Data Management Decisions


I coded out missing data for all my three variables. As missing data I considered only those cases when respondents refused to give an answer.

My first question (variable) was “W1_P13: Are you a citizen of the United States?”. If the answer is negative, I’m not taking those cases into account anymore. The thing is that for the purpose of this research, I’m only interested in the US citizens attitudes, so any further questions would not make sense for me. The same is about those respondents, who refused to answer.

It also doesn’t apply to the rest of my variables, so nothing to code in as valid data in this case. Also, there is no necessity and no opportunity to create secondary variables and group variables.

Besides, I found no need for recoding my variables. My fourth question is “W2_QL3: Some people believe that homosexuality is immoral. To what extent do you agree or disagree with this perspective?”. The variants are as follows:

  1. “Strongly agree”,
  2. “Somewhat agree”,
  3. “Somewhat disagree”,
  4. “Strongly disagree”.

In my codebook, the higher values mean higher level of “disagree”. Yet, for this assignment, I reverse code my fourth variable. I gave this recoded variable a new name so that I won’t confuse it with my original variable “W2_QL3”. This new name is “HOMMOR”, which stands for “homosexuality is moral”.






  1. For my first question, “W1_P13: Are you a citizen of the United States?” the most commonly endorsed response was “yes” – 97,94%.
  2. The second variable is “W1_P13A: Were you born a United States citizen or are you a naturalized U.S. citizen?”. Frequency destribution shows that the majority of the respondents were born US citizens – 95,64%, and 4,35% are the naturalized ones.
  3. The third question shows that 28,25% strongly agree with the belief that homosexuality is immoral, while just a bit more – 27,00% endorsed the “Somewhat agree” variant, 19,65% chose “Somewhat disagree”, while 25,10% strongly disagree with the statement.

The difference between the counts with and without missing data is seen when comparing to previous results.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s