Biostats Chapters 1-7 EXAM

2026 Fall Dr. Mous- Abou Mamadou

Population

Everyone we want information about

Sample

people who were actually selected/ responded from the population

Statistic

Number calculated from a sample

Parameter

Number describing an entire population.

Simple random

where every person or item in a total population has an exact and equal chance of being chosen

Stratified

Divide into groups, take random samples from each group.

Cluster

Randomly select an entire group/ cluster

Systematic

Every 5th, 10th, 40th, etc. Item is selected from a list after a random start.

Convenience

Whoever is easiest to get (First 20 people in a room)

Multistage

Sampling method that combines multiple sampling techniques, involving selection at various stages.

Categorical

Labels/groups

Quantitative

Numbers where mathematical calculations make sense

Discrete

Countable numbers/values: 1, 2, 3. . .

Continuous

Measurements: height, weight, time, temperature, etc.

Ordinal

Categories with an order (mild, medium, hot spice levels)

Quantitative continuous

data that can take any value within a range, used for measurements such as height and weight.

Ratio

A type of quantitative data that has a true zero point, allowing for the comparison of absolute magnitudes, such as weight, height, and temperature in Kelvin.

Cross-sectional

A study design that examines data at a single point in time, often used to assess the prevalence of outcomes or characteristics within a population.

Case-control

A study design that compares individuals with a specific condition or outcome to those without, looking backward in time to identify possible risk factors or exposures.

Descriptive

statistics that summarize and describe the features of a dataset, such as measures of central tendency and variability.

Inferential

statistics that use a random sample of data to make inferences about a larger population, often involving hypothesis testing and confidence intervals.

Blocks

A method used in experimental design to control for the effects of certain variables by grouping subjects with similar characteristics, thereby reducing variability within treatment groups.

Randomized block

Randomize within the group/ block.

double- blinding

A technique in clinical trials where neither the participants nor the researchers know who is receiving the treatment or the placebo, minimizing bias in the results.

Single- blinding

A method in which only the participants are unaware of whether they are receiving the treatment or placebo, while the researchers know the assignments.

Census

The process of systematically collecting, analyzing, and recording information about the members of a population, often conducted at regular intervals.

Relative frequency

frequency/total

Frequency

Total X relative frequency

Gap in distribution

If numbers go from small to large back to small and then repeats this pattern( 2 bell shapes) This could mean that there are two populations.

Bar graph

Represents each category by a bar whose height Is the count, or the percent, for the category. The bars are separated by blank space and may be arranged in any order.

Pie chart

Shows each category as a slice of a single circle, the size of the slice being the percent of the whole that the category represents.

Bell-shaped

Highest frequency occurs in the middle, pretty symmetrical and looks like a usual histogram.

Uniform

A distribution where all categories have the same frequency, creating a flat shape on the graph.

Skewed to the right

A distribution where most values are concentrated on the left side, with a long tail extending to the right.

Skewed to the left

A distribution where most values are concentrated on the right side, with a long tail extending to the left.

Normal distribution

The points lie reasonably close to a straight line, with no systematic pattern away from it.

Not normal

The points do not lie close to a straight line, or they show a systematic pattern that is not a straight line.

Percentiles

The values that divide a data set into 100 equal parts, where each percentile represents 1% of the data. They are a position, not a diagnosis.

Interquartile range

Q3-Q1

Five number summary

A summary that includes the minimum, first quartile (Q1), median, third quartile (Q3), and maximum values of a data set.

IQR rule

Used to identify outliers by determining data points that fall BELOW Q1 - 1.5 X IQR (lower fence) or ABOVE Q3 + 1.5 X IQR (upper fence)

Standard score/ Z- score

A statistical measure that indicates how many standard deviations an element is from the mean of a data set. Z-scores can be positive or negative, indicating whether the value is above or below the mean.

Blood type of patient

Qualitative- labels, type but doesn’t effect traits

Number of emergency room admissions in a night

Quantitative discrete- describes amount, but its just a number (count)

Systolic blood pressure

Quantitative continuous- describes number measurements

Patient identification number

Qualitative- just a label

Ratio

The values can be ordered, differences are meaningful, and there is a natural zero. Ratios of values are therefore meaningful as well. Examples include heights, weights, and distances.

Time from admission to first treatment, in minutes

Quantitative continuous- measurement

Number of prescriptions a patient currently takes

Qualitative discrete- just a count

Patient satisfaction rated as poor, fair, good, or excellent

Ordinal

Resting heart rate, in beats per minute

Ratio

Type of insurance a patient carries

Nominal

Year in which a patient was diagnosed

Interval

Volume of blood drawn, in millimeters

Ratio

Descriptive Statistics

gathers, sorts, summarizes, and displays the data. The main purpose is to describe the data and present the information in a convenient form.

Inferential data

Involves using descriptive statistics to estimate population parameters.

Observational study

Looks at data that already exists. It observes variables in their natural settings without manipulation for causal relationships.

Retrospective/ case control study

Data are collected from a past time period by going back in time.

Lurking variable

A variable that is not included in the study but may influence the relationship between the variables being studied, potentially confounding results.

Confounding variables

Variables that are related to both the dependent and independent variables, potentially leading to incorrect conclusions about their relationship.