<p>Alicimoo is correct. you can only reject or fail to reject the null hypothesis. It is not possible to prove a null hypothesis.</p>
<p>I think its Type II. The test did not reject the null, but came pretty close, so there is a probability that the power was not high enough and we ended up not rejecting the null when we really should have.</p>
<p>It cannot be a Type I error since we did not reject the null.</p>
<p>“A null hypothesis is never proven by such methods, as the absence of evidence against the null hypothesis does not establish it. In other words, one may either reject, or not reject the null hypothesis; one cannot accept it. Failing to reject it gives no strong reason to change decisions predicated on its truth, but it also allows for the possibility of obtaining further data and then re-examining the same hypothesis.” </p>
<p>Quote wikipedia.com</p>
<p>you can not “accept” a null hypothesis as true… you can either have enough evidence to reject your null hypothesis and consider your alternative hypothesis to be “more true” than your null hypothesis
or you can fail to reject your null hypothesis
it is unreasonable to say that you “accept” either of the hypotheses</p>
<p>It is most definitely Type II
in part a, we did not reject the null
therefore the only error we could have committed was that the null was false and we did not reject it which is a TYPE II error!
a type I error can only occur if we rejected the null and the null was, in reality, true</p>
<p>Whether or not you can accept the null hypothesis, it was still “favored” in this case.</p>
<p>“It has to be Type I because according to the test, null is true, so the mistake that can be made is rejecting the null and accepting the alt when null is true.”</p>
<p>ACCORDING TO THE TEST the null is true so we did not reject it, but the test may be false becasue it was only a sample
HOWEVER, in reality, the null may in fact BE FALSE therefore it was a type II error
alicimoo is thinking about it the wrong way</p>
<p>Type I error is when you ASSUME the null is false when it is really true.</p>
<p>
meh…</p>
<p>Anyways, if it really is Type II, it’d work in my favor, because I put down Type II but forgot to change it to Type I. x_x</p>
<p>From Barron’s study guide: Type I error: mistakenly rejecting a true Ho
Type II error: a mistaken failure to reject a false Ho</p>
<p>Since the Ho is assumed true (we failed to reject it, p-value>a (.0761>.05)) type I error is the only possible mistake that can be made.</p>
<p>EDIT: This is not the case…i thought about it more and of course it’s type II that can be made.</p>
<p>ohhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh****. i just realized why its Type II…nevermind. God ■■■</p>
<p>I still don’t get it, if it really is Type II…I think my brain is being fried by all these APs.</p>
<p>the reason is because we failed to reject Ho. In the case of failing to reject a Ho, the only possible error is a type II error.</p>
<p>It’s a Type II error! I memorized that and Type I error right before the test lol
Reject the null hypothesis when it’s true = Type I
Fail to reject the null hypothesis when it’s false = Type II</p>
<p>If it isn’t, ■■■. xD</p>
<p>just fyi…the free response questions are posted online now at </p>
<p><a href=“Supporting Students from Day One to Exam Day – AP Central | College Board”>Supporting Students from Day One to Exam Day – AP Central | College Board;
<p>Now time for a question: does question 4b require a significance test?</p>
<p>…oohhhh…</p>
<p>Maybe there’s still hope for me.</p>
<p>…I misread the question for 4a and put down 2 CIs, one for each fire station…ugh eff.</p>
<p>For 4b I just wrote out a null and alternative hypothesis and stated that since zero was in the confidence interval there was no evidence to prove that there was a difference between the response times of the two fire departments.</p>
<p>NYEM - Same here!!! I did everything right but I used a 2-sample z-interval test. 
Still got that though. :)</p>
<p>I wonder if they would still give me credit? I’ve heard they’re lenient on FRQ’s…</p>
<p>Hey guys, I got a type II error for the question as well and im pretty darn sure of it!</p>
<p>Also, for the "make your own statistic’ I just flipped the given fraction.
(ex. if they gave mean/median, my stat would be median/mean)</p>
<p>Is that ok?</p>
<p>What is the probability that at least 2 cars out of 5 randomly selected cars in the study will stop in a distance that is greater than the distance calculated in part (a)?</p>
<p>How do you do this?</p>
<p>As for question 1, for the graph I used a bar graph, with the proportion of the male population against the proportion of female population for each of the three job experience categories. For part c I said that we would perform a chi square test for independence with a null that there was no association between the two variables and an alternative that there was an association.</p>
<p>For part b of question 2, I used binomial CDF with a probablity equal to .3 (if a distance was greater than the distance calculated in part a, which was the 70th percentile, it would occur 30 percent of the time) and a range from 2 to 5.</p>