Chi-square test - I do not understand the results :-&

  • Thread starter markecb
  • Start date
  • Tags
    Test
In summary, the conversation discusses the use of a chi-square test to examine the significance of differences in data. The first test shows a significant difference, while the second test does not apply a Yates correction and is only barely significant. The conversation also mentions using different statistical tests on the same data, which may yield different conclusions. The additional data provided includes the use of the chi-square test to examine differences based on gender and school achievement, and the results show no statistically significant differences based on gender. However, it is important to note that the test was not trying to prove that there was no difference, but rather to determine if there was a difference with 95% confidence.
  • #1
markecb
2
0
In one case I get the results as a significant difference in the other with the same dana, the difference is not significant.


Data sample
A B
I 5 8
II 4 28

http://imageshack.com/a/img542/467/o61k.jpg [Broken]

Same data and got significant difference

http://imageshack.com/a/img200/7366/y1le.jpg [Broken]

Where I'm wrong? :frown:
 
Last edited by a moderator:
Physics news on Phys.org
  • #2
The images don't say what kind of chi-square test is being done.

Try using various options for chi-square tests on the page http://graphpad.com/quickcalcs/contingency1/. Different statistical tests on the same data may give different conclusions.
 
  • #3
The second one says it does not apply a Yates correction. It's results are just barely significant at the 95% level. The first test may apply the correction and the result might become insignificant or it may use a different level than 95%.
 
  • #4
Thank you, here is little more data; I used chi-square (χ2) test to investigate the statistical significance of differences of opinion about the students offered the choice of extra-curricular activities with regard to gender and school achievement, ie the most recently completed assessment of students in the English language.

Can I (completed by SPSS) results interpreted as: no statistically significant differences based on gender.?

http://imageshack.com/a/img837/3372/0wv6.jpg [Broken]
 
Last edited by a moderator:
  • #5
The test tried to prove that there was a difference with 95% confidence. It barely succeeded by Pearson chi-squared and barely failed by the other statistics tests. You should NOT conclude that it proved there was no difference. It was not trying to prove that.
 

1. What is a Chi-square test?

A Chi-square test is a statistical test used to determine if there is a significant relationship between two categorical variables. It helps to analyze if the observed data fits the expected data and if any difference between the two is due to chance or a significant relationship.

2. How is a Chi-square test performed?

To perform a Chi-square test, you need to have two categorical variables and a large enough sample size. The first step is to create a contingency table with the observed frequencies for each variable. Then, calculate the expected frequencies based on the null hypothesis. Finally, use a Chi-square calculator or a statistical software to determine the Chi-square value and compare it to the critical value to determine the significance of the relationship.

3. What do the results of a Chi-square test mean?

The results of a Chi-square test indicate whether there is a significant relationship between the two variables or not. If the calculated Chi-square value is greater than the critical value, then we can reject the null hypothesis and conclude that there is a significant relationship between the variables. On the other hand, if the calculated Chi-square value is less than the critical value, then we fail to reject the null hypothesis and conclude that there is no significant relationship between the variables.

4. How can I interpret the p-value in a Chi-square test?

The p-value in a Chi-square test represents the probability of obtaining results as extreme or more extreme than the observed data, assuming that the null hypothesis is true. A small p-value (usually less than 0.05) indicates that the observed data is significantly different from the expected data and that we can reject the null hypothesis. A larger p-value suggests that the observed data is not significantly different from the expected data, and we fail to reject the null hypothesis.

5. What are some possible sources of error in a Chi-square test?

One possible source of error in a Chi-square test is having a small sample size, which may lead to inaccurate results. Another source of error is using incorrect data or assumptions in calculating the expected frequencies. It is also essential to ensure that the variables being tested are truly independent and not influenced by any other factors. Lastly, it is crucial to use a reliable Chi-square calculator or statistical software to perform the test accurately.

Similar threads

  • Set Theory, Logic, Probability, Statistics
Replies
1
Views
782
  • Set Theory, Logic, Probability, Statistics
Replies
5
Views
2K
  • Set Theory, Logic, Probability, Statistics
Replies
8
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
20
Views
2K
  • Set Theory, Logic, Probability, Statistics
Replies
2
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
7
Views
2K
  • Set Theory, Logic, Probability, Statistics
Replies
4
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
4
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
2
Views
2K
  • Set Theory, Logic, Probability, Statistics
Replies
4
Views
1K
Back
Top