CLINICAL STATS 1 Flashcards
(38 cards)
Why is it important to learn clinical statistics?
To develop research skills, interpret data effectively, and make independent judgments in clinical practice.
What are the main types of qualitative (categorical) data?
- Binary – Two categories (e.g. Dead/Alive, Yes/No, Disease/No disease)
- Nominal – Named, unordered categories (e.g. Blood type, Occupation)
- Ordinal – Ordered categories (e.g. Cancer stages, Education level, Socioeconomic status)
Give examples of binary categorical data.
Dead/Alive
Male/Female
Treatment/Placebo
Disease/No disease
Exposed/Unexposed
Caries (Yes/No)
Heads/Tails
Give examples of nominal categorical data.
Blood type
Marital status
Hair colour
Country of residence
Occupation
Give examples of ordinal categorical data.
Stages of cancer
Socioeconomic status
Education level
Rating on a scale (e.g., 1–5)
Age categories
Rank order (e.g., race position)
What are the two main types of quantitative (numerical) data?
Discrete – Countable values (e.g. number of teeth, number of patients)
Continuous – Can take any value within a range (e.g. age, BP, time, speed)
Classify the following data types:
Age
Age last birthday
Number of teeth
Pocket depth
Socioeconomic status
Has patient visited dentist in last year
Hardness of filling material
Colour of filling
Type of radiograph
Calcium:phosphorus ratio
Severity of gum disease
Age – Continuous
Age last birthday – Discrete
Number of teeth – Discrete
Pocket depth – Discrete
Socioeconomic status – Ordinal
Visited dentist (Y/N) – Binary
Hardness – Can be Nominal, Ordinal, or Numerical depending on how it’s recorded
Colour of filling – Nominal
Type of radiograph – Nominal
Calcium:phosphorus ratio – Continuous
Severity of gum disease – Ordinal
❓ What is the difference between descriptive and inferential statistics?
👉
Descriptive statistics: Organise, summarise, and present data (graphs + numbers)
Inferential statistics: Interpret data, make predictions or conclusions from sample to population
What are common graphical techniques for different data types?
Categorical data → Bar charts, Frequency plots
Continuous data → Histograms, Boxplots
What do boxplots show?
Minimum
Q1 (25th percentile)
Median (Q2)
Q3 (75th percentile)
Maximum
Outliers
Also shows distribution shape and spread.
❓ What does it mean if a distribution is left or right skewed?
Left skewed: Tail on the left, most values are high, median closer to Q3
Right skewed: Tail on the right, most values are low, median closer to Q1
Symmetric: Mean ≈ Median, bell-shaped
What are the three measures of central tendency?
Mean: Average (sensitive to outliers)
Median: Middle value (not affected by outliers)
Mode: Most frequent value (can be used for categorical or numerical data)
When is the median preferred over the mean?
When there are extreme values or outliers
Because the median is more robust
What are the main measures of dispersion/variation
Range = Max - Min
Interquartile Range (IQR) = Q3 - Q1
Variance = Average of squared deviations
Standard deviation = √Variance
Coefficient of variation = SD ÷ Mean
What are quartiles?
👉
Q1: 25% of observations below it
Q2: Median (50%)
Q3: 75% of observations below it
How do you calculate Interquartile Range (IQR)?
IQR=Q3−Q1
Shows spread of middle 50% of the data.
What is a deviation in statistics?
The difference between a data point and the mean:
Deviation = Value − Mean
Deviation=Value−Mean
Shows how far a point is from the average.
Why do we square deviations when calculating variance?
👉
To eliminate negatives
So that deviations don’t cancel each other out
Gives greater weight to values far from the mean
What is sample variance?
The average of squared deviations from the mean:
What is sample standard deviation?
The square root of the variance:
Most commonly used measure of spread
Same units as original data
Small SD = data close to mean
Large SD = data more spread out
Why is the standard deviation useful?
Gives a clear measure of variation around the mean
Helps you understand how spread out the data is
Commonly used in clinical and research data analysis
what does it mean if a data is left skewed
what does it mean if a data is right skewed
What is the first thing you should do when you get new data?
Plot your data!
