Introduction
Many nursing students know they need to examine a relationship between two variables, but they are unsure whether Pearson correlation analysis in nursing research is the correct statistical test. You may have age and systolic blood pressure, medication adherence score and blood pressure, stress score and sleep quality score, nurse burnout score and job satisfaction score, or pain intensity and quality-of-life score. The challenge is not only collecting the data. The challenge is deciding whether Pearson correlation fits your research question, variable type, assumptions, software output, and Chapter 4 reporting expectations.
Pearson correlation is useful when a nursing student wants to examine the strength and direction of a linear relationship between two continuous variables. It answers questions such as, “Are these two measured variables related?” and “When one variable increases, does the other variable tend to increase or decrease?” However, Pearson correlation does not prove cause and effect. A statistically significant Pearson correlation can show association, but it cannot prove that stress caused poor sleep, medication adherence caused lower blood pressure, or burnout caused lower job satisfaction.
Medical-statistics guidance warns that correlation coefficients must be selected, interpreted, and reported carefully because misuse can lead to exaggerated or inaccurate conclusions (Mukaka, 2012; Schober et al., 2018).
This guide explains what Pearson correlation is, when nursing students should use it, what assumptions must be checked, how to interpret Pearson’s r, how sample size affects results, how to interpret p-values and confidence intervals, how missing data affect analysis, how to read SPSS and Excel output at a practical level, and how to report Pearson correlation in APA 7th edition.
For the broader topic cluster, use the main guide on correlation analysis in nursing research. For broader test selection, you may also review statistical tests in nursing research, inferential data analysis in nursing research, and types of data analysis in quantitative research.
What Is Pearson Correlation Analysis?
Pearson correlation analysis measures the strength and direction of a linear relationship between two continuous variables. The result is called the Pearson correlation coefficient, commonly written as Pearson’s r. Pearson’s r ranges from −1 to +1. A value close to +1 suggests a strong positive linear relationship. A value close to −1 suggests a strong negative linear relationship. That which is close to 0 suggests little or no linear relationship. IBM’s official SPSS documentation describes Pearson’s correlation coefficient as a measure of linear association and states that correlation coefficients range from −1 to +1, with 0 indicating no linear association (IBM, n.d.-a).
A positive Pearson correlation means the two variables tend to increase together. For example, higher nurse workload scores may be associated with higher burnout scores.
A negative Pearson correlation means one variable tends to increase as the other decreases. For example, higher medication adherence scores may be associated with lower systolic blood pressure.
A zero or near-zero Pearson correlation means the two variables do not show a clear linear relationship in the sample.
Pearson correlation is not only about statistical significance. A complete nursing interpretation should include the coefficient, direction, strength, p-value, sample size, confidence interval when available, and clinical or practical meaning.
What Pearson’s r Means
Pearson’s r is the numerical value that summarizes the linear relationship between two variables. It tells the student both the direction and the strength of the relationship.
If r = +1, the relationship is a perfect positive linear relationship. As one variable increases, the other increases in a perfectly straight-line pattern.
If r = −1, the relationship is a perfect negative linear relationship. As one variable increases, the other decreases in a perfectly straight-line pattern.
If r = 0, there is no linear relationship. This does not always mean there is no relationship at all. A curved or non-linear relationship can exist even when Pearson’s r is weak.
Values closer to −1 or +1 are stronger. The sign only tells direction. It does not tell importance. For example, r = −.60 is stronger than r = .25 because .60 is farther from zero. The negative sign does not make the relationship weaker; it only tells you that the relationship moves in the opposite direction.
A statistically significant r can still be weak. A non-significant r does not always prove that no relationship exists, especially when the sample size is small. Nursing students should interpret Pearson’s r together with the sample size, p-value, confidence interval, measurement quality, study design, and clinical context. The American Statistical Association warns that p-values do not measure effect size or practical importance and should not be used alone as the basis for scientific conclusions (Wasserstein & Lazar, 2016).
Table 1. General Guide for Interpreting Pearson Correlation Coefficients
| Pearson’s r | General strength | Direction | Nursing interpretation caution |
|---|---|---|---|
| 0 to ±.09 | Very weak or negligible | Positive or negative | May have little practical meaning unless the outcome is highly important |
| ±.10 to ±.29 | Weak | Positive or negative | Can be statistically significant in a large sample but still weak |
| ±.30 to ±.49 | Moderate | Positive or negative | May be meaningful, depending on the clinical or educational context |
| ±.50 to ±.69 | Strong | Positive or negative | Check for outliers, overlapping measures, or similar constructs |
| ±.70 to ±1.00 | Very strong | Positive or negative | May suggest very similar variables or possible multicollinearity |
These thresholds are general guides, not absolute rules. In nursing research, a weak correlation may still matter if the outcome involves medication safety, falls, readmission, patient harm, or treatment adherence. A strong correlation may be less impressive if the two variables measure nearly the same construct.
Pearson Correlation Analysis in Nursing Research: When Should Students Use It?
Nursing students should use Pearson correlation when the research question asks about the relationship or association between two continuous or approximately continuous variables and the expected relationship is linear.
Pearson correlation is appropriate when the research question asks about a relationship or association, both variables are continuous or approximately continuous, both variables are measured on the same participants, the relationship is expected to be linear, and the student wants to measure the direction and strength of association.
Pearson correlation is commonly used in cross-sectional, observational, or non-experimental quantitative research. It is not the correct test when the student is comparing groups, testing pretest-posttest change, or predicting an outcome using several predictors.
Strong nursing research questions for Pearson correlation include:
What is the relationship between medication adherence scores and systolic blood pressure among adults with hypertension?
Is there a relationship between nurse burnout scores and job satisfaction scores?
What is the relationship between academic stress scores and sleep quality scores among nursing students?
Is pain intensity related to quality-of-life scores among postoperative patients?
What is the relationship between health literacy scores and diabetes self-management behavior scores?
Pearson correlation fits these examples because the student is examining whether two measured variables move together in a linear pattern. It does not fit questions that compare groups, test change over time, or predict an outcome from multiple predictors.
A student who is unsure whether the research question is a Pearson correlation question should compare the planned analysis with the broader guide on statistical tests in nursing research before finalizing Chapter 3.
Variables Suitable for Pearson Correlation
Pearson correlation works best with variables that are continuous or approximately continuous. In nursing research, these often include clinical measurements, questionnaire total scores, composite scale scores, and approximately interval-level scores.
Suitable variables may include age, systolic or diastolic blood pressure, BMI, length of stay, pain intensity score, stress score, burnout score, job satisfaction score, sleep quality score, medication adherence total score, patient satisfaction scale score, health literacy score, quality-of-life score, and diabetes self-management behavior score.
A common issue involves Likert-scale data. A single Likert item is ordinal. For example, one item rated from 1 = strongly disagree to 5 = strongly agree is not the same as a continuous measurement. However, a summed or averaged score from several well-designed Likert-type items is often treated as approximately continuous in applied health research when scoring, reliability, and distribution are acceptable. Students should follow committee guidance and inspect assumptions before deciding.
Table 2. Nursing Variables Suitable for Pearson Correlation
| Variable 1 | Variable 2 | Why Pearson may fit | Caution before analysis |
|---|---|---|---|
| Age | Systolic blood pressure | Both are continuous measurements | Check scatterplot for linearity and outliers |
| Medication adherence score | Blood pressure | Both can be measured numerically | Confirm adherence score is correctly calculated |
| Stress score | Sleep quality score | Both may be scale totals | Check normality, linearity, and scoring |
| Burnout score | Job satisfaction score | Both are common questionnaire scale scores | Check whether scales measure distinct constructs |
| Pain score | Quality-of-life score | Both may be numerical or scale scores | Pain scores may be ordinal or skewed |
| Health literacy score | Self-care behavior score | Both may be composite scores | Check reliability and missing items |
For background on preparing variables before inferential testing, students may review descriptive data analysis in nursing research.
Pearson Correlation Assumptions
Pearson correlation is simple to run in SPSS or Excel, but it is not assumption-free. A student should not run the test and copy the output without checking whether the analysis is appropriate.
The main Pearson correlation assumptions include two continuous or approximately continuous variables, paired observations, independence of observations, a linear relationship, approximate normality or bivariate normality, absence of serious outliers, homoscedasticity, reliable measurement of variables, correct questionnaire scoring, adequate sample size, and appropriate handling of missing data.
IBM’s SPSS documentation states that researchers should screen data for outliers and evidence of a linear relationship before calculating a correlation coefficient, and it notes that Pearson’s correlation coefficient assumes bivariate normality (IBM, n.d.-a). Schober et al. (2018) also emphasize that Pearson correlation is designed for linear relationships and that correlation interpretation should consider the data pattern and appropriate coefficient choice (Schober et al., 2018).
Linearity
Pearson correlation measures linear relationships. If the relationship is curved, Pearson’s r may be weak or misleading even when a real relationship exists.
For example, pain and mobility may not always relate in a straight-line pattern. Mild pain may have little effect on mobility, moderate pain may reduce mobility, and severe pain may create a sharper decline. If the scatterplot shows a curved pattern, Pearson correlation may not summarize the relationship well.
A scatterplot is the easiest way to inspect linearity. If the points form a general upward or downward straight-line pattern, Pearson may fit. If the points curve, cluster, or form a U-shape, Pearson may be inappropriate.
Normality
Pearson correlation is more appropriate when the variables are approximately normally distributed, especially in small samples. Students can inspect histograms, Q-Q plots, skewness, kurtosis, and normality tests.
Normality does not mean every value must be perfect. In applied nursing research, data are rarely ideal. The practical question is whether the distribution is reasonably acceptable or whether skewness, extreme values, or ordinal measurement make Spearman correlation safer.
Outliers
Outliers can inflate, weaken, or reverse Pearson correlation. A single unusual value can make the coefficient look stronger or weaker than the actual pattern.
For example, suppose a student studies age and systolic blood pressure. Most participants are between 25 and 70 years old, but one participant is coded as 170 years old because of a data-entry error. That one outlier could distort the correlation. Another example is a systolic blood pressure value of 280 mmHg. That value may be clinically possible, but it should be verified.
Outliers should not be deleted automatically. Students should first check whether the value is a data-entry error, a valid extreme case, or a measurement problem. Any decision to correct, retain, exclude, or analyze sensitivity should be documented.
Independence of Observations
Pearson correlation assumes that observations are independent. This means one participant’s data should not determine another participant’s data.
Independence can be violated when there are repeated measurements, matched pairs, clustered data, family pairs, unit-level clusters, or multiple observations from the same participant. For example, if a student collects multiple blood pressure readings from the same patient and treats each reading as if it came from a different person, the assumption is violated.
Repeated-measures, clustered, or longitudinal data may require different methods. The correct approach depends on the design and research question.
Homoscedasticity
Homoscedasticity means the spread of one variable is reasonably similar across the range of the other variable. In simple terms, the scatterplot should not look narrow on one side and extremely wide on the other.
For example, if low stress scores show similar sleep-quality scores but high stress scores show a very wide spread of sleep-quality scores, the relationship may be harder to interpret. A scatterplot helps students inspect this pattern.
Reliable Measurement and Correct Scoring
Pearson correlation depends on measurement quality. If questionnaire scores are calculated incorrectly, the correlation result becomes unreliable. Before running the analysis, students should confirm item coding, reverse-coded items, missing-item rules, subscale scoring, total-score calculation, and reliability where relevant.
This step is especially important in nursing dissertations that use validated instruments for stress, burnout, depression, anxiety, satisfaction, self-care, adherence, quality of life, or health literacy.
How to Check Pearson Correlation Assumptions
Students can check Pearson correlation assumptions before relying on the output. This does not require turning Chapter 4 into a statistics textbook, but the analysis should be defensible.
Practical checks include descriptive statistics, histograms, boxplots, scatterplots, Q-Q plots, normality tests, missing-data review, extreme-value review, questionnaire scoring checks, reliability analysis for multi-item scales, and confirmation that both variables are measured on the same cases.
Pearson Correlation Assumption Checklist for Nursing Students
Use this checklist before interpreting Pearson’s r:
Are both variables continuous or approximately continuous?
Are both variables measured on the same participants?
Is each participant included only once?
Have questionnaire scores been calculated correctly?
Have reverse-coded items been handled correctly?
Are missing values identified?
Is the scatterplot approximately linear?
Are there serious outliers?
Are the variables approximately normal, especially in a small sample?
Is the sample size adequate for the research question?
Is Pearson more appropriate than Spearman, chi-square, t-test, ANOVA, paired testing, or regression?
Can the result be interpreted without causal language?
A student who cannot answer these questions confidently may need statistical guidance before writing Chapter 4. Nursing Dissertation Help can support students with assumption checks, data cleaning, questionnaire scoring, and SPSS output interpretation.
Scatterplots in Pearson Correlation
A scatterplot is essential before interpreting Pearson correlation. It shows the relationship between two variables visually. Pearson’s r and the p-value summarize the relationship numerically, but they do not show whether the pattern is linear, distorted, clustered, or driven by outliers.
A scatterplot helps students inspect direction of the relationship, strength of the relationship, linearity, outliers, clusters, unusual data patterns, possible non-linear relationships, and whether one or two extreme values drive the result.
For example, a student may find r = .52 between burnout and job dissatisfaction. That appears to be a strong positive relationship. However, a scatterplot may show that one group of nurses from one unit has unusually high burnout and low satisfaction, while the rest of the sample shows only a weak pattern. In that situation, the result may reflect subgroup differences or clustering rather than a simple relationship across the whole sample.
A student should not interpret Pearson correlation blindly from software output. The scatterplot protects against misleading conclusions.
Sample Size and Statistical Power in Pearson Correlation
Sample size affects Pearson correlation in several ways. Small samples can produce unstable estimates. A correlation from a sample of 18 participants can change greatly if only one or two values change. Small samples may also fail to detect meaningful relationships because the analysis lacks statistical power.
Large samples create a different problem. A weak correlation can become statistically significant when the sample is large. For example, r = .15 may be statistically significant in a large sample but may still have limited clinical meaning. A statistically significant weak relationship should not be described as strong.
A moderate correlation can fail to reach significance in a very small sample. For example, r = .40 may have practical interest in a pilot study but fail to reach p < .05 because the sample is too small. This does not prove there is no relationship. It means the result was not statistically significant in that sample.
Students should interpret Pearson correlation using Pearson’s r, sample size, p-value, confidence interval, measurement quality, clinical context, proposal requirements, committee expectations, and power-analysis guidance when available. Brydges (2019) emphasizes that effect-size interpretation and statistical power should be understood in relation to sample size and study context rather than treated as mechanical rules (Brydges, 2019).
Confidence Intervals for Pearson’s r
A 95% confidence interval for Pearson’s r gives a range of plausible values for the population correlation. It helps students understand uncertainty.
For example, suppose a student reports:
r(78) = −.34, p = .002, 95% CI [−.52, −.13]
This means the sample showed a statistically significant negative relationship, and the confidence interval suggests that the population relationship may plausibly range from a weak negative association to a moderate negative association.
Confidence intervals matter because the sample correlation is only an estimate. Narrower intervals suggest more precision. Wider intervals often occur with smaller samples, more variable data, or less stable estimates. Schober et al. (2018) note that hypothesis tests and confidence intervals can help address statistical significance and estimate the strength of the relationship in the population (Schober et al., 2018).
Many confidence intervals for Pearson correlation are based on Fisher’s z transformation. Welz et al. (2022) discuss Fisher-transformation-based confidence intervals for correlations and explain their role in estimating uncertainty around correlation coefficients (Welz et al., 2022).
Example Confidence Interval Interpretation
A Pearson correlation was conducted to examine the relationship between medication adherence scores and systolic blood pressure. The relationship was statistically significant, r(88) = −.41, p < .001, 95% CI [−.57, −.22]. The confidence interval suggests that the population relationship was likely between a weak-to-moderate and moderate negative association.
Not all basic Excel outputs provide confidence intervals automatically. IBM’s SPSS Bivariate Correlations documentation identifies confidence interval options for Pearson and Spearman correlations, and tools such as Jamovi, JASP, R, or professional statistical support can also help produce confidence intervals (IBM, n.d.-a).
Missing Data in Pearson Correlation
Missing data are common in nursing datasets. Survey participants may skip items. Clinical data may be unavailable. Some patients may have adherence scores but no blood pressure value, or stress scores but no sleep-quality score.
Missing data can reduce the number of valid cases in Pearson correlation. If a participant completed the stress scale but skipped the sleep-quality scale, that participant cannot be included in the Pearson correlation between stress and sleep quality because Pearson requires paired data for both variables.
SPSS and other tools may use listwise or pairwise deletion depending on the procedure and settings. Listwise deletion uses only cases with complete data across all selected variables. Pairwise deletion uses all available cases for each variable pair, which means different correlations in a matrix may have different sample sizes.
Students should check the valid n for each correlation. This is especially important when reporting a correlation matrix. If stress and sleep quality have n = 92 but burnout and job satisfaction have n = 77, the student should not assume all correlations used the same sample size.
Missing data should not be ignored. Students should describe missing-data handling when it affects the results, especially in Chapter 3 methodology or Chapter 4 results. If missingness is substantial or patterned, professional statistical support may be needed.
One-Tailed vs Two-Tailed Significance in Pearson Correlation
Pearson correlation can be tested using a one-tailed or two-tailed significance test. Nursing students should be cautious with this choice.
A two-tailed test is usually the safer default. It tests whether a relationship exists in either direction, positive or negative.
A one-tailed test tests whether the relationship exists in a specified direction. It should only be used when the direction was clearly predicted before analysis and when the opposite direction would not be interpreted as support for the hypothesis.
Students should not choose a one-tailed test after seeing the results just to make a result statistically significant. The choice should follow the proposal, committee guidance, institutional expectations, or approved methodology plan.
For example, if the proposal says, “There is a relationship between stress and sleep quality,” a two-tailed test is usually appropriate. If the proposal specifically predicts that “higher stress is associated with poorer sleep quality,” a one-tailed test may be defensible only if the directional decision was justified before analysis.
IBM’s SPSS documentation states that one-tailed probabilities may be selected when the direction of association is known in advance; otherwise, two-tailed probabilities should be selected (IBM, n.d.-a).
Pearson Correlation in Chapter 3, Chapter 4, and Chapter 5
Pearson correlation should connect logically across the dissertation. It should not appear suddenly in Chapter 4 without a clear explanation in Chapter 3.
Chapter 3: Methodology
In Chapter 3, students should explain why Pearson correlation is appropriate. This means identifying the research question, naming the variables, describing the measurement level, explaining why a linear association is expected, and stating how assumptions will be checked.
A strong Chapter 3 statement may look like this:
Pearson correlation will be used to examine the relationship between medication adherence scores and systolic blood pressure because both variables are continuous and the research question asks whether the variables are linearly associated. Assumptions will be evaluated using descriptive statistics, scatterplots, normality review, outlier screening, and missing-data assessment.
Chapter 4: Results
In Chapter 4, students should report the actual findings clearly. This includes valid n, Pearson’s r, p-value, confidence interval when available, direction, strength, and plain-language interpretation.
Chapter 4 should not claim that one variable caused another. It should state that variables were associated, related, or correlated.
Chapter 5: Discussion
In Chapter 5, students should discuss what the result means in relation to nursing practice, prior literature, study limitations, and future research. If the study is cross-sectional or observational, causal interpretation must remain cautious.
Many nursing Pearson correlation studies are observational. The STROBE guidance was developed to strengthen reporting of observational studies, including cohort, case-control, and cross-sectional designs (STROBE, n.d.; von Elm et al., 2007). For nursing students, this means clearly reporting the design, participants, variables, statistical methods, missing data, limitations, and noncausal interpretation.
Pearson Correlation vs Spearman Correlation
Pearson and Spearman both examine association, but they are used in different situations. Pearson correlation is best for continuous variables and linear relationships. Spearman correlation is often better when variables are ordinal, ranked, skewed, non-normal, or monotonic rather than linear.
Spearman correlation is not discussed in full here because this article focuses on Pearson correlation. However, nursing students should understand when Spearman may be safer.
Table 3. Pearson vs Spearman Correlation in Nursing Research
| Feature | Pearson correlation | Spearman correlation | Student decision point |
|---|---|---|---|
| Best for | Continuous variables | Ordinal, ranked, skewed, or non-normal variables | Check measurement level and distribution |
| Relationship type | Linear | Monotonic | Use scatterplots to inspect pattern |
| Coefficient | Pearson’s r | Spearman’s rho or rs | Report the correct symbol |
| Example | Adherence score and systolic blood pressure | Satisfaction rating and communication rating | Single Likert items often need caution |
| Assumption sensitivity | More sensitive to outliers and linearity violations | Less dependent on normality but still needs monotonicity | Do not choose automatically |
A single ordinal Likert item may fit Spearman better than Pearson. A multi-item scale total may sometimes be treated as approximately continuous, but the student should check assumptions and committee expectations. For the broader comparison, use the main guide on correlation analysis in nursing research.
Pearson Correlation vs Regression, T-Test, ANOVA, Paired Tests, and Chi-Square
Pearson correlation examines the linear association between two continuous variables. It is not the correct test for every quantitative nursing question.
Regression is more appropriate when the student wants to predict or explain an outcome using one or more predictors. StatPearls explains that correlation identifies the strength and direction of association, while regression predicts and explains a dependent variable from one or more independent variables (Wisniewski & Brannan, 2024).
A t-test is more appropriate when comparing two group means. ANOVA is more appropriate when comparing three or more group means. A paired t-test or Wilcoxon signed-rank test is more appropriate for pretest-posttest change. Chi-square is more appropriate when both variables are categorical.
Table 4. When Pearson Correlation Is Not the Right Test
| Research goal | Example question | Better test | Why |
|---|---|---|---|
| Compare two group means | Do intervention and control groups differ in anxiety scores? | Independent-samples t-test or Mann–Whitney U | The question compares groups |
| Compare three or more group means | Do burnout scores differ across three hospital units? | ANOVA or Kruskal–Wallis | The question compares more than two groups |
| Test pretest-posttest change | Did knowledge scores improve after education? | Paired t-test or Wilcoxon signed-rank | The question tests change over time |
| Examine categorical association | Is readmission status associated with medication adherence category? | Chi-square or Fisher’s exact test | Both variables are categorical |
| Predict an outcome | Do workload, burnout, and experience predict job satisfaction? | Regression | The question involves prediction or adjustment |
| Examine ordinal or skewed relationship | Is pain rating related to satisfaction rating? | Spearman correlation | Pearson assumptions may not fit |
This decision-making step is important for Chapter 3. A committee may ask not only what test you used, but why the test matched the research question and variables.
How to Run Pearson Correlation in SPSS
SPSS is commonly used for nursing dissertation statistics. This section provides a clear overview but not a screenshot-level tutorial.
A typical SPSS workflow includes preparing and cleaning the dataset, checking variable coding, checking questionnaire scoring, reviewing descriptive statistics, reviewing missing values, inspecting scatterplots, checking outliers, going to Analyze > Correlate > Bivariate, selecting the two variables, selecting Pearson, choosing two-tailed significance unless the study has a justified directional hypothesis, and reviewing Pearson correlation, significance value, and sample size.
IBM’s official Bivariate Correlations documentation states that SPSS computes Pearson’s correlation coefficient, Spearman’s rho, and Kendall’s tau-b with significance levels; it also identifies the menu path as Analyze > Correlate > Bivariate (IBM, n.d.-a).
Students should check assumptions before relying on output. The SPSS table is not the whole analysis. The student still needs to confirm that the variables are suitable, the relationship is linear, serious outliers are absent, and missing data are handled appropriately.
How to Run Pearson Correlation in Excel
Excel can calculate Pearson correlation using the CORREL function. Microsoft states that CORREL returns the correlation coefficient of two cell ranges and can be used to determine the relationship between two properties (Microsoft, n.d.-a). Microsoft also provides the PEARSON function, which returns the Pearson product-moment correlation coefficient, r, and reflects the extent of a linear relationship between two datasets (Microsoft, n.d.-b).
Excel can also produce correlation output through the Data Analysis ToolPak. Microsoft explains that the ToolPak can produce a correlation matrix that shows the value of CORREL or PEARSON for each possible pair of measurement variables (Microsoft, n.d.-c).
Excel can help with simple Pearson correlation, correlation matrices, scatterplots, preliminary data review, and basic descriptive checks. However, students should be cautious when relying only on Excel for dissertation-level analysis. Excel does not automatically provide all assumption checks, APA-ready interpretation, confidence intervals, advanced missing-data handling, or nonparametric alternatives in the same way dedicated statistical software can.
For broader Excel support, review Using Excel for Data Analysis. A separate article on How to Do Correlation Analysis in Excel for Nursing Research should cover the full Excel procedure without overloading this Pearson-focused guide.
How to Interpret Pearson Correlation Results
A strong interpretation of Pearson correlation should include more than “the result was significant.” Students should interpret the direction of the relationship, the strength of the relationship, the p-value, the sample size, the confidence interval where available, the practical or clinical meaning, whether the result answers the research question, and whether causation can or cannot be inferred.
Positive Significant Correlation
Example:
r(98) = .46, p < .001
Interpretation:
There was a statistically significant moderate positive relationship between nurse workload scores and burnout scores. Higher workload scores were associated with higher burnout scores.
Negative Significant Correlation
Example:
r(88) = −.41, p < .001
Interpretation:
There was a statistically significant moderate negative relationship between medication adherence scores and systolic blood pressure. Higher adherence scores were associated with lower systolic blood pressure.
Weak but Significant Correlation
Example:
r(248) = .16, p = .011
Interpretation:
There was a statistically significant but weak positive relationship. The association should not be overstated because the coefficient was small.
Moderate Non-Significant Correlation in a Small Sample
Example:
r(22) = −.39, p = .059
Interpretation:
The correlation was not statistically significant at the .05 level, although the coefficient suggested a moderate negative pattern. The small sample size may have limited statistical power.
Correlation With a Wide Confidence Interval
Example:
r(30) = .34, p = .058, 95% CI [−.01, .61]
Interpretation:
The result was not statistically significant, and the wide confidence interval suggests uncertainty about the population relationship. The true relationship could be very weak or moderately positive.
These examples show why interpretation should include the coefficient, p-value, sample size, confidence interval, and nursing meaning.
P-Values in Pearson Correlation
The null hypothesis in Pearson correlation usually states that there is no linear relationship between the two variables in the population. The p-value helps test how compatible the observed result is with that null hypothesis.
In many nursing dissertations, p < .05 is treated as statistically significant. However, the p-value does not show the strength of the relationship. It does not prove causation. It does not prove clinical importance. It is also affected by sample size.
For example, r = .18, p = .02 may be statistically significant but weak. A result of r = .45, p = .08 may be non-significant in a small sample but still worth discussing cautiously as a possible pattern or limitation.
The ASA statement on p-values warns that p-values do not measure effect size or the importance of a result and should not be used alone as the basis for scientific conclusions (Wasserstein & Lazar, 2016).
Statistical Significance vs Clinical Significance
Statistical significance and clinical significance are not the same. Statistical significance tells whether the relationship is unlikely under the null hypothesis. Clinical significance asks whether the relationship matters for nursing practice, patient outcomes, education, safety, or healthcare decision-making.
A weak correlation between nurse workload and medication errors may still matter if the outcome involves patient harm. A moderate correlation between health literacy and diabetes self-care may support patient-education planning, even if the study design does not prove causation.
Students should consider sample size, effect size, confidence intervals, clinical relevance, patient-care implications, measurement quality, study design, and practical significance.
Do not exaggerate weak correlations. Do not ignore clinically meaningful patterns just because a small pilot study did not reach statistical significance. Discuss results carefully and transparently.
Pearson Correlation and Correlation Matrix
A Pearson correlation matrix is a table showing Pearson correlations among several continuous variables. It is useful in Chapter 4 when a student has multiple relationship-based questions.
A correlation matrix may be used to examine relationships among stress, sleep quality, burnout, job satisfaction, medication adherence, blood pressure, quality of life, and health literacy.
A Pearson correlation matrix can also help before regression because very high correlations among predictors may suggest multicollinearity. However, students should avoid over-interpreting many correlations without clear research questions.
Missing data can also complicate a matrix. If pairwise deletion is used, each correlation may have a different sample size. Students should check and report valid n values where needed.
APA Style provides sample correlation-table guidance and emphasizes clear table setup and readable table notes (American Psychological Association, n.d.-a).
Table 5. Sample Pearson Correlation Matrix Layout
| Variable | 1 | 2 | 3 | 4 |
|---|---|---|---|---|
| 1. Medication adherence score | — | |||
| 2. Systolic blood pressure | −.41** | — | ||
| 3. Health literacy score | .36** | −.28* | — | |
| 4. Self-care behavior score | .48** | −.31* | .42** | — |
Note. Values are examples only. p < .05. p < .01. Replace with actual dissertation results.
How to Report Pearson Correlation in APA 7th Edition
APA reporting is one of the most important parts of Chapter 4. A good Pearson correlation write-up should be clear, complete, and noncausal.
Students should report the statistical test, variables being correlated, Pearson’s r, degrees of freedom where appropriate, p-value, sample size where helpful, 95% confidence interval where available or required, direction of the relationship, strength of the relationship, plain-language interpretation, missing-data handling if it affects valid n, and non-causal wording.
APA Style’s statistics guidance states that statistical symbols such as p, r, and R² should be italicized, and exact p-values should generally be reported when possible (American Psychological Association, 2024). APA Style also provides table setup guidance for clear table construction (American Psychological Association, n.d.-b).
APA Reporting Rules for Pearson Correlation
Use italic statistical symbols: r, p, N, M, and SD.
Report exact p-values where possible.
Use p < .001 when the value is very small.
Do not write p = .000.
Report confidence intervals if required or available.
Avoid causal words such as “caused,” “impacted,” “influenced,” or “effect” unless the design supports causal inference.
Use association language such as “was associated with,” “was related to,” or “showed a relationship with.”
A weak report says:
The correlation was significant.
A strong APA-style report says:
A Pearson correlation was conducted to examine the relationship between medication adherence scores and systolic blood pressure. The results showed a statistically significant negative relationship, r(88) = −.41, p < .001, indicating that higher medication adherence scores were associated with lower systolic blood pressure.
APA Write-Up Examples for Pearson Correlation
1. Significant Positive Pearson Correlation
A Pearson correlation was conducted to examine the relationship between nurse workload scores and burnout scores. The results showed a statistically significant positive relationship, r(96) = .52, p < .001. This finding indicates that higher workload scores were associated with higher burnout scores.
2. Significant Negative Pearson Correlation
A Pearson correlation was conducted to examine the relationship between medication adherence scores and systolic blood pressure among adults with hypertension. The results showed a statistically significant negative relationship, r(88) = −.41, p < .001. This finding indicates that higher medication adherence scores were associated with lower systolic blood pressure.
3. Non-Significant Pearson Correlation
A Pearson correlation was conducted to examine the relationship between age and patient satisfaction scores. The results showed a weak, non-significant positive relationship, r(46) = .16, p = .274. This finding indicates that age was not significantly associated with patient satisfaction scores in the sample.
4. Weak but Significant Pearson Correlation
A Pearson correlation was conducted to examine the relationship between health literacy scores and appointment adherence scores. The results showed a statistically significant but weak positive relationship, r(248) = .16, p = .011. Although the relationship was statistically significant, the strength of the association was weak and should be interpreted cautiously.
5. Pearson Correlation With Confidence Interval
A Pearson correlation was conducted to examine the relationship between sleep quality scores and academic stress scores among nursing students. The results showed a statistically significant negative relationship, r(78) = −.34, p = .002, 95% CI [−.52, −.13]. The confidence interval suggests that the population relationship may range from weak negative to moderate negative.
6. Pearson Correlation Matrix Summary
Pearson correlations were conducted to examine relationships among medication adherence, systolic blood pressure, health literacy, and self-care behavior. Medication adherence was negatively associated with systolic blood pressure, r(88) = −.41, p < .001, and positively associated with self-care behavior, r(88) = .48, p < .001. These findings suggest that higher adherence scores were associated with lower systolic blood pressure and higher self-care behavior scores, but causality cannot be inferred from the correlational design.
Sample Pearson Correlation Table for Chapter 4
Table 6. Sample APA-Style Pearson Correlation Results Table
| Variable pair | n | Pearson’s r | 95% CI | p-value | Direction | Interpretation |
|---|---|---|---|---|---|---|
| Medication adherence and systolic blood pressure | 90 | −.41 | [−.57, −.22] | < .001 | Negative | Higher adherence was associated with lower systolic blood pressure |
| Stress and sleep quality | 80 | −.34 | [−.52, −.13] | .002 | Negative | Higher stress was associated with poorer sleep quality |
| Burnout and job satisfaction | 98 | −.52 | [−.65, −.36] | < .001 | Negative | Higher burnout was associated with lower job satisfaction |
| Health literacy and self-care behavior | 120 | .39 | [.22, .54] | < .001 | Positive | Higher health literacy was associated with better self-care behavior |
| Age and satisfaction score | 48 | .16 | [−.13, .42] | .274 | Positive | Age was not significantly associated with satisfaction |
Note. n = valid paired cases; r = Pearson correlation coefficient; CI = confidence interval; p = probability value. Values are examples only.
Common Mistakes Nursing Students Make With Pearson Correlation
Using Pearson for Ordinal Data Without Justification
Pearson correlation may not be appropriate for a single ordinal Likert item. Students should consider Spearman correlation when variables are ordinal, ranked, skewed, or non-normal.
Ignoring Scatterplots
A scatterplot can reveal outliers, clustering, or non-linear patterns. Students should not rely only on the output table.
Ignoring Outliers
Outliers can inflate or weaken Pearson’s r. Students should verify unusual values and document how they were handled.
Failing to Check Normality
Pearson correlation is more defensible when variables are approximately normal, especially in small samples. Students should review histograms, Q-Q plots, and descriptive statistics.
Ignoring Sample Size
Small samples can produce unstable correlations. Large samples can make weak correlations statistically significant.
Interpreting P-Values Without Effect Size
A significant p-value does not mean the relationship is strong or clinically important.
Ignoring Confidence Intervals
Confidence intervals show uncertainty. A wide confidence interval suggests that the estimate may be imprecise.
Ignoring Missing Data
Students should check valid n values and explain missing-data handling when it affects results.
Confusing Pairwise and Listwise Deletion
Pairwise deletion can produce different sample sizes across a correlation matrix. Listwise deletion can reduce the sample sharply.
Claiming Causation
Pearson correlation does not prove cause and effect. Use association language.
Reporting Only P-Values
Always report Pearson’s r, direction, strength, and p-value.
Using Pearson When Regression Is Needed
Regression is more appropriate when the goal is prediction or adjustment for covariates.
Using Pearson When a Group-Comparison Test Is Needed
Use t-tests, ANOVA, paired tests, or chi-square when the research question requires those tests.
Using Unscored Questionnaire Items Instead of Scale Totals
Students should calculate scale totals or subscale scores according to instrument instructions.
Using One-Tailed Tests Without Justification
One-tailed tests should be planned before analysis and justified in the methodology.
Failing to Explain Results in Nursing Terms
A Chapter 4 result should explain what the relationship means for the nursing topic, not only the statistics.
How to Know Whether Pearson Correlation Is Right for Your Nursing Dissertation
Use this checklist before choosing Pearson correlation.
Am I examining the relationship between two variables?
Are both variables continuous or approximately continuous?
Are the variables measured on the same participants?
Is the relationship roughly linear?
Have I checked for serious outliers?
Are the data approximately normal, especially in small samples?
Is the sample size adequate for the planned analysis?
Do I understand how missing data will be handled?
Am I comparing groups instead?
Am I testing change over
time?
Am I predicting an outcome using multiple variables?
Would Spearman correlation be safer?
Can I report the result without causal language?
Table 7. Pearson Correlation Decision Guide
| Student situation | Use Pearson? | Better option | Reason |
|---|---|---|---|
| Two continuous variables with a linear pattern | Yes | Pearson correlation | Matches Pearson assumptions |
| Two ordinal variables | Usually no | Spearman correlation | Ordinal data may not fit Pearson |
| One binary variable and one continuous variable | Maybe | Point-biserial correlation | Better match for binary + continuous data |
| Two categorical variables | No | Chi-square or Fisher’s exact test | Pearson is not for two categorical variables |
| Pretest and posttest scores | No | Paired t-test or Wilcoxon signed-rank | The question tests change |
| Two or more groups compared on a mean score | No | t-test or ANOVA | The question compares groups |
| One outcome predicted from several variables | No | Regression | The question involves prediction or adjustment |
| Curved relationship | Usually no | Reconsider analysis or use another model | Pearson measures linear association |
Students who are unsure about test selection should get help before writing Chapter 4. Choosing the wrong test can lead to incorrect interpretation, weak methodology, and avoidable committee feedback.
Getting Help With Pearson Correlation Analysis in Nursing Research
Pearson correlation analysis may look simple, but it affects several parts of a nursing dissertation or capstone project. It affects Chapter 3 methodology, data cleaning, questionnaire scoring, assumption checking, SPSS output, Excel analysis, APA reporting, Chapter 4 tables, and Chapter 5 interpretation.
Nursing Dissertation Help can support students with Pearson correlation analysis, Spearman correlation analysis, SPSS correlation output, Excel correlation analysis, assumption checking, scatterplot interpretation, sample size and power guidance, confidence interval interpretation, missing-data handling, questionnaire scoring, correlation matrix interpretation, APA 7th reporting, Chapter 4 results writing, and dissertation statistics consultation.
If you already have a dataset, SPSS output, Excel file, questionnaire responses, or a Chapter 4 draft, expert support can help you choose the correct test, interpret the output accurately, and report the results in clear APA 7th format.
Conclusion
Pearson correlation analysis in nursing research is useful when students need to examine the strength and direction of a linear relationship between two continuous or approximately continuous variables. It can help answer research questions involving medication adherence and blood pressure, stress and sleep quality, burnout and job satisfaction, pain and quality of life, health literacy and self-care behavior, and many other nursing and healthcare variables.
However, Pearson correlation must be used responsibly. Students should check assumptions, review scatterplots, inspect outliers, consider sample size, understand missing data, interpret Pearson’s r, p-value, and confidence interval together, avoid causal language, and report results clearly in APA 7th edition.
If you are unsure whether Pearson correlation is the right test, or if you need help with SPSS, Excel, assumption checks, confidence intervals, APA tables, Chapter 4 results, or dissertation statistics interpretation, request expert help from Nursing Dissertation Help.
Frequently Asked Questions About Pearson Correlation Analysis in Nursing Research
What is Pearson correlation in nursing research?
Pearson correlation is a statistical test used to examine the strength and direction of a linear relationship between two continuous variables in nursing research.
When should I use Pearson correlation?
Use Pearson correlation when your research question asks about the relationship between two continuous or approximately continuous variables, the same participants provide data for both variables, and the relationship is roughly linear.
What type of variables are needed for Pearson correlation?
Pearson correlation usually requires two continuous or approximately continuous variables, such as blood pressure, age, stress scores, burnout scores, adherence scores, satisfaction scale scores, or quality-of-life scores.
What is the difference between Pearson and Spearman correlation?
Pearson correlation is used for continuous variables and linear relationships. Spearman correlation is often used for ordinal, ranked, skewed, or non-normal data and monotonic relationships.
Can Pearson correlation prove cause and effect?
No. Pearson correlation can show association, but it cannot prove cause and effect. A significant correlation does not prove that one variable caused another.
How do I report Pearson correlation in APA 7th edition?
Report the test, variables, Pearson’s r, degrees of freedom or sample size, p-value, confidence interval if available, direction, strength, and interpretation. Use noncausal wording.
Can I run Pearson correlation in Excel?
Yes. Excel can calculate Pearson correlation using the CORREL or PEARSON function and can produce correlation matrices through the Analysis ToolPak. However, students should be cautious because Excel may not provide all assumption checks, confidence intervals, missing-data diagnostics, or APA-ready interpretation.
What should I do if my data are not normally distributed?
If the variables are skewed, ordinal, ranked, or affected by outliers, Spearman correlation may be more appropriate. You should inspect distributions, scatterplots, and outliers before deciding.
What does a confidence interval for Pearson’s r mean?
A confidence interval gives a range of plausible values for the population correlation. A narrow interval suggests more precision, while a wide interval suggests more uncertainty.
How does missing data affect Pearson correlation?
Missing data can reduce the number of valid paired cases. If a participant is missing one of the two variables, that participant cannot be included in that Pearson correlation. Students should check valid n values and explain missing-data handling when necessary.
References
Akoglu, H. (2018). User’s guide to correlation coefficients. Turkish Journal of Emergency Medicine, 18(3), 91–93. https://doi.org/10.1016/j.tjem.2018.08.001
American Psychological Association. (n.d.-a). Sample tables. APA Style.
American Psychological Association. (n.d.-b). Table setup. APA Style.
American Psychological Association. (2024). Number and statistics guide. APA Style.
Brydges, C. R. (2019). Effect size guidelines, sample size calculations, and statistical power in gerontology. Innovation in Aging, 3(4), igz036. https://doi.org/10.1093/geroni/igz036
IBM. (n.d.-a). Bivariate correlations. IBM SPSS Statistics Documentation.
Microsoft. (n.d.-a). CORREL function. Microsoft Support.
Microsoft. (n.d.-b). PEARSON function. Microsoft Support.
Microsoft. (n.d.-c). Use the Analysis ToolPak to perform complex data analysis. Microsoft Support.
Mukaka, M. M. (2012). Statistics corner: A guide to appropriate use of correlation coefficient in medical research. Malawi Medical Journal, 24(3), 69–71.
Schober, P., Boer, C., & Schwarte, L. A. (2018). Correlation coefficients: Appropriate use and interpretation. Anesthesia & Analgesia, 126(5), 1763–1768. https://doi.org/10.1213/ANE.0000000000002864
STROBE. (n.d.). Strengthening the Reporting of Observational Studies in Epidemiology.
von Elm, E., Altman, D. G., Egger, M., Pocock, S. J., Gøtzsche, P. C., & Vandenbroucke, J. P. (2007). The Strengthening the Reporting of Observational Studies in Epidemiology Statement: Guidelines for reporting observational studies. Annals of Internal Medicine, 147(8), 573–577. https://doi.org/10.7326/0003-4819-147-8-200710160-00010
Wasserstein, R. L., & Lazar, N. A. (2016). The ASA statement on p-values: Context, process, and purpose. The American Statistician, 70(2), 129–133. https://doi.org/10.1080/00031305.2016.1154108
Welz, T., Doebler, P., & Pauly, M. (2022). Fisher transformation based confidence intervals of correlations in fixed- and random-effects meta-analysis. British Journal of Mathematical and Statistical Psychology, 75(1), 1–22. https://doi.org/10.1111/bmsp.12242
Wisniewski, S. J., & Brannan, G. D. (2024). Correlation coefficient, partial, and Spearman rank, and regression analysis. In StatPearls. StatPearls Publishing.
