Anomali Tespiti

Zaman Serisi · Anomali

Anomaly Detection is one of the statistical analyses automatically performed in MerQur. This page illustratively demonstrates, using a sample dataset from the field of Sport Sciences, how the analysis is applied, how the MerQur output appears, and how it is reported in APA 7 format.

🎯 What is it for?

Anomaly Detection automatically applies, in the background, all the assumption checks required for the relevant data type (normality, homogeneity of variance, etc.) and presents the results with a clear table + chart. Automatic interpretation to the APA 7 standard, effect sizes such as Cohen’s d/η²/R², and 95% confidence intervals are reported.

📌 When is it used?

In the statistical analysis of measurements in the field of Sport Sciences
To generate APA 7-compliant result tables for academic publication
In hypothesis testing and decision-making processes
After selecting an appropriate method in undergraduate / master’s / doctoral theses

📐 Assumptions

Appropriate scale — Variables must be at the scale level required by the analysis (nominal/ordinal/interval/ratio)
Independent observations — Observations must come from mutually independent individuals
Adequate sample — The minimum n requirement for the analysis must be met
Outlier check — Outliers must be detected and evaluated

If the assumptions are violated, MerQur automatically steers you toward a non-parametric or robust alternative.

🛠 How to do it in MerQur

Load the data. Select the sample file from the File → Open menu. MerQur automatically detects the column types.

Select the analysis. From the left sidebar, select Anomaly Detection.

Panel assignments (form fields in the program):

feature_cols: ['sporcu_id']
method: iqr
iqr_multiplier: 1.5
z_threshold: 3.0
mad_threshold: 3.5
contamination: 0.1
n_neighbors: 20

Optional settings. Effect size ✓ · 95% confidence interval ✓ · Assumption checks (automatic).

Press the ▶ Run button. Results are generated automatically as a table + chart.

📄 Export to Word. A report in APA 7 format with italic statistical symbols.

📊 Sample Dataset — Spor Bilimleri

ℹ Note: The MerQur output and interpretation tables on this page are illustrative and intended to help understand the analysis. The numerical results for your own data may differ; this page does not have to match the YouTube video walkthrough exactly.

🎬 Example File Used in the Video

The YouTube video walkthrough of this page was recorded for the Sport Sciences field using the sample file below:

MerQur_Hoca_Tanitim/Spor_Bilimleri/99_anomali_sporcu.xlsx

Topic: The application of the Anomaly Detection analysis on a real sample data set belonging to the Sport Sciences field.

Data Preview (First 5 Rows)

sporcu_id	VO2_max	kuvvet	antrenman	performans
1.00	51.20	63.90	15.70	66.80
2.00	55.10	94.60	11.10	76.30
3.00	58.20	88.60	18.60	72.00
4.00	41.80	91.00	7.20	77.30
5.00	68.00	72.60	19.00	83.40

n = 200 · Sütunlar: sporcu_id, VO2_max, kuvvet, antrenman, performans

MerQur Output (Illustrative)

ANOMALY DETECTION RESULT ───────────────────────────────────────────── Data: n = 200, 5 columns Test statistic: 12.43 p-value: < .001 Effect size: medium-large Detailed results are generated automatically with MerQur’s ▶ Run command.

MerQur Interpretation (Plain Language)

Anomaly Detection revealed a statistically significant finding among the relevant variables (p < .001). Detailed results and visuals are generated automatically in MerQur’s output panel.

APA 7 Interpretation (Academic Format · Illustrative)

According to the Anomaly Detection results, a statistically significant effect/relationship was observed on VO2_max (p < .001). The effect size was at a medium-to-large level, indicating that the findings carry practical significance. For a detailed report, MerQur’s APA 7 Word output can be used.

⚠ Common Mistakes

Specifying the data type incorrectly (e.g., loading a categorical variable as numeric)
Skipping the assumption checks and looking directly at the p-value
Not reporting the effect size — APA 7 requires both p and the effect size
Not applying a Type I error correction (Bonferroni/Tukey) in multiple comparisons
Not switching to a non-parametric alternative when n is insufficient

📹 Video Walkthrough

You can watch the video below for an end-to-end application of this analysis using the Sport Sciences file.

▶

The video will soon be uploaded to the MerQur YouTube channel

📺 MerQur YouTube Channel

🔀 The same analysis in other Main Fields:
🎓 Educational Sciences · 🧪 Natural Sciences and Mathematics · 🏛 Architecture, Planning and Design · ⚙ Engineering · 🏥 Health Sciences · 📊 Social, Humanities and Administrative Sciences · 🌾 Agriculture, Forestry and Aquaculture

📚 If You Used This Analysis, Cite MerQur

If you performed this analysis in a scientific study using MerQur, please use the following citation (APA 7) in accordance with the academic citation requirement:

Örücü, Ö. K. (2026). MerQur: An Integrated Academic Data Analysis and Reporting Platform [Computer Software] (Version 1.0.0). https://doi.org/10.53463/merqur.2026001

For BibTeX, RIS, EndNote and the English equivalent: all citation formats →

References:

American Psychological Association. (2020). Publication manual of the American Psychological Association (7th ed.).
Field, A. (2018). Discovering statistics using IBM SPSS Statistics (5th ed.). Sage.
Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd ed.). Lawrence Erlbaum.