Posted: 9/28/2011 5:22:43 PM EDT
|
Can someone please help me interpret this data? Specifically, which p-value am I using and how do I decide whether or not to reject the Null Hypothesis based on the t-value ttest atotinc = 9100 One-sample t test –––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––– Variable | Obs Mean Std. Err. Std. Dev. [95% Conf. Interval] ––––––––-+–––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––– atotinc | 1989 5195.55 118.145 5269.056 4963.848 5427.251 –––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––– mean = mean(atotinc) t = -33.0480 Ho: mean = 9100 degrees of freedom = 1988 Ha: mean < 9100 Ha: mean != 9100 Ha: mean > 9100 Pr(T < t) = 0.0000 Pr(|T| > |t|) = 0.0000 Pr(T > t) = 1.0000 |
|
Okay...what exactly are you trying to do? There is no hypothesis testing with a 1-sample T-test. Testing a hypothesis involves comparing two sets of similar data to see if they are significantly different (rejecting the null) or they are not significantly different (failing to reject the null). This is not accomplished with a 1-sample T-test.
|
|
Quoted: Okay...what exactly are you trying to do? There is no hypothesis testing with a 1-sample T-test. Testing a hypothesis involves comparing two sets of similar data to see if they are significantly different (rejecting the null) or they are not significantly different (failing to reject the null). This is not accomplished with a 1-sample T-test. Running a simple ttest that the average total income (atotinc) was 5000 |
|
Quoted: Quoted: Okay...what exactly are you trying to do? There is no hypothesis testing with a 1-sample T-test. Testing a hypothesis involves comparing two sets of similar data to see if they are significantly different (rejecting the null) or they are not significantly different (failing to reject the null). This is not accomplished with a 1-sample T-test. Running a simple ttest that the average total income (atotinc) was 5000 Okay so...1 set of data? A one sample t-test is just giving you information on the distribution. There is no hypothesis testing with it. Now...say you had data from city A and city B, run a 2-sample t-test = hypothesis testing possible. I guess the biggest thing to pull from there is the mean and std dev...
|