. You want to estimate what percentage of people in your town own a BMW. You call 100 people at random and ask them whether they own a BMW. Even assuming that everyone answers truthfully, why will you still not know accurately what percentage of people own BMWs?

Question

.  You want to estimate what percentage of people in your town own a BMW.  You call 100 people at random and ask them whether they own a BMW.  Even assuming that everyone answers truthfully, why will you still not know accurately what percentage of people own BMWs?

anonymous · Answer

yes

mrnood · Answer

is EVERY car owner in your town EQUALLY likely to be selected in your sample?

e.g. how many people did not pick up th e phone?
what time did you call? were most adult males at work then?
Did you want to know the proportion of 'households' or the proportion of 'people' - How many people did the answer cover ?

Can you see how many ways the data you collected may not be representative of 'all the people in your town'?

Sample bias is the MAIN fault with surveys... be very aware of it in class - AND in the real world - do not trust surveys un;less you know HOW the sample was selected....

anonymous · Answer

Thank you for your response.  truly appreciate it.