Definitions / Concepts Related to Probability and Nonprobability

1. Define probability sampling and nonprobability sampling. Discuss their main

differences.
o Probability sampling: A sampling technique where every member of the
population has a known, non-zero chance of being selected. It involves
random selection, which ensures that the sample is representative of the
population.
o Nonprobability sampling: A sampling method where not every individual
has a chance of being selected. The selection process is subjective or based
on convenience, and the sample may not be representative of the population.
o Main difference: Probability sampling ensures randomness and represents
the population accurately, while nonprobability sampling can introduce bias
because the selection process is not random.
2. What are the advantages and disadvantages of using probability sampling
methods in research?
o Advantages:
 Reduces sampling bias.
 Provides more accurate and generalizable results.
 Statistical techniques can be applied to calculate the probability of
errors.
o Disadvantages:
 Time-consuming and expensive.
 Requires access to the entire population list (sampling frame).
 May be difficult to achieve in large-scale studies.
3. Explain nonprobability sampling. When might a researcher choose to use
nonprobability sampling instead of probability sampling?
o Nonprobability sampling is when participants are selected based on non-
random criteria, such as convenience or expert judgment. Examples include
convenience sampling, purposive sampling, and quota sampling.
o Researchers might use nonprobability sampling when they have limited
resources, time, or when a specific target group is needed. It's also useful in
exploratory research or when studying rare phenomena.

Probability Sampling Methods and Common Applications

4. List and describe the different types of probability sampling methods. Provide
one real-world example of when each would be appropriately used.
o Simple Random Sampling: Every member has an equal chance of being
selected. Example: Randomly selecting patients from a hospital database.
o Systematic Sampling: Every nth member is selected. Example: Every 10th
visitor to a clinic is chosen for a survey.
 o Stratified Sampling: The population is divided into subgroups (strata), and
a random sample is taken from each subgroup. Example: Surveying different
age groups in a national health survey.
o Cluster Sampling: The population is divided into clusters, and some
clusters are selected randomly. Example: Randomly selecting schools from a
district to study student health behaviors.
5. What are common applications of probability sampling in healthcare
research? Provide two examples.
o Example 1: Using stratified sampling to ensure a representative sample of
patients from various age groups for a health survey.
o Example 2: Using simple random sampling to select individuals from a
population for a clinical trial.

Types of Data

6. Differentiate between categorical and continuous data. Provide examples of

each.
o Categorical data: Data that can be placed into distinct categories or groups.
Example: Gender (male, female).
o Continuous data: Data that can take any value within a range. Example:
Height (measured in centimeters).
7. Explain the following types of data: nominal, ordinal, interval, and ratio. Give
an example for each.
o Nominal data: Categories with no order. Example: Blood type (A, B, AB,
O).
o Ordinal data: Categories with a specific order, but the intervals between the
categories are not equal. Example: Pain scale (none, mild, moderate, severe).
o Interval data: Ordered data with equal intervals, but no true zero point.
Example: Temperature in Celsius.
o Ratio data: Similar to interval data but with a true zero. Example: Weight
(in kilograms).

Measures of Central Tendency, Modality, and Dispersion

8. What are the three measures of central tendency? Define each and explain how
they are used in data analysis.
o Mean: The average of all values in a data set. Useful for data that is
normally distributed.
o Median: The middle value when the data is ordered. Used for skewed data
or when there are outliers.
o Mode: The value that appears most frequently. Used for categorical data.
9. Explain what is meant by unimodal, bimodal, and multimodal distributions.
o Unimodal: A distribution with one peak. Example: Heights of a population.
o Bimodal: A distribution with two peaks. Example: Age distribution in a
retirement home (younger and older adults).
 o Multimodal: A distribution with multiple peaks. Example: Survey results
where there are different clusters of opinions.
10. How is the range calculated? What does it tell you about a data set?
o Range: The difference between the maximum and minimum values in a data
set. It gives an idea of the spread or variability of the data but is sensitive to
outliers.
11. Define standard deviation. How do you interpret the standard deviation of a
data set?
o Standard deviation is a measure of the amount of variation or dispersion in
a data set. A small standard deviation means the data points are close to the
mean, while a large standard deviation means the data points are spread out
over a wider range.
12. Explain the concept of dispersion in statistics. How does it relate to variability
in data?
o Dispersion refers to the spread of data points around the central tendency
(mean or median). Measures of dispersion, like range and standard
deviation, provide insights into how much variability exists in a data set.

Hypothesis Testing and Related Concepts

13. What is hypothesis testing? Describe the steps involved in testing a hypothesis.
o Hypothesis testing is a statistical method used to determine whether there is
enough evidence to reject a null hypothesis.
o Steps:
1. State the null and alternative hypotheses.
2. Choose the significance level (alpha).
3. Collect and analyze the data.
4. Compute the test statistic and p-value.
5. Make a decision to reject or fail to reject the null hypothesis.
14. Explain the difference between rejecting and accepting the null hypothesis.
o Rejecting the null hypothesis means there is enough evidence to support
the alternative hypothesis.
o Accepting the null hypothesis means there is insufficient evidence to reject
it, not necessarily that it is true.
15. What does a p-value indicate in hypothesis testing?
o A p-value indicates the probability of obtaining results at least as extreme as
the ones observed, assuming the null hypothesis is true. A p-value below a
pre-determined threshold (e.g., 0.05) suggests that the results are statistically
significant.
16. What is the significance of a confidence interval (CI) in statistical analysis?
How do you interpret a 95% confidence interval?
o A confidence interval provides a range of values within which the true
population parameter is likely to fall. A 95% confidence interval means that
there is a 95% chance that the true value lies within the interval.

Statistically Significant vs. Clinically Significant Results

 17. What is the difference between statistically significant and clinically significant
results? Provide an example where the results could be statistically significant
but not clinically significant.
o Statistically significant means that the results are unlikely to have occurred
by chance, based on a p-value below the threshold (e.g., 0.05).
o Clinically significant refers to a result that has practical importance or
relevance in a real-world setting.
o Example: A drug may significantly lower blood pressure by 0.5 mmHg,
which is statistically significant but not clinically meaningful because the
effect is too small to have practical implications for patient health.

Power of a Study

18. What is the power of a study? How does it relate to the probability of correctly
rejecting a false null hypothesis?
o The power of a study is the probability that the study will correctly reject a
false null hypothesis. A higher power reduces the chance of making a Type
II error (failing to reject a false null hypothesis).

Testing Instruments for Healthcare Research

19. What is a Likert scale, and how is it used in healthcare research?

o A Likert scale is a psychometric scale commonly used in surveys to
measure attitudes, opinions, or perceptions. It typically consists of a
statement followed by a range of response options (e.g., strongly agree to
strongly disagree). It is used in healthcare research to assess patient
satisfaction, quality of life, etc.
20. What is the difference between reliability and validity in the context of testing
instruments in healthcare research?
o Reliability refers to the consistency or repeatability of a test or instrument.
o Validity refers to the extent to which a test measures what it is intended to
measure.
21. What are the different types of validity (e.g., construct, content, criterion)?
Explain each.
o Construct validity: The extent to which a test measures the concept it is
intended to measure.
o Content validity: The extent to which a test covers the entire range of the
concept being measured.
o Criterion validity: The extent to which a test correlates with an external
criterion (e.g., how well a test predicts future performance).
22. What types of statistical analysis are commonly used with Likert scale data?
o Descriptive statistics (mean, median, mode) are often used to summarize
Likert scale data. Non-parametric tests like the Chi-square test or Mann-
Whitney U test may also be used to analyze relationships or differences.

Frequency / Percentage
 23. How do you calculate frequency and percentage from a data set? Provide an
example.
o Frequency is the count of how often each value occurs in a data set.
o Percentage is calculated by dividing the frequency of a value by the total
number of observations and multiplying by 100.
o Example: If 30 out of 100 patients report a certain symptom, the frequency
is 30, and the percentage is (30/100) * 100 = 30%.
24. Explain why frequency distributions and percentages are useful in healthcare
research.
o They help summarize and present large amounts of data in a meaningful
way. Percentages allow for easy comparisons between different groups or
time points.

Graphical Representation of Data

25. Describe the key differences between a line graph and a bar graph. When
should each be used?
o Line graph: Used to display trends over time or continuous data.
o Bar graph: Used to compare discrete categories or groups.
26. What types of data are best represented using a histogram, and why?
o Histogram: Best for continuous data where you want to display the
frequency distribution. It helps visualize the shape of the data distribution.
27. How would you interpret a pie chart showing the distribution of various health
conditions in a population?
o A pie chart visually displays the proportion of each health condition in the
population, making it easy to compare relative sizes. Larger segments
represent more common conditions, while smaller segments represent less
common conditions.
1. Definitions / Concepts Related to Probability and Nonprobability
Sampling

Term Definition Example

Sampling method where every member of Randomly selecting
Probability
the population has a known, non-zero patients from a hospital
Sampling
chance of being selected. database.
Sampling method where not every
Selecting participants from
Nonprobability individual has a chance of being selected,
a specific clinic where
Sampling and selection is based on non-random
access is limited.
criteria.

2. Advantages and Disadvantages of Probability Sampling

Advantages Disadvantages
Reduces sampling bias. Time-consuming and expensive.
Requires access to the entire population list
Provides accurate and generalizable results.
(sampling frame).
Statistical analysis can be used to calculate
May be difficult in large-scale studies.
error probabilities.

3. Nonprobability Sampling

Definition When to Use Example

Sampling method where When resources or time are Selecting a small group of
selection is based on non- limited or when studying patients from a hospital for a
random criteria. specific populations. study on a rare disease.

4. Types of Probability Sampling

Sampling
Description Example
Method
Simple Random Every individual has an equal chance Randomly selecting 100 patients
Sampling of being selected. from a hospital registry.
Systematic Every nth individual is selected from a Selecting every 10th visitor from a
Sampling list. hospital for a survey.
The population is divided into
Stratified Surveying patients of different age
subgroups, and random samples are
Sampling groups in a national health survey.
taken from each subgroup.
Cluster The population is divided into Selecting a few schools randomly
Sampling clusters, and entire clusters are in a district for a study on student
 Sampling
Description Example
Method
selected randomly. health behaviors.

5. Common Applications of Probability Sampling in Healthcare Research

Example Description
Ensuring a representative sample of patients across different age
Stratified Sampling
groups for a survey.
Simple Random Selecting patients from a clinic for a clinical trial to study the
Sampling effectiveness of a new medication.

6. Types of Data

Type Description Example

Categorical Data that can be grouped into categories without Blood type: A, B, AB,
Data any order. O.
Continuous
Data that can take any value within a range. Height in centimeters.
Data

7. Types of Data (Nominal, Ordinal, Interval, Ratio)

Type of
Description Example
Data
Nominal Categories with no specific order. Gender (Male, Female).
Categories with an order but no equal Pain scale (None, Mild,
Ordinal
intervals between them. Moderate, Severe).
Data with equal intervals between values, but
Interval Temperature in Celsius.
no true zero point.
Data with equal intervals and a true zero
Ratio Weight (in kilograms).
point.

8. Measures of Central Tendency

Measure Description Example

Mean age of patients: (60 + 65 + 70 + 75) / 4 =
Mean The average of all values.
70.
The middle value when the Median income: If incomes are 25k, 30k, 35k,
Median
data is ordered. 40k, 45k, the median is 35k.
Mode The most frequent value. Mode of exam scores: 85, 90, 85, 95 (mode =
Measure Description Example
85).

9. Modality (Unimodal, Bimodal, Multimodal)

Type Description Example

Unimodal One peak in the distribution. Distribution of heights in a population.
Age distribution in a community (younger and
Bimodal Two peaks in the distribution.
older age groups).
More than two peaks in the Distribution of survey responses with multiple
Multimodal
distribution. clusters of opinion.

10. Range Calculation

Description Example
The range is calculated as the difference between the For data set: 5, 10, 15, 20, 25,
maximum and minimum values in a data set. Range = 25 - 5 = 20.

11. Standard Deviation

Description Example
Standard deviation measures the spread of data In a data set (5, 7, 9, 11, 13), the
points around the mean. A smaller standard standard deviation is calculated to be
deviation means data points are close to the mean. 3.16, indicating a moderate spread.

12. Dispersion

Description Example
Dispersion refers to how spread out A data set (5, 6, 7, 8, 9) has low dispersion, while
data points are in a data set. (1, 10, 15, 20, 25) has high dispersion.

13. Hypothesis Testing Steps

Step Description
State Hypotheses Formulate the null and alternative hypotheses.
Choose Significance
Set the significance level (alpha), usually 0.05.
Level
Collect Data Gather the data necessary for analysis.
Analyze Data Perform statistical analysis to compute test statistics and p-
 Step Description
values.
Make Decision Reject or fail to reject the null hypothesis based on the p-value.

14. Rejecting and Accepting Null Hypothesis

Action Description
There is enough evidence to support the alternative
Reject Null Hypothesis
hypothesis.
Fail to Reject Null There is insufficient evidence to support the alternative
Hypothesis hypothesis.

15. P-Value Interpretation

Description Example
A p-value indicates the probability of observing the
A p-value of 0.03 means there is a 3%
data assuming the null hypothesis is true. A p-value
chance the results are due to chance,
below 0.05 usually means the results are statistically
suggesting statistical significance.
significant.

16. Confidence Interval Interpretation

Description Example
A confidence interval (CI) provides a range of values A 95% CI of [120, 130] for blood
that is likely to contain the true population parameter. pressure suggests the true
A 95% CI means we are 95% confident the true value population blood pressure is likely
lies within the interval. between 120 and 130.

17. Statistical vs. Clinical Significance

Type Description Example

Results are unlikely to be due to
Statistical A drug reduces blood pressure by 5
chance, based on a p-value
Significance mmHg with a p-value of 0.02.
threshold (usually < 0.05).
A 5 mmHg reduction in blood
Clinical Results have practical relevance
pressure may not have meaningful
Significance and impact on patient outcomes.
clinical benefits for patients.

18. Power of a Study

 Description Example
Power is the probability that a study will A study with 80% power has an 80% chance
correctly reject a false null hypothesis. of detecting a true effect if it exists.

19. Likert Scale in Healthcare Research

Description Example
A Likert scale measures attitudes or A 5-point Likert scale assessing patient
opinions on a range from strongly agree to satisfaction (Strongly Agree, Agree, Neutral,
strongly disagree. Disagree, Strongly Disagree).

20. Reliability vs. Validity

Type Description Example

Consistency of the measurement over A blood pressure cuff that gives the
Reliability
time. same reading when used multiple times.
The degree to which a test measures A blood pressure cuff that accurately
Validity
what it is intended to measure. measures blood pressure.

21. Types of Validity

Type Description Example

Construct The test measures the concept it is A depression scale measuring
Validity intended to measure. depression symptoms accurately.
Content The test includes all relevant A job satisfaction survey covering all
Validity content for the concept. aspects of job satisfaction.
Criterion The test correlates with an external A new IQ test correlating with
Validity criterion. established IQ tests.

22. Statistical Analysis for Likert Scale

Analysis Description
Descriptive Statistics Mean, median, mode to summarize Likert scale data.
Non-parametric Tests Chi-square test, Mann-Whitney U test for Likert data analysis.

23. Frequency and Percentage

Term Description Example

Frequency The count of occurrences of each In a sample of 100 patients, 60 report
 Term Description Example
value. headaches (frequency = 60).
The frequency expressed as a 60 out of 100 patients report headaches
Percentage
percentage of the total. (percentage = 60%).

24. Graphical Representation

Graph
Description Example
Type
Line Displays trends over time or Tracking patient blood pressure readings over
Graph continuous data. time.
Bar Compares discrete categories Comparing the number of patients with
Graph or groups. different types of health conditions.

25. Histogram

Description Example
A histogram displays the frequency A histogram showing the distribution of
distribution of continuous data. patients' ages in a hospital.

26. Pie Chart Interpretation

Description Example
A pie chart shows the proportion A pie chart showing the distribution of different health
of different categories in a conditions in a population (e.g., 40% cardiovascular
whole. disease, 30% diabetes).