9.4.15 Parametric and Non-Parametric Data
Warning: Attempt to read property "ID" on null in /home/990584.cloudwaysapps.com/hvcgdwcmdt/public_html/wp-content/plugins/sfwd-lms/themes/ld30/templates/topic.php on line 80
Describes Hypothesis Testing as Applied to Parametric and Non-Parametric Data
Hypothesis testing is a statistical method used to determine the likelihood of a hypothesis being true based on the available data. It involves two hypotheses: the null hypothesis and the alternative hypothesis. The null hypothesis (H0) is the hypothesis that there is no significant difference between the observed data and the expected values, while the alternative hypothesis (H1) is the hypothesis that there is a significant difference between the observed data and the expected values.
Parametric data:
Parametric data refers to data that follow a normal distribution, while non-parametric data refers to data that do not follow a normal distribution. The choice of hypothesis testing method depends on the type of data being analyzed.
For parametric data, the most commonly used hypothesis testing method is the t-test. The t-test is used to determine if the mean of a sample is significantly different from a known or hypothesized population mean. Clinical examples of parametric data include the analysis of blood pressure, serum cholesterol levels, and body mass index.
Non-parametric data:
For non-parametric data, the most commonly used hypothesis testing method is the Wilcoxon rank-sum test or Mann-Whitney U test. This test is used to determine if there is a significant difference between the median values of two independent groups. Clinical examples of non-parametric data include the analysis of pain scores, quality-of-life assessments, and symptom severity ratings.
| Parametric Tests | Non-Parametric Tests | |
| Assumption of data distribution | Assumes a normal distribution | No assumption of data distribution |
| Type of data | Assumes interval or ratio data | Assumes nominal or ordinal data |
| Examples | T-test, ANOVA, Pearson’s correlation, Linear Regression | Mann-Whitney U test, Wilcoxon signed-rank test, Kruskal-Wallis test, Spearman’s correlation |
| Strengths | High statistical power, more efficient | Robust to outliers and non-normal data, easier to interpret |
| Weaknesses | Sensitive to outliers and non-normal data, more complex to use | Lower statistical power, less efficient |
In hypothesis testing, the p-value is used to determine the level of statistical significance. The p-value is the probability of obtaining a result as extreme as the observed result if the null hypothesis is true. A p-value of less than 0.05 is considered statistically significant, indicating that the null hypothesis can be rejected in favour of the alternative hypothesis.
Overall, hypothesis testing is an important tool in clinical research, allowing researchers to draw conclusions about the significance of their findings and make informed decisions regarding patient care.
References:
- Gardner, M. J., & Altman, D. G. (1986). Confidence intervals rather than P values: estimation rather than hypothesis testing. BMJ (Clinical research ed.), 292(6522), 746–750. https://doi.org/10.1136/bmj.292.6522.746