Scribd
Upload
10 views

Test Difference Between Two Averages

The document discusses testing the difference between two scores or samples. It provides instructions for filling in values for sample size, average, standard deviation, and other factors to determine if there is a significant difference between the samples. Various statistical terms are also defined such as confidence interval, confidence level, t-test, and z-test.

Uploaded by

nafis022
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as XLS, PDF, TXT or read online on Scribd
10 views

Test Difference Between Two Averages

The document discusses testing the difference between two scores or samples. It provides instructions for filling in values for sample size, average, standard deviation, and other factors to determine if there is a significant difference between the samples. Various statistical terms are also defined such as confidence interval, confidence level, t-test, and z-test.

Uploaded by

nafis022
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as XLS, PDF, TXT or read online on Scribd
You are on page 1/ 3

Test difference between two scores

Instructions: Fill in all of the gray boxes with the appropriate numbers for your data. The results will appear in the green box.

Sample or Group 1 Sample size 1 (# data points in group 1)= Average = Standard deviation 1 = 3100 31.68 7.29

Sample or Group 2 3000 32.15 11.37 = Sample size 2 (# data points in group 2) = Score 2 = Standard deviation 2

Level of confidence (i.e. 0.90 for 90%) = Difference between groups = Margin of error (+/-) = Confidence Interval =

0.95 0 0.478 (-0.5 ; 0.5) Is the difference significant at the 95% level of confidence? NO

Notes: - The sample size is the number of data points in the sample in the specific period you are analyzing. - The standard deviation can be determined in Excel using the STDEV function Assumptions: - Populations unknown; - Scores are normally distributed; - Groups or samples are INDEPENDENT

Definitions

Confidence interval The range around a survey result for which there is a high statistical probability that it contains the true population parameter. Confidence level The probability that a particular confidence interval will include the true population value. Tests of significance Tests for determining whether observed differences in a sample are sufficiently large as to be caused by something other than mere chance. T-test for means A statistical test used to determine whether a difference between two sample means is likely to reflect a real difference between the groups that the samples represent. Standard deviation A measure of the dispersion about the mean for a sample. The standard deviation is often denoted by the symbol s and is the square root of the variance. Z-test for proportions A statistical test used to determine whether a difference between two samples' proportions/percentages is likely to reflect a real difference between the groups that the samples represent.

How do we describe a statistically significant difference, if we find one?


When the z-score for two proportions or the t-score for two means reaches a certain level, we can say that the difference is statistically significant at the XX% (90%, 95%, 99%) level of confidence. What this means, in plainer language, is that we can be XX% sure that the difference we see between two samples reflects a real difference in the groups they represent.

Some Statistical Formulas

You might also like