Research Class 1`2 Part 1

Most research questions are far more ___ than simply one independent variable and one dependent variable

complex

Numerous multi-variate statistical procedures are available for researchers to enable examination of many variables at once, such as…

• multiple regression

• two way ANOVA

• ANCOVA

• MANOVA

• MANCOVA

• factor analysis

___ is similar to linear regression and it examines how more than one independent variable can predict one dependent variable

multiple regression

___ regression analyzes the relationship between two variables. · Multiple regression examines several variables' effects on a single outcome.

linear

multiple regression examines the effect of more than one ___ variable (ratio or interval data) on the dependent variable (ratio or interval data)

independent

multiple regression is used to ___ a dependent variable based on two or more independent (predictor) variables

predict

what is the equation for multiple regression with two predictor variables

Y(1)’ = a + b(1)X(1) + b(2)X(2)

Y(1)’ is the ___ of variable Y (dependent variable)

predicted value

a is the intercept constant, b1 and b2 are the ___ for each of the variables, and x1 and x2 are the actual values for the variables

regression coefficients

So, the prediction equation for multiple regression is the same as for regression, except that it has ___ regression coefficients and X variables included

additional

the Multiple Correlation Coefficient is represented by..

R

the ___ for a dependent variable and two or more independent variables is the multiple correlation coefficient or R

correlation index

R does not have ___ values and therefore it shows strength of relationships, but not direction

negative

R can be squared (R²) to ___ the proportion of variability in the dependent variable accounted for by the independent variables

estimate

A total R² shows the proportion of variance in the dependent variable (Y) accounted for by the ___ simultaneous influence of the independent variables

combined

R² can also be calculated for each IV to determine the proportion of variance in the DV explained by each IV ___

separately

in multiple regression, we include ___ variables in our prediction equation, to account for more of the variation, and thereby make better predictions

more

With ___ correlations between IV and DV, additional IVs add little predictive power and therefore they are redundant (multiple regression)

high

With lower correlations, each IV can contribute something ___

unique

in multiple regression, we are concerned with not only the overall "R" (total correlation), but also, the total amount of ___ in Y accounted for by the combined influence of all the independent variables "R²"

variance

the multiple ___ variables known as “x” (IVs) in multiple regression

predictor

there is more than one response variable (DVs), known as “___”; continuous variable

y

allows us to statistically equalize or control for differences between groups that might influence the dependent variable

analysis of covariance (ANCOVA)

ANCOVA is used to compare the ___ of two or more groups, are they real or due to chance?

means

ANCOVA permits more ___ of extraneous variables

control

ANCOVA extends ANOVA by removing the effect of ___ (covariates) before testing whether mean group differences are statistically significant

extraneous variables

what are the levels of measurements for ANCOVA?

• DV is continuous

• IV is categorical

• covariates are continuous or dichotomous

what is multiple classification analysis (MCA)

A supplement to ANCOVA that yields information about the groups’ adjusted means on a dependent variable, after removing effect of covariates

what does MANOVA stand for

multivariate analysis of variance

MANOVA is the extension of ANOVA to more than one ___

dependent variable

MANOVA can be used when more than ___ groups are being compared

2

MANOVA can be used with covariates, which is called….

multivariate analysis of covariance (MANCOVA)

A a nurse researcher is interested on examining the effect of three different dressing techniques on wound healing and pain. Which test?

MANOVA because there is one IV (dressing techniques) and two dependent variables (wound healing and pain)

technique used to examine how well items on a measure are related and form clusters or factors

factor analysis (FA)

factor = unified ___ that represents several variables

concept

FA is commonly used to test ___ of an instrument/measure

construct validity

FA allows a researcher to determine how many ___ an instrument has and which items “fit” best with each factor.

factors

items that measure a ___ factor (e.g. empathy) should be closely related to each other but less well related to a different concept (e.g. physical caring)

similar

thus, FA is a good measure of ___

construct validity

FA helps ___ figure out how many factors (underlying themes or concepts) a survey or test has, and which test questions (items) fit best into each factor.

researchers

Questions measuring the same overall trait (e.g., empathy) should group closely ___, while remaining distinct from questions measuring a different trait (e.g., physical caring).

together

Because FA ___ that test questions properly group into the right concepts, it is a great tool for measuring construct validity (proving a test measures what it claims to measure).

verifies

Imagine you give a 50-question personality survey. Instead of looking at 50 separate questions, Factor Analysis acts like a ___ tool that finds hidden patterns behind the scenes.

sorting

___ designs or mixed method designs are designs which integrate qualitative and quantitative paradigms.

Multi-method

Some researchers believe that because quantitative and qualitative methods are distinct, they are ___

incompatible

multi-method philosophy that argues that truth can only be known by what is objectively and numerically measurable is incongruent with a philosophy that argues multiple truths and ___ the subjective experience.

values

Mixed methods can ___ one another.

complement

the use of multiple sources to uncover multiple truths

triangulation

when are mixed method designs appropriate?

• instrument development

• explicating and validating constructs

• hypothesis generation

• illustration clarification and amplification

• theory building and testing

multimethod enhance ___ as evidence is derived from different approaches

validity

If different methods provide the same or similar answers than that gives greater credence to the ‘___’

truth

research opportunities for mixed methods designs include…

• clinical trials

• evaluation studies

• survey research

• ethnographic research

what are the two categories of multi-method designs

sequential and concurrent

the qualitative and quantitative measures are implanted as ___ phases of the research process (sequential design)

discrete and separated

the qualitative and quantitative methods are incorporated throughout all phases of the research process in the ___ design

concurrent

___ is material or literature produced by non-academic organizations such as government policies

grey literature

in systematic reviews, the researcher keeps a record of the ___ as well as those discarded documents, so that consumers of the systematic review can critically appraise the scope (breadth and depth) of the literature that was searched

search strategy

Sometimes only qualitative research has been conducted on a topic area, usually of a ___ phenomenon

poorly understood

A ___ is the systematic review and integration of findings from qualitative studies

meta synthesis

A ___ helps to give an objective and transparent overview of all evidence surrounding a particular question

systematic review

what counts as grey literature?

1. non peer reviewed journal articles

2. peer reviewed journal articles

3. reports written by professional associations

4. prior lit reviews

what does the CNO say a communicator should do?

use evidence informed communication skills to build trusting relationships with patients

what are areas of nursing research utilization?

• practice

• administration

• education

• research

Uses and analyses assembled quantitative data (risk management data, LOS, absenteeism, falls etc) for the unit and/or the organization to identify areas of care that require focus and initiatives for improvement

quality improvement

quality improvement may be mixed methods and include ___ data too

qualitative

In a study about exercise tolerance in young patients with COPD, the participants were given a daily exercise regime of 30 minutes of gentle aerobic exercises. Their exercise tolerance on a treadmill was measured weekly for 6 weeks. This is an example of a pretest post test design. T or F?

true

The following is an example of a multivariate design. T or F

A study is measuring the impact of a calorie-controlled diet, a daily exercise plan and nonsmoking on heart rate, blood pressure, and ability to climb three flights of stairs without shortness of breath.

true

The following is an example of a posttest design.

Patients two days post-knee replacement are measured for range of motion in the affected limb before they receive an analgesic and one hour after they receive an analgesic.

false

The research design is the structure of the research process.

true

A research design specifies step by step how the study is conducted.

true

The research design is just an idea the researcher has about what the study will do.

false

The research design includes the methodology, instruments, procedures, consent, data collection, and data analysis for the study.

true

The research design has to be approved by the institutional research ethics board.

true

The research design is an aesthetic look at the research study.

false

There is a “fit” between the beliefs of the researcher, question and the research design.

true

___ statistics enable the researcher to organize, synthesize and summarize quantitative data

Descriptive

In a ___ values are ordered from lowest to highest accompanied by the # of times (or %) each value was obtained

frequency distribution

Frequency ___ display frequency information graphically

polygons

A continuous variable data set may be completely described in terms of…

the shape of the distribution, central tendency and variability

The shape may be symmetrical or skewed, one tail longer than the other; unimodal with one peak (i.e. one value of higher frequency) or ___ with more than one peak

multimodal

A normal distribution (bell shaped curve) is symmetric, ___ and not too peaked

unimodal

Measures of central tendency represent the ___ or typical value of a measure

average

The ___ is the value that occurs most frequently in the distribution

mode

The ___ is the point on a scale above which and below which 50% of the cases fall

median

how spread out the data are—include the range and standard deviation

measures of variability

The range is the __ between the highest and lowest scores

distance

the ___ indicates how much, on average, the scores deviate from the mean

standard deviation

A ___ is a two-dimensional frequency distribution in which the frequencies of two nominal or ordinal level variables are cross tabulated

contingency table

___ descriptive statistics describe the degree and magnitude of relationships between two variables

Bivariate

___ describe the direction and magnitude of a relationship between two variables

Correlation coefficients

the values range from –1.00 for a perfect ___ correlation to .00 for no relationship, to +1.00 for a perfect positive correlation

negative

The most frequently used correlation coefficient is the product-moment correlation coefficient (Pearson’s r) used with ___ level variables.

interval or ratio

___ statistics are based on the laws of probability and allow researchers to make inferences about a population based on data from a sample

Inferential

They offer a ___ for deciding whether the sampling error that results from sampling fluctuation is too high to provide reliable population estimates

framework

The ___ of the mean is a theoretical distribution of the means of many different samples drawn from the same population.

sampling distribution

Sampling distributions are the ___ for inferential statistics.

basis

The ___ of the mean—the standard deviation of this theoretical distribution—indicates the degree of average error of a sample mean; the smaller the standard error, the more accurate are the estimates of the population value based on the mean of a sample

standard error

___ testing through statistical procedures enables researchers to make objective decisions about the results of their studies

Hypothesis

The ___ states that no relationship exists between the variables and that any observed relationship is due to chance or sampling fluctuations; rejection of the null hypothesis lends support to the research hypothesis

null hypothesis

A ___ error occurs when a null hypothesis that should be rejected is accepted.

Type II