PSYCH 3500 Assignment1 ANSWERS - Psychology 3500 Statistics...

Psychology 3500 – Statistics and Research Design
Assignment #1, due Fri 09 September 2016
Answer the following questions. Ideally, type your answers into the word processor document; to create figures, either use software like R or Excel to
create a figure or sketch it and scan the page. Turn in your assignment in BOTH of these TWO WAYS: [1] upload it as a single file (ideally PDF, but
word processor formats are also accepted) under Assignments in Blackboard, using the filename netid_Assignment1.pdf where netid is your NetID.
(If you disorganize my efforts to grade efficiently by not naming your file in this way then you will lose points and make me sad). [2] Print out your
completed assignment and turn in this hardcopy at the START of class on the due date. Please write your name on every physical page in case they
are separated during grading.
(1) Consider the following distribution of continuously-valued scores. You can assume that the real limits of the
categories shown reflect the normal practice of your textbook authors. Fill in the cumulative frequency and cumulative
percentage columns.
(2) From the following frequency table of continuously-valued scores and cumulative percentages, use interpolation to
determine the requested percentiles and percentile ranks. Remember real limits!
X c%
14-15 100
12-13 84
10-11 72
8-9 48
6-7 32
4-5 10
2-3 6
(A) What is the percentile rank for x = 5?
X = 5 is in 3.5 – 5.5 (4 – 5 bin)
(B) What is the percentile rank for x = 12? (C) What is the 30 th percentile?
(D) What is the 80 th percentile? (3) For each of the following data sets, (1) identify whether the data sets are nominal, ordinal, interval, or ratio scaled. (2)
Define whether the scores constitute a population or a sample (to do this, assess whether the goal is to infer a result
about only the exact group studied or about some larger population meant to be represented by the group studied). (3) If
the scores constitute a population , define that population. If the scores constitute a sample , identify a corresponding
population for which that sample is a reasonably fair sample, if any, and explain your choice.
1

(A) A data set of the lead levels in public drinking water sources across New York state, in parts per million (ppm), as
assessed by a randomized sampling of tap water from several sources within each county of the state.
(B) A data set of all Cornell ROTC cadets, listed by military rank. The intent is to visualize these data to see whether the
Cornell program has the optimal distribution of ranks to conduct its operations.