Assignment: Inferential and Hypothesis Testing by Amith C

Problem Statement
Comprehension

The pharmaceutical company Sun Pharma is manufacturing a new batch of painkiller drugs,
which are due for testing. Around 80,000 new products are created and need to be tested for
their time of effect (which is measured as the time taken for the drug to completely cure the
pain), as well as the quality assurance (which tells you whether the drug was able to do a
satisfactory job or not).

Question 1:

The quality assurance checks on the previous batches of drugs found that — it is 4 times more
likely that a drug is able to produce a satisfactory result than not.

Given a small sample of 10 drugs, you are required to find the theoretical probability that at
most, 3 drugs are not able to do a satisfactory job.

a.) Propose the type of probability distribution that would accurately portray the above scenario,
and list out the three conditions that this distribution follows.
b.) Calculate the required probability.

Answer:

From the previous batch of drugs, probability of drug producing result is: 4 success and 1
failure.

Probability of failure = p = 1/5 = 0.2.

Given samples is 10. So n=10.
We need to find the probability of at most 3 drugs are not able to do a satisfactory job.

For the above scenario, probability distribution is discrete and we need to use ​Binomial
Probability Distribution ​ to calculate the result.

3 Conditions which the distribution follows is

1. Result is either success or failure.
2. Total number of trial is fixed.
3. Success or failure rate is same for all the trials.

Need to find P(n<=3)

P(n<=3)=P(0)+P(1)+P(2)+P(3)
P(n<=3)=P(0)+P(1)+P(2)+P(3)
= 0.107+0.268+0.302+0.201
= 0.878

Probability of at most 3 drugs are not able to do a satisfactory job is 0.878.

Question 2:

For the effectiveness test, a sample of 100 drugs was taken. The mean time of effect was 207
seconds, with the standard deviation coming to 65 seconds. Using this information, you are
required to estimate the range in which the population mean might lie — with a 95% confidence
level.

a.)Discuss the main methodology using which you will approach this problem. State all the
properties of the required method. Limit your answer to 150 words.
b.)Find the required range.

Answer:

Number of samples = 100

Mean time of samples = x̅ = 207
Standard Deviation = s = 65

Need to ​estimate the range in which the population mean might lie — with a 95% confidence
level.

The probability is measured here as a continuous variable(time). So we need to use continuous

probability distribution to calculate the result.

Since the number of samples is more than 30, the sampling distribution becomes normal
distribution. We can use the Central Limit Theorem to calculate the confidence interval for a
confidence level of 95%.

Confidence Interval= (​x̅-(Z*s)/√n) to (​x̅+(Z*s)/√n)

For a confidence level of 95% ,Z=1.96

CI=(207-(1.96*65)/√100) to (207+(1.96*65)/√100)
=(194.26 to 219.74)
Question 3:

a) The painkiller drug needs to have a time of effect of at most 200 seconds to be considered as
having done a satisfactory job. Given the same sample data (size, mean, and standard
deviation) of the previous question, test the claim that the newer batch produces a satisfactory
result and passes the quality assurance test. Utilize 2 hypothesis testing methods to make your
decision. Take the significance level at 5 %. Clearly specify the hypotheses, the calculated test
statistics, and the final decision that should be made for each method.

b) You know that two types of errors can occur during hypothesis testing — namely Type-I and
Type-II errors — whose probabilities are denoted by α and β respectively. For the current
sample conditions (sample size, mean, and standard deviation), the value of α and β come out
to be 0.05 and 0.45 respectively.

Now, a different sampling procedure(with different sample size, mean, and standard deviation)
is proposed so that when the same hypothesis test is conducted, the values of α and β are
controlled at 0.15 each. Explain under what conditions would either method be more preferred
than the other, i.e. give an example of a situation where conducting a hypothesis test having α
and β as 0.05 and 0.45 respectively would be preferred over having them both at 0.15. Similarly,
give an example for the reverse scenario - a situation where conducting the hypothesis test with
both α and β values fixed at 0.15 would be preferred over having them at 0.05 and 0.45
respectively. Also, provide suitable reasons for your choice(Assume that only the values of α
and β as mentioned above are provided to you and no other information is available).

Answer:

Part A:
From the above question,

Null hypothesis is : H0 : μ<= 200.

Alternate hypothesis is : H1 : μ> 200.
x̅=207
S=65
n=100
α=0.05
x=1-0.05=0.95
It is an upper tailed test.

We shall use ​Critical Value Method ​to test the hypothesis.

Since σ is​ not available, ​σ=S=65.

So Z(for x=0.95) from Z table is 1.645

Standard error ​σx̅​ = σ / √n = 65/√100=6.5

So Critical Value(CV)= μ+Z*​σx̅​

CV=200+1.645*6.5
=210.7

Since x̅=207, which is within the range of critical value of 210.7.

So by using critical value method,we fail to reject the null hypothesis(H0).

Now we shall use ​P Value ​method to test the Hypothesis:

Z=(x̅-μ)/σ​x̅
=(207-200)/6.5
=1.08

p(for Z=1.08) from z table is 0.1401.

Since 0.1401>0.05, ​we fail to reject the null hypothesis(H0) using P value method.

Part B:

The Type-1 error for the above test is , if the painkiller drug is producing satisfactory result but
we still go ahead and certify that painkiller drug is not suitable for use.

The Type-2 error for the above test is , if the painkiller drug is not producing satisfactory result
but we still go ahead and certify that painkiller drug is suitable for use.

The value of α and β for the above test is 0.05 and 0.45 respectively. With lower value of α, the
occurrence of type-1 error can be reduced. And with lower value of β,the occurrence of type-2
error can be reduced. With decrease in value of α ,β will increase and vice versa. In the above
case, the occurrence of type-2 error will be more.
That is we will be rejecting many samples of painkiller drug even though it is producing
satisfactory results.It is recommended if any side effects or health issues are observed by
consuming the drugs which is not good for use, decreasing the α value is recommended.

Now if we conduct one more hypothesis test with value of α and β at 0.15 each, the results
obtained will be different. The probability of occurrence of type-2 error will reduce and inturn, it
will increase the probability of occurrence of type-1 error.
This is accepted/preferred if there are no/very less side effects of consuming the painkiller drug
which is not suitable for use.
Question 4:

Now, once the batch has passed all the quality tests and is ready to be launched in the market,
the marketing team needs to plan an effective online ad campaign to attract new customers.
Two taglines were proposed for the campaign, and the team is currently divided on which option
to use.

Explain why and how A/B testing can be used to decide which option is more effective. Give a
stepwise procedure for the test that needs to be conducted.

Answer:

2 taglines were proposed for the painkiller drug for marketing purposes. A/B testing needs to be
done to test which result is more suitable.

1. Identify 2 suitable taglines for marketing purposes and prepare 2 different ads for the
product.
2. Identify 2 regions/cities where sales of this painkiller drug is almost the same for
previous quarter.
3. Push the 2 previously created online ads , one for each region.
4. After 1 month, get the value of sales for these 2 regions for the painkiller drug.
5. Based on the performance figures, A/B testing needs to be conducted to check how both
the regions are performing in terms of sales.
6. We need to validate is there is a considerable difference in sales for these 2 regions or
the difference is negligible.
7. Based on the results of the previous step, we need to choose the ad campaign which
was more successful in generating sales in the previously selected 2 regions.
8. By doing this test we can conclude that which of the 2 online ad campaign is attracting
most of the customers in buying the product and same online add can be continued
further for future ad campaign.
9. Rather than pushing the new online ad campaign in the entire country and testing its
outcome, A/B testing is more convenient. Any negative effects or issues with the ad will
be limited to only one region and its effects or repercussions can be managed or
negated with minimal efforts.