# Help Required!

#### Lakshmanan Ramakrishnan

##### New Member
1. The average revenue per transaction in the population is Rs 614. Based on this attribute only, would you be confident that this sample is representative of the population?

Hint: Is the sample average different from the population average? If yes, how different based on statistical significance? Please note that sample size > 100

Type in the p-value of your hypothesis here, rounded to two decimals (0.xx)

Avg Revenue per transaction - Pop: 614
Avg Revenue per transaction - Sample: 590

Ho - Revenue per transaction for Population is same as Sample
Ha - Revenue per transaction for Population is not same as Sample

Which statistics test I need to use?

#### obh

##### Active Member
Hi Lakshmanan,
Did you try to solve the question? What direction did you try to go?

#### Suganya Kannan

##### New Member
Hi Lakshmanan,

Let me re-frame your hypothesis as,
Ho: There is no significance difference between the sample mean and the population mean
H1: There is a significance difference between the sample mean and the population mean

For this type,
You have to apply t-test to test the above hypothesis.

#### Lakshmanan Ramakrishnan

##### New Member
Hi Lakshmanan,

Let me re-frame your hypothesis as,
Ho: There is no significance difference between the sample mean and the population mean
H1: There is a significance difference between the sample mean and the population mean

For this type,
You have to apply t-test to test the above hypothesis.

I have mentioned sample size > 100, so we can't use T test.

#### Lakshmanan Ramakrishnan

##### New Member
Hi Lakshmanan,
Did you try to solve the question? What direction did you try to go?
Yes, I used normal distribution.

#### Suganya Kannan

##### New Member
I have mentioned sample size > 100, so we can't use T test.
Then you can use z test. The t test as compared with z test is its advantage for small sample comparison. As n increases, t approaches to z. The advantage of t test disappears, and t distribution simply becomes z distribution. In other words, with large n. t test is just close to z test. and one don't loose anything to continue to use t test. In the past, for convenience, we use z table when n > 30. We don't have to do it anymore. In fact, all statistical packages use t test even n is large. This is easy, convenience with computer programming, and is correct. All statistical packages are good references.

#### Lakshmanan Ramakrishnan

##### New Member
Thank you Suganya!... Can I use normal distribution to solve this problem?

#### Lakshmanan Ramakrishnan

##### New Member
Thank you Suganya! for your reference

#### obh

##### Active Member
I have mentioned sample size > 100, so we can't use T test.
Generally, If you use sample standard deviation you should the t-test and if you use the population standard deviation you should use the Z test.

When the sample size > 30 you still can use the t-test, but using z-test will give almost as good results.
A long time ago in a place far away people use tables, so when the sample size was bigger than 30 it was easier to use the smaller more detailed Z table ...

With a big sample size, t distribution value approaches to normal distribution value
http://www.statskingdom.com/t_test.html

Last edited: