Scribd
Upload
13 views

Unit 20 - Assignment Without Answers

Uploaded by

z13612909240
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
13 views

Unit 20 - Assignment Without Answers

Uploaded by

z13612909240
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Assignment unit 20:

First steps towards inference - certainty about


means
In this assignment, you will learn why you can say something about a population
characteristic using data from a random sample from that population (inference) and
how you can use the sampling distribution for this.
Statistic; Parameter; Inference ; Population distribution; Sample distribution; Sampling
distribution; Central limit theorem
Read this assignment carefully and answer all questions.
Hand in the assignment via Canvas.

1) In a previous assignment you were asked to visit the website:


http://onlinestatbook.com/stat_sim/sampling_dist/

Click on ‘begin’ (or read the instructions first)

On top, we see a ‘population’ measured by one single ratio variable. This population is described by
population parameters (we focus on mean, median and standard deviation). Although population
parameters are generally unknown, here we pretend that we know them. With the mouse, you can
change this distribution.

A box next to the third graph says ‘n = 5’ (you can change that). That is the size of the random sample
we are going to pick (n=5). In this third graph, we will later see the mean of the sample.

Click on ‘animated’, and see that a simple random sample from the population is selected. This is of
course based on the first distribution: the likelihood that elements from ‘the middle’ are selected is
bigger than elements from areas where there is no peak.

Click on ‘animated’ a couple of more times, and see that the mean of each sample is shown in the
third graph.

a. What is the distribution called in the first graph? ….


b. What is the distribution called in the second graph? ….
c. What is the distribution called in the third graph? ….

The distribution of the fourth graph is free to choose. The default is none. You can choose mean,
median, SD, variance, range, etcetera (also for the third graph, but we will not change this).

d. Which of these distributions is known by the researcher in most research projects?

2) The mean and the standard deviation in the first graph are normally described by a specific type of
characters. Which characters, Greek or Latin? And how are they called?

1
3) The mean and the standard deviation in the second graph are normally described by another
specific type of characters. Which characters? And how are they called?

Start a new session (by clicking on ‘Begin’) and change the boxes next to the third and fourth graph
so that sample sizes of 25 units will be drawn for the population distribution. Be sure not to confuse
sample size with number of samples. Click the ‘animated’ button and a first sample of 25 units is
drawn from the population (sample size: n=25) and 25 values are presented in the second graph. The
mean of these 25 values is shown in the third graph (blue box).

Click the ‘animated’ button again. The first graph is cleared and a second sample of 25 units is drawn.
The mean value of the second sample is added in the third graph as another blue box.

4) The means of the two samples might be somewhat different from each other and from the
population mean. Why?

5) Imagine the population is a distribution of the variable ‘height’ (in some unknown measure, so not
‘meters) ranging between 0 and 32 (we assume the height in the population is normally distributed).
Start a new session (by clicking on ‘Begin’) and select samples of two (n = 2) in the third graph. Select
n = 25 (samples of 25) in the fourth graph (the output should be ‘mean’) and click on 10.000.
a. Explain what you have done in plain language.

b. What differences do you observe with respect to the mean and the standard deviation in
graph 3 and 4?

c. Which formula is used to describe the standard deviation of the third and fourth graph?

d. Use the formula to compute the standard deviation of the third and fourth distribution. Are
the computed values the same as the values on the website?

6) Click on ‘Clear lower 3’. Then, create the weirdest distribution you can think of by using the
mouse. For example, this one:

a. Again create different sampling distributions from that population (use sample sizes 16 and
25 and click on 10.000). What do you see?

b. What is this phenomenon called?

2
7) Normally the parameters µ and σ are unknown, but just suppose that for a certain distribution we
know: µ is 16 and σ is 5 (population A).

a. What do µ and σ stand for?

b. Write down the mean and the standard deviation of the sampling distribution of the mean for
n = 25.
c. In this sampling distribution, where can you find the 95% of the sample means that are closest
to the population mean? For this you need to recall the normal distribution (see the slides of the
powerpoint of Unit 23).

d. Let’s say you have a sample of n=25 and your sample mean equals to 13. Is it likely that your
sample originate from the population A?

e. Let’s assume that you draw 10.000 random samples with n=10 from the population A. What
happens to the SD (=standard deviation of the mean) and mean of the sampling distribution?

f. And what happens to the range where you can find 95% of the sample means that are closest to
the population mean (= 95% confidence interval (CI) of the mean)?

<<End of the assignment>>

You might also like