PMH-C Statistics Study Guide (2025/2026 Syllabus)
Introduction: This guide covers the key statistical concepts required for the PMH-C
examination. The focus is on interpreting and applying statistical results in the context of
evidence-based psychiatric nursing practice, rather than on complex calculations. Each
answer is illustrated with a clinically relevant example.
Section 1: Fundamental Concepts & Descriptive Statistics
1. What is the difference between descriptive and inferential statistics?
ANSWER ✓ Descriptive statistics summarize and describe the characteristics of a
specific dataset, while inferential statistics use a sample from a population to make
inferences, predictions, or generalizations about the larger population.
Illustration: A PMHNP surveys 50 patients in their clinic with Generalized Anxiety
Disorder (GAD) and calculates their average Beck Anxiety Inventory (BAI) score. This is
a descriptive statistic. If they then use that sample's data to estimate the average BAI
score for all adults with GAD in the state, that is an inferential statistic.
2. Define and differentiate a Population, Sample, and Parameter.
ANSWER ✓ A Population is the entire group of interest (e.g., all adolescents with Major
Depressive Disorder in the US). A Sample is a subset of the population selected for
study (e.g., 200 adolescents with MDD from three clinics). A Parameter is a numerical
characteristic of a population (e.g., the true mean PHQ-9 score for all US adolescents
with MDD), while a Statistic describes the sample.
3. What are the four levels of measurement? Provide an example of each in a
mental health context.
ANSWER ✓
Nominal: Categories with no order (e.g., DSM-5 diagnosis: Schizophrenia, Bipolar
Disorder, PTSD).
Ordinal: Categories with a meaningful order, but intervals between are not equal (e.g.,
Likert scale: "Never, Sometimes, Often, Always" for frequency of suicidal ideation; or
Clinical Global Impression-Severity scale: 1=Normal to 7=Extremely Ill).
, Interval: Ordered values with equal intervals, but no true zero (e.g., Temperature in
Celsius, IQ score).
Ratio: Ordered values with equal intervals and a true zero point (e.g., Number of panic
attacks in a week, Duration of sleep in hours).
4. When is the Mean the most appropriate measure of central tendency? When is
the Median preferred?
ANSWER ✓ The Mean is best for normally distributed, interval/ratio data without
extreme outliers. The Median is preferred for ordinal data or when the data is skewed or
has outliers, as it is not affected by extreme values.
Illustration: Reporting the average (mean) number of therapy sessions is useful.
However, if reporting the "average" income of patients in a clinic where one patient is a
multi-millionaire, the median income would give a better representation of the "typical"
patient, as the mean would be skewed high.
5. What does Standard Deviation (SD) tell us about a dataset?
ANSWER ✓ Standard Deviation measures the average amount of variability or spread
around the mean. A small SD indicates data points are clustered closely around the
mean; a large SD indicates data is more spread out.
Illustration: In a study on a new medication for PTSD, Group A has a mean CAPS-5
score reduction of 15 points with an SD of 2. Group B has the same mean reduction but
an SD of 8. This means Group A's response was very consistent, while Group B's
response was highly variable—some patients improved dramatically, and others did not.
6. What is the purpose of a Confidence Interval (CI), commonly 95% CI?
ANSWER ✓ A 95% Confidence Interval provides a range of values within which we can
be 95% confident that the true population parameter (e.g., the true mean difference)
lies.
Illustration: A study finds that a new therapy reduces depression scores by an average
of 5 points compared to treatment as usual, with a 95% CI of (2, 8). This means we are
95% confident the true average effect of this therapy in the entire population is between
a 2-point and an 8-point reduction. Since the interval does not include 0, the effect is
statistically significant.
7. How is a Percentage different from a Proportion?
ANSWER ✓ A proportion is a decimal between 0 and 1 (e.g., 0.25), representing a part
of a whole. A percentage is a proportion multiplied by 100 (e.g., 25%). They convey the
same information in different formats.
, 8. What is the difference between Prevalence and Incidence?
ANSWER ✓ Prevalence is the proportion of a population who have a condition at a
specific point in time (a "snapshot"). Incidence is the proportion of a population
who develop a new condition over a specified period (a "movie").
Illustration: The prevalence of Major Depressive Disorder in the US might be 7% in a
given year. The incidence might be 2%, meaning 2% of the population without MDD
developed it during that year.
9. Define Risk and how it is calculated in a cohort study.
ANSWER ✓ Risk is the probability of an outcome occurring in a defined population. In a
cohort study, it is calculated as (Number of people who develop the outcome) / (Total
number of people at risk at the start).
10. What is the relationship between a Standard Error (SE) and a Standard
Deviation (SD)?
ANSWER ✓ The Standard Deviation (SD) describes the variability of individual data
points. The Standard Error (SE), often the Standard Error of the Mean (SEM), describes
the variability of the sample mean itself—how much the mean would vary if you took
repeated samples from the same population. SEM = SD / √(sample size). It is used to
calculate confidence intervals.
Section 2: Inferential Statistics & Hypothesis Testing
11. What is a Null Hypothesis (H₀)?
ANSWER ✓ The Null Hypothesis is the default assumption that there is no effect, no
difference, or no relationship between groups or variables.
Illustration: H₀: There is no difference in the mean reduction in PANSS scores between
patients receiving the new antipsychotic drug and those receiving a placebo.
12. What is an Alternative Hypothesis (H₁ or Hₐ)?
ANSWER ✓ The Alternative Hypothesis states that there is an effect, a difference, or a
relationship. It is what the researcher aims to support.
Illustration: H₁: There is a difference in the mean reduction in PANSS scores between
patients receiving the new antipsychotic drug and those receiving a placebo.
Introduction: This guide covers the key statistical concepts required for the PMH-C
examination. The focus is on interpreting and applying statistical results in the context of
evidence-based psychiatric nursing practice, rather than on complex calculations. Each
answer is illustrated with a clinically relevant example.
Section 1: Fundamental Concepts & Descriptive Statistics
1. What is the difference between descriptive and inferential statistics?
ANSWER ✓ Descriptive statistics summarize and describe the characteristics of a
specific dataset, while inferential statistics use a sample from a population to make
inferences, predictions, or generalizations about the larger population.
Illustration: A PMHNP surveys 50 patients in their clinic with Generalized Anxiety
Disorder (GAD) and calculates their average Beck Anxiety Inventory (BAI) score. This is
a descriptive statistic. If they then use that sample's data to estimate the average BAI
score for all adults with GAD in the state, that is an inferential statistic.
2. Define and differentiate a Population, Sample, and Parameter.
ANSWER ✓ A Population is the entire group of interest (e.g., all adolescents with Major
Depressive Disorder in the US). A Sample is a subset of the population selected for
study (e.g., 200 adolescents with MDD from three clinics). A Parameter is a numerical
characteristic of a population (e.g., the true mean PHQ-9 score for all US adolescents
with MDD), while a Statistic describes the sample.
3. What are the four levels of measurement? Provide an example of each in a
mental health context.
ANSWER ✓
Nominal: Categories with no order (e.g., DSM-5 diagnosis: Schizophrenia, Bipolar
Disorder, PTSD).
Ordinal: Categories with a meaningful order, but intervals between are not equal (e.g.,
Likert scale: "Never, Sometimes, Often, Always" for frequency of suicidal ideation; or
Clinical Global Impression-Severity scale: 1=Normal to 7=Extremely Ill).
, Interval: Ordered values with equal intervals, but no true zero (e.g., Temperature in
Celsius, IQ score).
Ratio: Ordered values with equal intervals and a true zero point (e.g., Number of panic
attacks in a week, Duration of sleep in hours).
4. When is the Mean the most appropriate measure of central tendency? When is
the Median preferred?
ANSWER ✓ The Mean is best for normally distributed, interval/ratio data without
extreme outliers. The Median is preferred for ordinal data or when the data is skewed or
has outliers, as it is not affected by extreme values.
Illustration: Reporting the average (mean) number of therapy sessions is useful.
However, if reporting the "average" income of patients in a clinic where one patient is a
multi-millionaire, the median income would give a better representation of the "typical"
patient, as the mean would be skewed high.
5. What does Standard Deviation (SD) tell us about a dataset?
ANSWER ✓ Standard Deviation measures the average amount of variability or spread
around the mean. A small SD indicates data points are clustered closely around the
mean; a large SD indicates data is more spread out.
Illustration: In a study on a new medication for PTSD, Group A has a mean CAPS-5
score reduction of 15 points with an SD of 2. Group B has the same mean reduction but
an SD of 8. This means Group A's response was very consistent, while Group B's
response was highly variable—some patients improved dramatically, and others did not.
6. What is the purpose of a Confidence Interval (CI), commonly 95% CI?
ANSWER ✓ A 95% Confidence Interval provides a range of values within which we can
be 95% confident that the true population parameter (e.g., the true mean difference)
lies.
Illustration: A study finds that a new therapy reduces depression scores by an average
of 5 points compared to treatment as usual, with a 95% CI of (2, 8). This means we are
95% confident the true average effect of this therapy in the entire population is between
a 2-point and an 8-point reduction. Since the interval does not include 0, the effect is
statistically significant.
7. How is a Percentage different from a Proportion?
ANSWER ✓ A proportion is a decimal between 0 and 1 (e.g., 0.25), representing a part
of a whole. A percentage is a proportion multiplied by 100 (e.g., 25%). They convey the
same information in different formats.
, 8. What is the difference between Prevalence and Incidence?
ANSWER ✓ Prevalence is the proportion of a population who have a condition at a
specific point in time (a "snapshot"). Incidence is the proportion of a population
who develop a new condition over a specified period (a "movie").
Illustration: The prevalence of Major Depressive Disorder in the US might be 7% in a
given year. The incidence might be 2%, meaning 2% of the population without MDD
developed it during that year.
9. Define Risk and how it is calculated in a cohort study.
ANSWER ✓ Risk is the probability of an outcome occurring in a defined population. In a
cohort study, it is calculated as (Number of people who develop the outcome) / (Total
number of people at risk at the start).
10. What is the relationship between a Standard Error (SE) and a Standard
Deviation (SD)?
ANSWER ✓ The Standard Deviation (SD) describes the variability of individual data
points. The Standard Error (SE), often the Standard Error of the Mean (SEM), describes
the variability of the sample mean itself—how much the mean would vary if you took
repeated samples from the same population. SEM = SD / √(sample size). It is used to
calculate confidence intervals.
Section 2: Inferential Statistics & Hypothesis Testing
11. What is a Null Hypothesis (H₀)?
ANSWER ✓ The Null Hypothesis is the default assumption that there is no effect, no
difference, or no relationship between groups or variables.
Illustration: H₀: There is no difference in the mean reduction in PANSS scores between
patients receiving the new antipsychotic drug and those receiving a placebo.
12. What is an Alternative Hypothesis (H₁ or Hₐ)?
ANSWER ✓ The Alternative Hypothesis states that there is an effect, a difference, or a
relationship. It is what the researcher aims to support.
Illustration: H₁: There is a difference in the mean reduction in PANSS scores between
patients receiving the new antipsychotic drug and those receiving a placebo.
