You are on page 1of 5

PAF 3401: Quantitative Methods for Policy & Practice

Neil G. Bennett Fall 2022


HW #2 – Due 11:59pm, Friday, 16 September 2022
65 POINTS TOTAL

AS THIS IS A WORD FILE, PLEASE INSERT ENOUGH SPACE AFTER EACH QUESTION TO PROVIDE
ROOM FOR YOUR ANSWERS ON THIS DOCUMENT. (YOU DON’T HAVE TO TYPE YOUR ANSWERS.)
SCAN, IF YOU HAVE TO, AND UPLOAD ONE ALL-INCLUSIVE PDF FILE OF THIS TO OUR BLACKBOARD
GRADE CENTER.

PLEASE SHOW ALL WORK IN ORDER TO GET FULL CREDIT FOR ANY ANSWER. THANKS.

ACADEMIC HONESTY:

 Academic dishonesty is unacceptable and will not be tolerated.


 Dishonesty includes unauthorized collaboration with others, for example whether copying from another
student or allowing another student to copy your work. Referring to web sites that provide assistance in any
way, including serving as sources for previous versions of Baruch assignments or exams is also prohibited.
 Violations of this policy will result in academic sanctions. Sanctions in this class will range from a zero on the
assignment or the exam to an F in this course. Anyone who violates this policy will also be reported to the
appropriate Dean’s office.
 Please sign immediately below, either by hand or by typing, which confirms that you understand this policy:

Name: Marufjon Sharofov

The Data for This and Many Future Assignments:

I’ve emailed each of you a unique data set that you should use for this assignment (and subsequent ones,
too). The file is called Gallup_01.sav, or Gallup_02.sav, or, generally, Gallup_XX.sav, where the number
“XX” refers to your particular data set (anywhere from 01 to 30). (Note that in SPSS, a data file’s extension is
“.sav”.)

On your home computer, open SPSS and click File => Open => Data => … Gallup_20.

On our BB site in Course Documents for this week – Sep 12-16 – please look carefully at the Data Dictionary
I’ve posted. That document describes each variable included in your SPSS data set. For any variable shown,
it lists a respondent’s possible answers. For example, for the “Political Party” variable, the possible values are
1, 2, or 3, and the data dictionary supplies what each of those values means – in this case, Republican,
Independent, or Democrat.

I’ve also provided URLs for many video tutorials – under “Syllabus & Stuff” in Course Documents – that will
help you greatly in carrying out SPSS tasks I ask for in this assignment. See, in particular, my YouTube videos
and supplementary videos # 4-9.
(1) (18 points total)

(a) Using your SPSS Gallup_XX.sav data set, present a screenshot of the crosstab of FEMALE by HEALTH,
where the 2 categories of FEMALE are the the 2 columns and the 5 categories of HEALTH are the 5 rows.
Please show row, column, and total percentages. (10 points)

PASTE SCREENSHOT HERE:

Please answer all parts, (b) THROUGH (e), with a percentage that includes one decimal place (e.g.,
23.4%), and show the numerator and denominator you used (from your SPSS output) to get each
answer.

(b) What percentage of the entire sample were females in poor health? (2 points)
6 (total # females in poor health) /1020 (# entire sample) =0.005882352941176. ~ 0.06%
(c) What percentage of the entire sample were in excellent health? (2 points)
213/1020= 0.208823529411765. ~ 20.9%
(d) What percentage of males were in poor health? (2 points)
16/615= 2.6%
(e) Of all people in poor health, what percentage were females? (2 points)
6/22= 27.3%

(2) Suppose you have the following information on whether individuals get their news primarily online (vs.
newspapers or TV, for example), broken down by age. A sample of 500 individuals was drawn from
Community A and 300 from Community B: (18 points total)
COMMUNITY A COMMUNITY B
Age of
<35 35+ <35 35+
Individual:

No. of
300 200 100 200
individuals
No. of
individuals who
225 20 75 20
get their news
online

(a) What is the overall (or “crude”) proportion of individuals in Community A who get their news online? What
is the corresponding proportion in Community B? (Please show both the numerator and denominator
associated with each answer.) (4 points)
Community A – 245(225+20)/500(300+200) = 0.49
Community B – 95(75+20)/300(100+200) = ~0.32

(b) What is the set of age-specific individual news-from-online rates for each community – that is, the rate
within each age category (<35 and 35+ years old, separately) for each community (A vs. B)? (Again, please
show both the numerator and denominator associated with each answer.) (8 points)
Community A – (<35) 225/300= 75%, (35+) 20/200= 10%
Community B – (<35) 75/100= 75%, (35+) 20/200= 10%
(c) Please compare the age-specific rates of Community A vs. Community B and then compare the overall
rates of the two communities. Please “make sense” of the two different stories that these two measures
imply. Put differently, please “weave” these different results into one explanation that helps us understand
the way people access news within and between these two communities. (6 points)
Both Communities (A&B) have the same percentages of people who get their news online within the
each age specific category even though sample size differs for both communities.
(3) Suppose I had a sample of five individuals and have information on their number of years of education and
IQ: (9 points total)

Individual’s Individual’s
Name Education (years) IQ
Chip 14 100
Jose 14 120
Marufjon 16 140
James 12 100
Chrystal 4 140
NOTE: PLEASE MAKE SURE YOU INSERT YOUR NAME TO RECEIVE ANY CREDIT FOR THIS PROBLEM.

(a) Find the sample mean for Individual’s Education (please show both the numerator and denominator
associated that resulted in your answer). (1 point)
(14+14+16+12+4)/5= 12
(b) Find the sample median for Individual’s Education. (1 point)
16,14,14,12,4. 14 because it separates sample from lower and higher points
(c) Find the sample mode for Individual’s Education. (1 point)
14 because its most likely to appear
(d) Why does the sample mean differ as much as it does from the sample median? (3 points)
Because sample mean uses all the numbers in the sample and those numbers can be very high or very
low affecting the sample mean. Meanwhile sample median uses only number in the middle of the
sample.
(e) Find the sample standard deviation for Individual’s Education. (Please round your final answer to 2
decimal places.) (3 points)
1. Mean = 12 (given)
2. Sum of sq dev from mean = (14-12)^2+(14-12)^2+(16-12)^2+(12-12)^2+(4-12)^2= 88
3. Degrees of freedom = 5-1= 4
Std. Dev = Sqrt(88/4) = 4.69

(4) (20 POINTS TOTAL)

PLEASE CONSULT THE SPSS VIDEOS WHOSE LINKS I’VE PROVIDED ON OUR BB SITE FOR THE WEEK.

(a) Using SPSS, please create the data set given in the previous problem (#3), labelling the three variables –
Name, Individual’s Education, and IQ – meaningfully (not merely “x”, “y,” and “z”).

Take a screenshot of that data set and display it here: (10 POINTS)

NOTE: AGAIN, PLEASE MAKE SURE YOU PLACE YOUR NAME IN THE DATA SET IN ORDER TO
RECEIVE ANY CREDIT FOR THIS PROBLEM.

(b) Use the Analyze  Descriptive Statistics  Frequencies command in SPSS, to provide sample statistics for both
variables, Individual’s Education and IQ. They should include the mean, median, and sample standard deviation for
each of the quantitative variables.

Place a screenshot of your results here (only the “Statistics” box) : (10 POINTS)

NOTE 1: PLEASE SAVE THIS DATA SET FOR USE IN THE NEXT ASSIGNMENT.
NOTE 2: In displaying/attaching any SPSS results, please do so with no extraneous output. Remember, I
want ONLY a screenshot of the 5-person data set (part (a)), along with only the specific information I
requested (part (b)).

You might also like