BASICS OF HYPOTHESIS TESTING Flashcards
A claim or a statement about a property of a population
Hypothesis
The assumption about the population parameter
Hypothesis
Conjecture which may or may not be true
It could either be rejected or not rejected
Hypothesis
A standard procedure for testing a claim about a property of population
Hypothesis Test (Test of Significance)
the general goal of hypothesis testing
The general goal of hypothesis testing is to rule out chance or something
error a plausible explanation or the result of a research study, in that
case, the result is said to be statistically significant.
Hypothesis testing is one of 2 common forms of _____________
statistical inference
Identify a target population or study population, the population of interest.
You do _______________sampling then collect data from the
sample.
random or probability
From the collected data, ____________are determined or
calculated. And there used to make an inference or generalizations
about the ____________
sample statistics; population of interests
The goal of hypothesis testing has a form of ____________, is to
make a statements or generalizations regarding unknown ___________ based on sample data.
statistical inference; parameter
values
Statement that the value of a population parameter (e.g. proportion, mean,
or standard deviation) is equal to some claimed value (To the hypothesized
value)
Null Hypothesis (Ho)
β Uses equal symbol (=)
β Statement of equality
β A claim of no difference or of equality
Null Hypothesis (Ho)
the researchers in general hope to reject in favor of the other hypothesis
Null Hypothesis (Ho)
Either reject it or do not reject it
Null Hypothesis (Ho)
A statement that the parameter has a value that somehow differs from the
null hypothesis;
Alternative Hypothesis (Ha,HA, or H1)
use contradictory statement
β Uses one of these symbols: , β
β Also, at least (less than or equal) & at most (greater than or equal)
Alternative Hypothesis (Ha,HA, or H1)
what is the sign of at least
(less than or equal)
what is the sign of at most
(greater than or equal)
Identify the null and alternative hypotheses using the given claims:
The proportion of drivers who admit to driving under the influence of
alcohol is less than 0.5.
- P < 0.5 (claim)
- P β₯ 0.5
- Ho: p = 0.5
- Ha: p < 0.5
Identify the null and alternative hypotheses using the given claims:
The average number of calories of a lowβcalorie meal is at most 300.
- Β΅ β€ 300 (claim)
- Β΅ > 300
- Ho: Β΅ = 300
- Ha: Β΅ > 300
Identify the null and alternative hypotheses using the given claims:
The standard deviation of IQ scores of hospital employees is 15.
- Ho: Ο = 15 (claim)
* Ha: Ο β 15
A value used in making a decision (to whether or not to reject the null
hypothesis) about the null hypothesis and is found by converting the sample
statistic to a score with the assumption that the null hypothesis is true.
TEST STATISTIC
z test for mean can be used when n is ____, or when the population is
__________ and Ο is known. Otherwise, used t test equation
instead.
β₯ 30, normally distributed
The tails in a distribution are the extreme regions bounded by____________
critical value
Directional / One tailed
Left-tailed or Right-tailed
Non-directional
two-tailed
We can identify it by the _______________hypothesis wether you have a
right-tailed, left-tailed, or two-tailed test
alternative
Alternative hypothesis uses the symbols:
> , < , or, β
what tail is Less than (
Left-tailed
what tail is Greater than (>)
Right-tailed test
what tail has Inequality (β )
two-tailed test
(meaning the Ξ± is divided in the
opposite tails)
Consider the claim that the XSORT (in vitro fertilization) method of gender
selection increases the likelihood of having a baby girl. Preliminary results from
a test of the XSORT method of gender selection involved 14 couples who gave
birth to 13 girls and 1 boy. Use the given claim and the preliminary results to
calculate the value of the test statistic and test the claim at Ξ± = 0.05.
β H0: p = 0.5
β H1: p > 0.5 (right-tailed)
βͺ The CLAIM is on the ALTERNATIVE HYPOTHESIS (Ha)
πΜ= π πππππ πππππππ‘πππ = 13/14 = 0.929 z= 3.21
If the test statistic (zstat) is within the critical region = REJECT H0β
β zstat = 3.21 is within the critical region or beyond the z Critical = 1.645.
Therefore, we reject H0.
P-VALUE METHOD:
βIf P-value β€ Ξ± = REJECT H0β
β P-value β 1 β P(Z<3.21) = 1 - 0.9993 = 0.0007
β 0.0007 < 0.05 (Ξ±) = reject H0
There is not enough evidence to support the claim that the XSORT
method of gender selection increases the likelihood of having a baby girl.β
what is the decision if the test statistic (zstat) is within the critical region
= REJECT H0
If P-value β€ Ξ±, what is the decision
= REJECT H0
it is the βObserved Significance Levelβ
P-VALUE
what is the p-value of zstat = -1.82
P-value = 0.0344
what is the p-value of zstat = 2.23
P-value = 1 β 0.9871 = 0.0129
what is the decision if P-value β€ Ξ±,
reject H0
what is the decision if P-value > Ξ±
do not reject H0 / fail to reject H0 / retain H0
what is the decision If the test statistic falls within the critical region,
reject H0
what is the decision If the test statistic does not fall within the critical region
do not reject H0 / fail to reject H0 / retain H0
mistake of rejecting the null hypothesis when it is actually true.
Type I error
mistake of failing to reject the null hypothesis when it is actually false
Type II error
H0: New drug is no better than standard treatment
β’ H1: New drug is better than standard treatment
what is the type I error?
Concluding that the new drug is better than the standard (HA)
when in fact it is not (H0).
H0: New drug is no better than standard treatment
β’ H1: New drug is better than standard treatment
what is the type II error?
Failing to conclude that the new drug is better (HA) when in
fact it is
A survey claims that 9 out of 10 doctors recommend aspirin for their patients
with headaches. To test this claim, a random sample of 100 doctors is obtained.
Of these 100 doctors, 82 indicate that they recommend aspirin. Use Ξ± = 0.05
to test if the claim is accurate.
- Claim: p = 0.9 (p=proportion)
- 9 out of 10 β 90%
- counter claim: p οΉ 0.9
The probability that the test statistic will fall in the critical region when the null
hypothesis is actually true
SIGNIFICANCE LEVEL
- Also called as the rejection region
* Related and corresponds to ο‘
CRITICAL REGION
It encompasses all values beyond the critical value that will cause us to reject
the null hypothesis
CRITICAL REGION
If you have an alpha= 0.05, there is_____ in the right tail and ______ in the left
tail (area under the curve)
.025
If the test statistic falls under either tail
reject null hypothesis
Any value that separates the critical region from the test statistic that do not
lead to rejection of the null hypothesis
CRITICAL VALUE
Boundary between the non-rejection and rejection region
CRITICAL VALUE
Depends on the nature of the null hypothesis, whether it is left, right, or two-tailed test
CRITICAL VALUE
What is the critical z value given H1: p β 0.5 and Ξ± = 0.01?
Β±2.58
The standard deviation of heights of adult women is greater than 6.0 cm.
Ο > 6.0
What is the critical z value given H1: p < 0.5 and Ξ± = 0.05?
-1.645
A survey claims that 9 out of 10 doctors recommend aspirin for their patients
with headaches. To test this claim, a random sample of 100 doctors is
obtained. Of these 100 doctors, 82 indicate that they recommend aspirin.
Use =0.0.5 to test if the claim is accurate.
State the H0 and H1.
β’ Answer:
β H0: p = 0.9
β H1: p β 0.9
β Two-tailed test
State the level of significance, Ξ± and determine critical value. Ξ±. β’ Answer: β Ξ± : 0.05 β’ Z critical Value β Β±1.96
Compute the test statistic and find the P-value.
z = -2.67
P Value
P= P(Z β₯ z) = 0.0038
Decision: Reject H0
Conclusion: There is enough evidence to reject the claim that 90% of
doctors recommend aspirin for their patients with headaches