false

Class Notes
(835,760)

Canada
(509,376)

McGill University
(27,860)

Nursing
(204)

NUR1 422
(4)

John Hayes
(2)

Lecture

Unlock Document

Description

Chapter 15: Analyzing Quantitative Data
nominal measurement – classification of attributes into mutually exclusive categories
ordinal measurement – ranking of objects based on relative standing on an attribute
interval measurement – indicating not only the ranking of objects but also the distance between
them
ratio measurement – distinguished from interval measurement by having a rational zero point
descriptive statistics – enables researchers to synthesize and summarize quantitative data – data
for a variable can be completely described in terms of shape of its distribution, central tendency, and
variability
frequency distribution – numeric values are ordered from lowest to highest, together with count of
number (or percentage) of times each value was obtained
skewed distribution – one tail longer than the other on curve (positively skewed or negatively
skewed)
unimodal distribution – one peak (one value of high frequency)
multimodal distribution – more than one peak
normal distribution – bell-shaped curve – symmetric, unimodal, and not too peaked
central tendency – indicates average or typical value of a variable – mode, median, mean
mode – value that occurs most frequently in a distribution
median – point above which and below which 50% of the cases fall (middle number)
mean – average of all scores – usually preferred measure of central tendency because of stability
variability – how spread out the data are – range and standard deviation
range – distance between highest and lowest scores
standard deviation – indicates how much, on average, scores deviate from mean
contingency table – two-dimensional frequency distribution in which frequencies of two nominal or
ordinal level variables are cross-tabulated (against each other and see the relationship)
correlation coefficients – describe the direction and magnitude of a relationship between two
variables - -1 for perfect negative correlation, 0 for no relationship, +1 for perfect positive correlation
product-moment correlation coefficient (Pearson’s r) – most commonly used coefficient – used
with interval or ratio level variables – can be used to test whether a correlation is significantly different
from zero
inferential statistics – based on laws of probability – allow researchers to make inferences about a
population based on data from a sample – offer framework for deciding whether the sampling error
that results from sampling fluctuation is too high to provide reliable population estimates
sample distribution of the mean – theoretical distribution of the means of an infinite number of
same-sized samples drawn from a population – basis for inferential statistics
standard error of the mean – SD of this theoretical distribution – indicates the degree of error of a
sample mean – smaller SD error, the more accurate the estimates of the population value based on
sample mean
hypothesis testing – through statistical tests enables researchers to make objective decisions about
relationships between variables
type I error – occurs in null hypothesis is incorrectly rejected (false positive)
type II error – occurs when null hypothesis is incorrectly accepted (false negative)
level of significance (alpha level) – used to control risk of making Type I error – specifies the
probability that such an error will occur – 0.5 level means that only 5/100 samples would the null
hypothesis be rejected when should have been accepted
beta – probability of committing Type II error – can be estimated through power analysis
power – ability of a statistical test to detect true relationships – complement of beta – standard
criterion for an acceptable level of power is 0.80
statistically significant – obtained results are not likely to be due to chance fluctuations at a given
probability level (p level) parametric statistical tests – involve estimation of at least one parameter, use of interval or ratio
level data, and an assumption of normally distributed variables
non-parametric tests – used when data are nominal or ordinal and the normality of the distribution
cannot be assumed
t-test and analysis of variance (ANOVA) – two common statistical tests – used to test significance
of difference between group means – ANOVA used when more than two groups
chi-squared test – most frequently used nonparametric test used to test hypothesis about
differences in proportions
multivariable statistics – increasingly being used in nursing research to untangle complex
relationships among three or more variables
multiple regression – method for understanding effect of two or more predictor (independent)
variables on a dependent variable
multiple correlation coefficient (R) – can be squared to estimate the proportion of variability in the
dependent variable accounted for by predictors
analysis of covariance

More
Less
Related notes for NUR1 422

Join OneClass

Access over 10 million pages of study

documents for 1.3 million courses.

Sign up

Join to view

Continue

Continue
OR

By registering, I agree to the
Terms
and
Privacy Policies

Already have an account?
Log in

Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.