Week 5

Question 1

What is biostatistics?

Answer 1

The application of statistical principles to biological, medical, and public health research to design studies and interpret data.

Question 3

What is the difference between a population and a sample?

Answer 3

A population includes all individuals of interest, while a sample is a smaller group selected from the population to make inferences.

Question 4

Define descriptive vs inferential statistics.

Answer 4

Descriptive: Summarise data (mean, median, SD); Inferential: Draw conclusions about a population using data from a sample.

Question 5

What is a null hypothesis (H₀)?

Answer 5

A statement of no effect or difference (e.g., no difference in treatment outcomes).

Question 6

What is an alternative hypothesis (H₁)?

Answer 6

A statement that suggests there is an effect or difference (e.g., treatment causes improvement).

Question 7

What does a p-value represent?

Answer 7

The probability of observing the data (or more extreme) if the null hypothesis is true.

Question 8

What does it mean when p < 0.05?

Answer 8

It indicates statistically significant evidence against the null hypothesis at the 5% significance level.

Question 9

What is a t-test used for?

Answer 9

Comparing the means of two groups.

Question 10

When is an independent t-test used?

Answer 10

When comparing means of two unrelated groups (e.g., treatment vs control).

Question 11

When is a paired t-test used?

Answer 11

When comparing means from the same group at two time points (e.g., before and after).

Question 12

What is a chi-square test used for?

Answer 12

To examine relationships between categorical variables.

Question 13

What is ANOVA used for?

Answer 13

To compare the means of three or more groups.

Question 13

What does correlation measure?

Answer 13

The strength and direction of a linear relationship between two numerical variables.

Question 14

What is regression analysis used for?

Answer 14

Predicting a dependent variable from one or more independent variables.

Question 15

What are the three sampling methods discussed?

Answer 15

Random, stratified, and cluster sampling.

Question 16

What are confidence intervals?

Answer 16

Ranges that estimate a population parameter with a given level of confidence (e.g., 95%).

Question 17

What affects the width of confidence intervals?

Answer 17

Sample size, variability, and confidence level.

Question 18

What’s the difference between statistical and practical significance?

Answer 18

Statistical: based on p-values; Practical: whether the effect is meaningful in real life.

Question 19

What are examples of categorical data?

Answer 19

Blood type, gender, disease status.

Question 20

What are examples of numerical data?

Answer 20

Number of hospital visits, test scores.

Question 21

What are examples of continuous data?

Answer 21

Height, weight, temperature.

Question 22

What measures are used for skewed data?

Answer 22

Median and IQR (interquartile range).

Question 23

What is standard deviation?

Answer 23

A measure of how spread out the data is around the mean.

Question 24

Why is standard deviation preferred over variance?

Answer 24

It is in the same units as the original data, making it easier to interpret.

Question 25

When critically appraising a research article, what are some key questions you should ask about the study design, sample size, and statistical methods used?

Answer 25

Is the study design appropriate? Is the sample size large enough and representative? Are the statistical methods appropriate for the data type and study aim? Are p-values and confidence intervals reported and interpreted correctly?

Question 26

Provide examples of categorical, numerical, and continuous data

Answer 26

Categorical: blood type (A/B/O), gender Numerical (discrete): number of children Continuous: height, cholesterol level

Question 27

Briefly describe the three different sampling methods discussed in this lecture

Answer 27

Random: equal chance of selection Stratified: divide into subgroups (e.g., by age), sample from each Cluster: divide into clusters (e.g., schools), then sample whole clusters

Question 28

* What type of data are the mean, mode, and median best used for?

Answer 28

Mean: for symmetrical, numerical data Median: for skewed data Mode: for categorical data

Question 29

Interpret the following statement: "The results of the study were statistically significant (p < 0.05)." What does this statement mean in the context of hypothesis testing? What does it not mean?

Answer 29

There is less than a 5% chance the observed results are due to random variation alone if the null is true. It does not mean the effect is large or important, nor does it prove the hypothesis is true.

Question 30

What is the purpose of a chi-square test? Describe a scenario where a chi-square test would be an appropriate statistical method to use.

Answer 30

Tests whether two categorical variables are related. Example: Is smoking status associated with disease outcome?

Question 31

Explain the purpose of a t-test. Under what circumstances would you use an independent samples t-test versus a paired samples t-test?

Answer 31

Tests if means differ between two groups. Use independent for unrelated groups; paired for repeated measures (same group pre/post).

Question 32

Explain the difference between variance and standard deviation. Why is the standard deviation often preferred over the variance when describing the spread of data?

Answer 32

Variance: average squared deviation SD: square root of variance (same units as data, easier to interpret)

Question 33

* List and briefly describe some of the common statistical tests

Answer 33

t-test: compare two means ANOVA: compare 3+ means Chi-square: test categorical associations Correlation: assess relationship strength Regression: prediction and relationship modeling

Question 34

* Briefly describe the 3 factors impacting confidence intervals

Answer 34

Sample size (larger = narrower CI) Variability (more = wider CI) Confidence level (higher = wider CI)

Question 35

Explain the difference between statistical significance and practical significance. Why is it important to consider both when interpreting research findings?

Answer 35

Statistical: relies on p-values and chance Practical: real-world relevance Both are needed to fully interpret findings (e.g., small but significant change may be clinically irrelevant)