Biostatistics Tutorial Week 4

What is true about sampling from a population?

• Researchers prefer convenient sampling over random sampling as the latter is more time-consuming

• We cannot obtain the real/true population parameters

• We use population parameters to infer sample characteristics

• Population mean is represented by the Greek letter π

What is NOT true about the standard error of the mean:

• The larger the sample size, the smaller the standard error

• The larger the sample size, the larger the standard error

• The larger the sample size, the more confident we are that our estimated mean is closer the true population mean  

• The standard error of the mean can be calculated using z x 1.96

What is true about the sampling distribution?

• If we draw 100 different samples from the same population, the means would be the same

• Researchers often re-sample the same population multiple times in order to achieve the most reliable estimates

• Theoretically, the mean of the sampling distribution will be exactly the same as the population mean

• Theoretically, the mean of the sampling distribution will unlikely be the same as the population mean

What should we NOT do if we want to reduce sampling variability?

• Reduce the sample size

• Use random sampling

• Use a larger sample

• Use better measurement tools like standardised questionnaires

Why does larger sample size lead to a smaller standard error of the mean?

• It's more difficult to capture each participants' characteristics in a larger sample

• Larger samples provide more information about the population

• We are more confident with obtaining detailed information with a smaller sample

• Trick question, larger sample size doesn't lead to smaller SEM

You need the mean, sd, and n to calculate standard error of the mean, but you only need the proportion and n to calculate standard error for a proportion

• TRUE

• FALSE