Mastering McNemar’s Test Using SPSS Statistics – Mastering SPSS






McNemar’s Test is a non-parametric test used on paired nominal data. It is applied to determine whether the row and column marginal frequencies are equal, which is useful in “before-after” studies or matched pairs of subjects. This tutorial will guide you through conducting McNemar’s Test using SPSS Statistics with real-time variables and provide results interpretation following APA style.

Understanding McNemar’s Test

McNemar’s Test is used when you have paired nominal data, typically in a 2×2 contingency table. It assesses the differences between two related proportions. For instance, it can be used to evaluate the effectiveness of a treatment by comparing the number of successes and failures before and after the treatment.

Assumptions

Before running McNemar’s Test, ensure your data meets these assumptions:

  • Paired samples: The data should consist of paired observations, such as pre-test and post-test scores.
  • Dichotomous outcome: The outcome variable should be dichotomous (e.g., success/failure).

Step-by-Step Guide to Conducting McNemar’s Test in SPSS

Step 1: Load Your Data

First, you need to enter your data into SPSS. For this example, we have a dataset with two variables: pre_treatment and post_treatment, both coded as 0 for failure and 1 for success.

Step 2: Open the Data

Open your data in SPSS. Go to the Data View tab to ensure your data is correctly entered.

Step 3: Access the Crosstabs Function

Navigate to Analyze > Descriptive Statistics > Crosstabs. Move pre_treatment to the Rows box and post_treatment to the Columns box.

Step 4: Conduct McNemar’s Test

Click on the Statistics button, check the box for McNemar, and click Continue. Then click OK to run the test.

Interpreting the Results

After running McNemar’s Test, SPSS will produce an output table. Below is an example of how to interpret the results using APA style.

Results Table

Post-Treatment
Pre-Treatment Failure Success Total
Failure 30 10 40
Success 5 55 60
Total 35 65 100

In this example, the McNemar test statistic is calculated as follows:

\[ \chi^2 = \frac{(b – c)^2}{b + c} \]

Where:

  • \( b \) = Number of cases where pre_treatment = 0 and post_treatment = 1 (10)
  • \( c \) = Number of cases where pre_treatment = 1 and post_treatment = 0 (5)

Using these values, we get:

\[ \chi^2 = \frac{(10 – 5)^2}{10 + 5} = \frac{25}{15} = 1.67 \]

Compare this value to the critical value from the chi-square distribution table with 1 degree of freedom at the desired significance level (usually 0.05). If the test statistic exceeds the critical value, we reject the null hypothesis.

Conclusion

In our example, the McNemar’s Test statistic is 1.67. If our critical value is 3.84 (for α = 0.05), we do not reject the null hypothesis, indicating no significant difference between the pre-treatment and post-treatment conditions.

Practical Application

McNemar’s Test is useful in various fields, including psychology, medicine, and social sciences. For instance, it can be used to assess the effectiveness of a new therapy or intervention by comparing pre- and post-intervention outcomes.

Further Reading

For more detailed tutorials on different statistical tests using SPSS, check out the following posts:

References

For more information on McNemar’s Test and other statistical analyses using SPSS, refer to the following resources:


Similar Posts

Leave a Reply

Your email address will not be published. Required fields are marked *