Scribd
Upload
502 views3 pages

Hypothesis Testing Examples and Exercises

The document describes a hypothesis test conducted to analyze the effects of a drug on rats' response times. A neurologist administered a drug to 100 rats and recorded their response times. The mean response time was 1.05 seconds with a standard deviation of 0.5 seconds. The mean response time for untreated rats is 1.2 seconds. Two hypothesis tests were conducted: 1) a two-tailed test to determine if the drug had any effect, and 2) a one-tailed test to determine if the drug reduced response time. Both tests found a p-value less than the significance level of 0.05, allowing the null hypotheses that the drug had no effect/did not reduce response time to be rejected.

Uploaded by

Wess Sklas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
502 views3 pages

Hypothesis Testing Examples and Exercises

The document describes a hypothesis test conducted to analyze the effects of a drug on rats' response times. A neurologist administered a drug to 100 rats and recorded their response times. The mean response time was 1.05 seconds with a standard deviation of 0.5 seconds. The mean response time for untreated rats is 1.2 seconds. Two hypothesis tests were conducted: 1) a two-tailed test to determine if the drug had any effect, and 2) a one-tailed test to determine if the drug reduced response time. Both tests found a p-value less than the significance level of 0.05, allowing the null hypotheses that the drug had no effect/did not reduce response time to be rejected.

Uploaded by

Wess Sklas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Hypothesis Testing with One Sample

Examples
1. A neurologist is testing the effect of a drug on response time by injecting 100
rats with a unit dose of the drug, subjecting each to neurological stimulus, and
recording its response time. The neurologist knows that the mean response time
for rats not injected with the drug is 1.2 seconds. The mean of the 100 injected
rats response time is 1.05 seconds with a sample standard deviation of 0.5
seconds. (Significance level =5 .)
a. Do you think that the drug has an effect on response time? (It implies a
two-tailed test)
Step 1: Clearly state the null and alternative hypotheses.
H0: the drug has no effect or mean response time =1.2 .
H1 (Ha): the drug has effect or mean response time 1.2 .
Step 2:

The sample mean,

X s / n=

0.5
=0.05 .
100

X =1.05 ; n = 100; s = 0.5.

Step 3: z = (1.05 1.2)/0.05 = -3.


p-value = P(z < -3) + P(z > 3) = 2*NORM.S.DIST(-3, 1) = 0.0027 or 0.27%.
(two-tailed test)
If H0 is true, then the probability we see a result more extreme than 3
standard errors away from the population mean is 0.27%. In other words,
|>3SE =0.27 .
P( |X
Step 4: Significance level is 5%, which is greater than the p-value,
0.27%. (It is highly unlikely to see such a result if H 0 is true.)Thus we reject
H0 and conclude that the drug does have effect on response time (accept
H1).
b. Do you think that the drug can reduce response time? (It implies a onetailed test)
Step 1: Clearly state the null and alternative hypotheses.
H0: the drug cannot reduce mean response time or 1.2 .
H1 (Ha): the drug can reduce mean response time or <1.2 .
Step 2:

The sample mean,

X s / n=
Step 3:

0.5
=0.05 .
100

X =1.05 ; n = 100; s = 0.5.

z = (1.05 1.2)/0.05 = -3.

p-value = P(z < -3) = NORM.S.DIST(-3, 1) = 0.00135 or 0.135%. (onetailed test)


If H0 is true, then the probability we see a sample mean response time of
1.05 seconds or less is 0.135%.
Step 4: Significance level is 5%, which is greater than the p-value,
0.135%. (It is highly unlikely to see a sample mean response time of 1.05
seconds or less if H0 is true.)Thus we reject H0 and conclude that the drug
does reduce response time (accept H1).

Exercises
New tires manufactured by a company are designed to provide a mean of at least
30,000 miles. Tests with 30 randomly selected tires resulted in a mean of 31,000
miles and standard deviation of 2,000 miles. Using a 0.05 significance level, test
whether there is sufficient evidence to reject the claim of a mean of at least 30,000.
a. Clearly state your null and alternative hypothesis and determine this is a onetailed or two-tailed test.
b. Find sample mean, sample standard deviation and calculate standard error.
c. Compute z-score and corresponding p-value. Explain the meaning of this pvalue.
d. Draw your conclusion on whether there is sufficient evidence to reject the
claim of a mean of at least 30,000.

Step 1:
This is one
tailed test.
H0: the drug
cannot increase
mean response
time u<=1.2
H1 (Ha): the
drug increases
mean response
time or u>1.2

Step 2:
(Sample mean)
X-bar=1.05 ;
n = 100; s =
0.5.
Standard
error(SE) =
s/sqrt(n)=
0.5/sqrt(100)=
0.05

Step 3:
z
= (1.05 1.2)/0.05
= -3.
p-value = P(z > 3)
=1NORM.S.DIST(3, 1)
= 0.001349
Conclusion:- 1)
This is one tailed
(right tailed) test.
2)
Since pvalue<alpha , we
can reject H0.

You might also like