the same time (i.e., concurrently). This method validates an assessment instrument by comparing its scores to another test or variable that researchers had validated previously. [Read more…] about Concurrent Validity: Definition, Assessing & Examples
Criterion validity (aka criterion related validity) is the degree to which scores from a construct assessment correlate with a manifestation of that construct in the real world (the criterion). [Read more…] about Criterion Validity: Definition, Assessing & Examples
Predictive validity is the degree to which a test score or construct scale predicts a criterion variable measuring a future outcome, behavior, or performance. Evaluating predictive validity involves assessing the correlation between the pre-test score and the subsequent criterion outcome. [Read more…] about Predictive Validity: Definition, Assessing & Examples
A retrospective study an experimental design that looks back in time and assesses events that have already occurred. The researchers already know the outcome for each subject when the project starts. Instead of recording data going forward as events happen, these studies use participant recollection and data that were previously recorded for reasons not relating to the project. These studies typically don’t follow patients into the future. [Read more…] about Retrospective Study: Definition & Examples
Political polls provide crucial information during elections. When done correctly, small samples can predict the outcomes. We’re approaching election time here in the U.S., and campaigns are switching into high gear along with political polls!
You’d think that conducting a poll is straightforward. You ask a bunch of people who they’ll vote for and count the results, right? But it’s not quite that simple.
For starters, political polls face the same challenges as other polls. However, a poll taken for political reasons also has some unique issues. When pollsters do everything correctly, the small, sampled group accurately reflects the entire population. The trick is to do it correctly!
In this post, learn how statistical concepts apply to political polls and the extra difficulties they face. [Read more…] about Political Polls and Their Challenges
Survivorship bias, or survivor bias, occurs when you tend to assess successful outcomes and disregard failures. This sampling bias paints a rosier picture of reality than is warranted by skewing the mean results upward. [Read more…] about Survivorship Bias: Definition, Examples & Avoiding
Sampling bias in statistics occurs when a sample does not accurately represent the characteristics of the population from which it was drawn. When this bias occurs, sample attributes are systematically different from the actual population values. Hence, sampling bias produces a distorted view of the population. Sampling bias often involves human subjects, but it can also apply to samples of objects and animals. Medical researchers refer to this problem as ascertainment bias. [Read more…] about Sampling Bias: Definition & Examples
Purposive sampling is a non-probability method for obtaining a sample where researchers use their expertise to choose specific participants that will help the study meet its goals. These subjects have particular characteristics that the researchers need to evaluate their research question. In other words, the researchers pick the participants “on purpose.” [Read more…] about Purposive Sampling: Definition & Examples
Snowball sampling is a non-probability method for acquiring a sample that uses participants to recruit additional participants. Researchers call it snowball sampling because if the initial participant recruits two more, and those two recruits each bring in two more, and so on, the number of participants can grow exponentially like a rolling snowball. This method is also known as chain sampling or network sampling. [Read more…] about Snowball Sampling: Definition and Example
Quota sampling is a non-random selection of subjects from population subgroups that the researchers define. Researchers use quota sampling when random sampling isn’t feasible, and they want more control over who they select compared to other non-probability methods, such as convenience sampling. [Read more…] about Quota Sampling: Definition & Examples