Use the Excel file titled, General-Electric that is posted to GAP under week one and upload it to SPSS.
This file contains GE’s daily stock market data covering the period of 12/13/2010 to 12/11/2019. The
file contains a total of 2013 daily transaction records including date, opening price of the GE stock for
the day, highest price, lowest price, closing price, closing price adjusted for dividends, and the number
of stocks traded (volume).
1. Use the explore command in SPSS and explain whether the trading volume of the stock is
normally distributed. Make sure to discuss, Skewness, kurtosis, results from the test of normality
as well as the Q-Q plots.
2. Select a random Sample of exactly 125 observations. Then run the descriptive command and
calculate the mean and standard deviation of the sample. Repeat this process (i.e., selection of a
random sample and descriptive command) exactly 50 times. Hint: Use SPSS syntax to repeat the
command. List both values (mean and the standard deviation) in a new excel file with proper
column headings.
3. Upload the newly created excel file into SPSS and create a histogram of both the calculated
means and standard deviations.
4. Run the explore command similar to what you did in step 1 for both variables and make your
observations. Does the Central Limit Theorem (CLT) apply to both measurements?
5. Suppose you believe that the true average daily trade volume for General Electric stock is
49,829,719 shares. Based on a recent sample you have also calculated a standard deviation of
21,059,637 shares. Considering a 95% confidence level, what is the minimum required sample
size if you like your sampling error to be limited to 10,000,000 shares. What sample size would
offer a sampling error of not more than 20,000,000 shares? Assuming N=2013 represents the
total population size, how will your calculations change for the finite sample?
6. Is there a statistically significant difference between the average trading volume in 2017 and
2018? Hint: While technically, this can be carried out as a paired sample t-test since volume data
are reported for the same stock, we will treat this as independent samples. Complete your calculations by hand assuming M2017=46108055, S2017=34099055, n2017=251, M2018= 87241844,
S2018=50977722, n2018=238.
7. Repeat the test, this time by using SPSS. Hint: Create a new grouping variable for 2017 and
2018 and use it to run your test.