STATSTESTREVIEW

# STATSTESTREVIEW - O ne sample t test p value method 9 steps...

This preview shows pages 1–3. Sign up to view the full content.

One sample t test - p- value method ( 9 steps) and CI method ( 9 steps) Step 1 : state assumptions Assume we have an SRS of ( n individuals), we do not know the population standard deviation and we assume the population distribution of ( whatever we are measuring) … n> 40 – has not outliers 15<n40<- is symmetric with no outliers n<15 is normal with no outliers Steo 2: Define parameter of interest U= the true mean ( whatever were measuring) for all ( individuals) Step 3: give point estimate Pe= xbar= Step 4: state ho and ha Get ha first because it is what we are trying to prove. Ha = same number as h0 Pvalue methong steps 6-9 Step 6-Calculate the test statistic T= xbar- ho value _________________ s/ square root of n step 7- determine the pvalue look up t test statistic on t table with DF= n-1 ( will probably be between 2 values_ - if ha > or < look up t on table and get one sided p - if ha look up t on table and get the 2 sided p ex. N=30 so 30-1 = 29 and test statistic =2.74 pvalue is between .01 and .02 so .01< pvalue<.02 step 8 and 9- make a decision and state the conclusion - Because the pvalue < a = .05, we reject h0 - The same date indicate that the mean amount of money spent of shitty beer is not equal to 8\$ - If pvalue < a , reject ho - If pvalue > a , do not reject Ho - If do not reject Ho- the data do no rule out the possibility that Ho CI method- steps 6-9 Step 6: compute the margin of error ME= t*x s/square root of n ---- t* comes from t table- match conifidence level and df= n-1 Round ME to one more decimal than x bar Step 7: calcuate the interval lb and ub ( lb, ub)= ( xbar-ME, xbar+ME) --- round ib DOWN and ub UP with the same decimals as xbar step 8 and 9 Because the entire interval given is above/ not above the hypothesized mean of _____, we reject/do not reject H0 9. The same data do not rule out the possibility that the mean amount - if Ha > , reject Ho if the entire interval is obove the H0 value ( otherwise do not reject h0) - if ha < , reject Ho if entire interval is below H0 value ( otherwise , do not reject H0 - if ha doesn’t = , reject Ho if Ho value is NOT in interval ( otherwise, do not reject Ho) important note- if asked to JUST make a one sameple t-interval ( ie we are NOT asked to run a test using the C0 method just do steps 1-3 and 6-7 as out outlined above and then… last step: we are ( 95%) confident that the true mean ( whatever we are measuring) for all ( individuals) fa between ( lb) and ( up) EXAMPLE: suppose u = the true mean weight of all sumo wrestlers in pounds suppose our null and alternative are hp =u = 200 and ha:u > 200 if reject H0- the data indicate that the true mean weight of all sumo wrestlers is greater than 200 lbs if do not reject h0- The date do not rule of the possibility that the true mean weight of all sumo wresterlers is 200

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
sameple size ( always round up) if C goes up than ME goes up- of ME goes down C goes down formula n = (z*x s/me) ^2 if n goes up than ME goes down- if ME goes down M goes up
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 03/29/2011 for the course CLT 3370 taught by Professor Eaverly during the Spring '06 term at University of Florida.

### Page1 / 4

STATSTESTREVIEW - O ne sample t test p value method 9 steps...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online