H355 Data Analysis and Research Midterm

What question is stats always trying to answer

Define the empirical method

systemic observation and experimentation to determine whether what is observed is consistently different from what is expected

Define population (N)

a group of objects or people that are alike on one or more dimestions as defined by the researcher

Define sample (n)

a group of cases selected from the population for the prupose of research

Define statistic

estimates derived from a sample (can be generalized back to the original population)

Define parameter

Infinite number of values between any 2 values, equal intervals (interval/ratio level of meaurement)

Continuous variable

finite number of categories

categorical/discrete variable

What are the four levels of measurement

nominal, Ordinal, Interval, Ratio

True or false: quantitative date can be converted into qualitative data

true

True or false: Qualitative date can be converted into quantitative data

false

Define nominal data

Simplest level of measurement- number are just used as names, showing sameness or differentness of a particular quality

Categories in nominal data are:

exhaustive (all possibilities fit into a category) and exclusive (can not fit into more than one category) and in no particular order (no ranking)

The measure of central tendency is appropriate for nominal data

mode (most frequently occurring value)

A researcher allows participants to choose between married, divorced, separated, or never married. What kind of data is this?

nominal data

Define ordinal data

also referred to as “discrete” data, finite number of values for each variable

Categories in ordinal data must be:

rank ordered (each category is higher/lower but don’t know level of difference between categories)

Observations of pain in a study are arranged as mild/severe/moderate. What type of data is this?

ordinal data

What measurements of central tendency are appropriate for ordinal data?

Median, range, mode

Define interval/ratio data

Highest form of measurement

Categories in interval/ratio data must be:

exhaustive, exclusive, and ordered with equal intervals

What kind of data is temperature?

interval/ratio

What is the EBP process using Melnyk’s model

ask the question, collect the best evidence, critically evaluate evidence, integrate evidence into practice, and evaluate practice change to revise or expand

How does a nurse collect the best evidence for EBP and then critically evaluate this evidence?

find current research articles and determine the quality of the research

What would measuring temperature be in a study?

variable

What would evaluating how likely temperature readings are above 50 degrees in January be?

probability

What would the mean age of college students in a class be?

statistic

What would the mean age of all college students in the US be?

parameter

only 2 categories (yes/no; hot/cold; normal/abnormal; pass/fail)

dichotomous variable

What is an extraneous variable?

variables we may/may not understand (can influence findings)

What is a variable we have not measured but noticed we should have measured?

extraneous variable

What type of scale is this?

visual analog scale

What type of scale is this?

likert-type scale

What type of scale is this?

sematic differential scale

Describe frequency distribution

frequency of each measure of a variable (summary of numerical counts of the values)

Calculate cumulative frequency

Calculate cumulative percentages

summing of percentages from the first category fo the table, ending with a cumulative percentage of 100%

Develop a frequency distribution

Calculate a percentage

(score/total score) x 100

What visual presentation is best for this data

Interpret meaning of percetile rank results

What does the symbol N represent

number of subject

What does the symbol X represent

raw score(s)

What does the symbol X-bar represent

mean

What is a cumulative frequency?

cumulative measure of frequency of a variable (number of observations with a value less than the max value of the variable interval)

What is a grouped frequency?

The frequency distribution with distinct intervals or groups to simplify the information (used when entirety of frequency distribution would be too large)

What is the drawback of grouped frequency?

Some data may be lost

How should this data be presented?: Nominal data

bar charts

How should this data be presented?: Ordinal data

Bar charts or histograms

How should this data be presented?: Interval/ratio, continuous data

histograms or line graphs

What graph has spaces between the vertical bars because each answer is in no particular order?

bar charts

what bar graph has no spaces between the bars?

histograms

what graph is developed by joining a series of points to show variable changes over time

line graph

what graph shows dots, each a subject placed where the score for variable x and variable y intersect?

scatter plot

what does an upward slope on a scatterplot show?

positive relationship/correlation

define descriptive stats

define inferential stats

define mean

average

define median

the 50th percentile or point at which 50% of subjects scored below and 50% scored above

define mode

most frequently occurring measure or category in the data

Define standard deviation

the average distance the values in your distribution fall from the mean

identify unimodal distributionse

one peak in the curve (one mode)

identify bimodal distributions

two modes (two measures or categories with the same highest frequency)

identify multimodal distributions

more than two modes (more than two measure with the same highest frequency)

determine which measure of centeral tendency is appropriate in a given data set

calculate and interpret a standard deviation adn range given for a data set

Explain descriptive results from a given data set using SPSS

Define probability and explain the range of possible probabilities.

Compare and contrast frequency and probability distributions

Frequency distributions

reflects the frequency of all outcomes in a data set (varies based on the sample)

Probability distributions

graphs the probability of all possible outcomes of a variable (uniform and never changes)

Contrast positive and negative distribution skews and describe where the outliers are present.

whats the best measure of central tendency for interval/ratio (continuous) data because all of the scores in the distribution are used to calculate it

standard deviation (s, S, SD, σ)

within one SD of the mean there is __% of data

68

within two SD of the mean there is __% of data

95

within three SD of the mean there is __% of data

99.7

Large Sd indicates ___ variability in a distribution and a ___ range of scores

more; large

small SD indicates ___ variability in a distribution and a ___ range of scores

less; small

Platykurtic Distribution

”heterogeneous” (no real similarities in scores/responses) so the distribution is flatter than a normal curve. The kurtosis (peakedness) would be negative or “platykurtic” with a short tail like a platypus.

Leptokurtic Distribution

“homogeneous” distribution that is tighter and taller than a normal distribution. The kurtosis (peakedness) would be positive or “leptokurtic” with a long tail like a kangaroo.

range

the simplest measure of variability (used with ordinal and interval/ratio data)

When outliers are to the right there is a ___ skew

positive

When outliers are to the left there is a ___ skew

negative

inferential stats

The ability to make inferences about populations based on sample measurements and the probabilities of each variable

what factors impact feasibility of a study

define validity

establishes the accuracy of an instrument in measuring the intended variables

identify methods for estabilishing validity and example of each

define reliability

what are th main components of reliability

when does inter-rater reliability needs to be assessed

whats a plan for assessing inter-rater reliability

Formulate a 2x2 table

define sensitivity

the probability that the patient will test positive for the disease if the patient has the disease [ true positive/all with disease x100]

define specificity

the probability that the patient will test negative for the disease if the patient does not have the disease [ true negative/all without disease x100]

Calculate positive predictive value of a screening test

the probability that a patient who receives a positive test result truly has the disease [ true positive/positive test result ccx100]

Calculate the prevalence of an illness and describe how the positive and negative predictive values of the screening test are affected by the prevalence of the illness among the test population

Critique a screening test utilizing a given data set

Prepare an argument for why or why not a particular screen should be utilized based on current research

Subject matter experts (SMEs) determine whether the instrument:

includes the major elements relevant to the concept being measured, maintains focus on major elements, is complete, concise, clear, and reliable

What is construct validity?

the ability of an instrument to measure a hypothesized phenomenon such as motivation, health, wellness, etc.