Read chapter 3 of Greasley’s Quantitative Data Analysis Using SPSS (pages 34 – 60)
Go back to the chapter and perform each of the SPSS operations for descriptive statistics and graphs, as shown in the chapter. These include the chapter demonstrations and the chapter exercises.
In the previous assignment you enter created a databased with the information provided in table 2.1. In this exercise you will keep using the same dataset.
Section 3.1 Explains how to run frequencies. Every time you perform an operation it automatically appears on the output screen. Section 3.2 Explains how to calculate Measures of central tendency.
Follow the instructions and create Table 3.1 SPSS descriptive statistics (page 40). Save the output and summited to the assignment box.
Section 3.3 Covers Graphs on SPSS. Follow the instructions to get familiar with the graph menu.
Create Figure 3.3 Edited histogram showing age distribution of patients (page50). Save the output.
Survey
(by Name)
Institution
Instructor
Course
Date
Exercise 1.1 Types of data
a. categorical data, this information does not represent values on a scale but rather a set of
distinct categories, such as the gender and race of patients, INCLUDING ethnic background.
b. Student assignment marks are hormonal data since they reflect discrete values along a
continuous scale.
c. Since diplomas, master’s degrees, MPhil degrees, and Doctoral degrees all reflect discrete
steps along a scale, and ordinal notation is commonly applied to them (5). Assigning
numerical values to these groups, as I have done here, makes it clear that I consider (2) a
greater academic success than (1), and so on.
d. Patient satisfaction ratings on a 17 scale may be considered interval data because the scale
is provided in equal intervals (however, strictly speaking, we should remark that the rating
scale is at least ordinal and closely resembles interval data).
Exercise 1.2 Measures of central tendency
a. Median since the vast majority of late books will be returned within a week, but a small
percentage of students may take months or even years to bring back their books.
b. Since IQ test results should be regularly distributed around a standardized mean of 100, this
value should be used as the mean.
c. There is no correlation here because they are purely categorical variables. A simple
frequency count would do.
d. Whether the number of sessions was regularly distributed (mean) or substantially biased by
a small number of patients (median).
Exercise 1.3 Correlation.
a. The expense of heating your home rises when the temperature drops (and falls), which is a
negative. 1
b. The positive trend of rising ice cream consumption with rising temperatures
c. None! Due to the lack of two interval variables, this data set is unsuitable for correlation.
Instead, we’d look at differences between the sexes regarding the average number of
counseling sessions sought.
Exercise 1.4 Independent and dependent variables.
a. Whether or not a person has consumed alcohol serves as the IV. The researcher may put this
theory to the test by giving One bottle of scotch, two bottles of wine, and a case of beer are
shown here. Vodka; rum, tequila; whisky, etc. Results on the mathematics test serve as the
DV test.
b. Back pain severity is measured in decibels (DV), with “IV” representing the treatment
modality (acupuncture or physical therapy).
Exercise 1.5 What type of analysis?
a. Due to the presence of two nominal/categorical variables, crosstabulation is the appropriate
data analysis technique.
b. Since both time and grades are interval variables, we can use correlation to determine
whether they are correlated.
c. To compare the average ratings of men and women, we need to apply a test because we are
comparing a categorical (gender) and an interval (ratings).
