is a guess that something is happening or there is a change. It’s what you’re trying to prove. For example, if you want to test if sending text reminders helps patients come to appointments, it would be:

"Text reminders increase appointment attendance."

means numbers that can be measured and have decimal points.

Plain examples:

• A person’s weight (like 150.5 pounds)

• Blood pressure (like 120.8 mmHg)

• Temperature (like 98.6°F)

It’s called “continuous” because the numbers can go on without stopping—there are always values between any two numbers.

applies to data made up of names, labels, or categories. There’s no way to rank or order these categories from smallest to largest.

For example, if you're looking at types of t-shirts—like polka dot or solid color—you’re just sorting them into groups. One type isn't more or less than the other. This is a clear example of nominal data.

is the whole group you want to study. It includes every person or item that fits what you're looking at—nothing is left out.

Plain example:

If you're studying pregnant women with high blood pressure in Horry County, it would be all of those women, not just a few.

If a child has 0, 2, or 4 teddy bears, that’s ratio data. You can say one child has twice as many as another, and having zero means they don’t have any. That’s why teddy bear count is a ratio level example.

means the numbers can be put in order, you can compare differences and ratios, and zero means none.

is a number that describes a group of data collected from a sample.

Plain example:

 If you survey 50 patients and find the average age is 28, that number (28) is this because it describes the sample group.

means putting people or items into groups with similar traits that could affect the results, so the experiment is more fair and accurate.

Plain example:

If you separate people into three age groups before testing a new prenatal education method, that’s blocking. Each group is tested separately to see how age might affect the outcome.

is when you choose people or items that are easy to reach or readily available, instead of picking them randomly.

Plain example:

If you stand outside your clinic and ask the first 10 patients you see to take a survey, that’s convenience sampling—because it’s based on who’s nearby, not a fair or random selection.

is a type of line graph that shows how often data values occur. It’s made by plotting points above each class midpoint (the middle value of each group), then connecting the dots with straight lines.

Plain example:

If you’re tracking the number of preterm births in different age groups, you can use this to see patterns or trends across the age ranges.

is a statement that says nothing is happening—no effect, no difference, no change.

Plain example:

If you're testing whether text reminders help pregnant patients keep their appointments,it would be:
"Text reminders do not change appointment attendance."

It’s what you try to disprove with your data.

is descriptive and tells you about the characteristics of something. It is usually expressed in words, not numbers.

Plain example:

Hair color (brown, blonde), patient satisfaction (happy, unhappy), or type of prenatal care received (group care, one-on-one) are all this—they describe, not measure.

are numbers used to summarize or describe a set of data.

Plain example:

If you collect data on pregnant patients’ ages and then calculate the average age, highest age, or most common age, you’re using this to explain what the data looks like.

are used to make predictions or draw conclusions about a larger group (population) based on data from a smaller group (sample).

Plain example:

If you survey 100 pregnant women and find that most prefer text reminders, you might conclude that most women in the whole clinic population prefer them too. 

is a small part of a population that is studied to learn about the whole group.

Plain example:

If you want to know how all pregnant women in your clinic feel about prenatal classes, but you only ask 50 of them, those 50 women are your ___

is the study of collecting, organizing, analyzing, and interpreting data to help make decisions or understand trends.

Plain example:

If you track how many OB patients missed appointments last month, then calculate the average, percent, or pattern—you’re using it to understand the data.

census

is when you collect data from every single person or item in the entire population.

Plain example:

If you ask every OB patient at your clinic about their prenatal care experience.—because you’re including everyone, not just a sample.

are facts or information collected for analysis. They can be numbers, words, measurements, or observations.

Plain example:

Tracking the ages, blood pressures, and delivery types of OB patients gives you ____ to study patterns and improve care.

A histogram

is a type of bar graph that shows how often data falls into different ranges or intervals.

Plain example:

If you record the ages of pregnant patients and group them into ranges (like 15–19, 20–24, 25–29), this would show how many patients fall into each age group using bars.

, researchers simply watch and record what happens without changing anything or giving any treatment.

Plain example:

If you track how often pregnant patients attend appointments based on their distance from the clinic—without changing anything—you’re doing an _______. You're just observing, not interfering.

is numerical data—it deals with numbers and can be counted or measured.

Plain example:

A pregnant patient’s age, weight, or number of prenatal visits are all this because they are expressed in numbers.

is a way to check if your results are meaningful or if they happened just by chance.

Plain example:

If you want to see whether text reminders improve prenatal appointment attendance, this helps you decide if the difference you see is real or just random luck. It tells you if your results are strong enough to reject the null hypothesis.

is when you divide a population into smaller groups based on a shared characteristic, then randomly pick people from each group.

Plain example:

If you separate OB patients by age groups (like teens, 20s, 30s, 40+), then randomly choose some from each group to survey. It helps make sure all age groups are fairly represented.

is when you divide the population into groups usually based on location or natural grouping—then randomly select entire groups to study.

Plain example:

If your OB patients are spread across 5 clinics, and you randomly pick 2 clinics and survey every patient in those 2 clinics

is made up of countable numbers—you can list them out, and they usually don’t include decimals.

Plain example:

The number of prenatal visits a patient has (like 5, 8, or 10 visits) is this because you can count each one and you can’t have half a visit.

is a statement or guess that you can test with data. It usually predicts a relationship between two things.

Plain example:

You might have a _____ that sending text reminders will help more OB patients keep their appointments. You can test this by collecting and comparing data.

The ordinal level

of measurement is used for data that can be put in order, but the differences between values aren't exact or meaningful.

Plain example:

Pain ratings like "mild," "moderate," and "severe" are this. You can rank them, but you can't say exactly how much worse "severe" is than "moderate."

A random sample

is when every person or item in a population has an equal chance of being chosen.

Plain example:

If you put all OB patients’ names in a hat and draw 50 at random to take a survey everyone had the same chance of being picked.

is when you select members from a population using a fixed, regular pattern—like every 5th or 10th person.

Plain example:

If you have a list of OB patients and you pick every 3rd patient on the list to complete a survey,

happens when a third factor affects both the treatment and the outcome, making it hard to tell what’s really causing the result.

Plain example:

If you’re studying whether prenatal vitamins reduce low birth weight, but income level also affects both vitamin use and birth outcomes, income is this because It confuses the results.

An experiment is double-blind when neither the participants nor the researchers know who is getting the treatment or the placebo.

Plain example:

If you're testing a new prenatal supplement, and neither the patients nor the doctors know who got the real supplement and who got a fake one, it’s a _______. This helps prevent bias in the results.

is the process of assigning people or items by chance to different groups in a study.

Plain example: If you're testing two types of prenatal education, and you randomly assign patients to either group, that’s _____. It helps keep the groups fair and reduces bias.

experiment is one where the participants don’t know if they’re getting the treatment or a placebo, but the researchers do.

Plain example:

If you give some OB patients a real prenatal supplement and others a fake one—but only the researchers know who got what. This helps reduce participant bias.

is a number calculated from your data that helps you decide whether to reject the null hypothesis in a hypothesis test.

Plain example:

If you're testing whether text reminders improve appointment attendance, the ____ helps show how different the results are between the reminder group and the no-reminder group. The bigger the difference, the more likely it is that the result is not due to chance.