BEC1 Improved Study Guide
A percentile rank is calculated as:
(number of scores less than a given score/total number of scores) x 100
Which Pearson correlation coefficient has the smallest strength of association? A) -0.9 B) -0.7 C) 0.5 D) 0.3
0.3
A study looking at the correlation between cholesterol level and distance between home and work found a correlation coefficient of -0.13. How much of the variance in cholesterol level is explained by distance between home and work (what is the coefficient of determination)?
1.7%
What BMI would you predict from this equation for someone age 25 years who works 45 hours per week? Y = -3.95 + 0.04(hours worked) + 1.21(age)
28.1
The researcher has determined the project has an alpha=0.05. This indicates all values outside _____ will be rejected
95%
What type of relationship between a dependent and independent variable is described by linear regression?
A linear relationship
An example of appropriate linear regression
A random sample of 30 nurses in a hospital unit of 90 nurses
_____ probability is the probability that one event will occur given that another event has occurred
Conditional
The process for testing hypotheses includes what?
Define significance level; compute the test statistic; compute the parameters that are being compared by the test statistic; obtain the p-value of computed statistic; make sure the data meet the necessary assumptions to compute the test statistic
Healthcare statistics can be used to:
Describe the results of medical, public health, environmental, and ecological studies; Isolate and estimate the effect of new treatment modalities while controlling for other important variables and identify risk factors for various diseases and syndromes; Make decisions about public health policy and plan for new treatments and interventions
When defining a good research study, which of the following should be included?
Description of the planned statistical analysis; statement of the problem; list of the hypothesis to be tested; description of the sample and how it was obtained
Commonly used techniques of presenting and organizing statistical data include:
Descriptive statistics, graphical displays, and frequency distributions
What symbol denotes a null hypothesis?
H0
At the age of one year, a child's height of 26 inches is at the 50th percentile according to a growth chart. What is true about this data?
Heights of children age one year were less than 26 inches in 50% of the population
What assumptions are required for the Pearson correlation coefficient to be valid?
Homoscedasticity; the two variable must be normally distributed; there are no outliers; the two variables must have a linear relationship; the two variable must be of interval or ratio measurement scale
A survey where 0=Depressed after 15 hrs, 1=Depressed after 10 hrs, 2=Depressed after 5 hrs, and 3=No change is what type of scale?
Interval scale
The normal distribution is a frequency polygon that demonstrates what properties?
Mean, median, and mode are equal; bell shaped; total area under the curve above the x-axis equals 1
A study compares five different genotypes. Each genotype is coded with numbers, but the order is arbitrary and the computing of an average is meaningless. Which type of measurement data was used?
Nominal
Under which conditions would you need to use the Spearman correlation coefficient and not the Pearson correlation coefficient?
One variable on the ordinal measurement scale and one is on the interval scale; Neither variable is normally distributed; There are only 3 outliers; The two variables do not have a linear relationship
A pain intensity scale is what type of scale?
Ordinal scale
In a study looking at the correlation between annual income and cholesterol level, one concern was that the age of the participants might be a confounder because both income and cholesterol generally increase with age. Which correlation method could the researchers use to remove the influence of age?
Partial correlation
Which of the following is not a part of the research project that is used statistically? 1) Interpretation of data 2) Peer review of data 3) Organization of data 4) Collection of data
Peer review of data
How would you interpret a correlation coefficient of -1?
Perfect negative correlation - as one variable increases, the other variable decreases
Why is it vital for nurses to inform policy makers of current health care problems?
Policies can be developed to resolve problems
A person wants to compare the average oxygen saturation for two patient groups. Which measurement scale should be used for the data?
Ratio
Linear regression is appropriate for what type of dependent variable?
Ratio scale and normally distributed
What measure(s) of the strength and direction of association can we get from a linear regression model?
Regression coefficient (beta)
A multivariate regression model looking at the association of intraocular pressure with having 1) having seasonal allergies 2) wearing contact lenses 3) using eye drops found a coeffiecient of determination (r2) of 0.23. How would you interpret this statistic?
Seasonal allergies, contact lenses, and eye drop use taken together explain 23% of the variation in intraocular lens pressure
A scatterplot compares smoking rates with mortality. If the points, going left to right, are generally going upwards, then what does this mean?
Smoking rates is positively correlated with mortality rates
What is the difference between stepwise methods versus the standard approach and hierarchical methods of selecting independent variables to include in a linear regression model?
Stepwise uses statistical criteria for selecting the variables to be included, whereas the other approaches use theoretical rational.
What is the general relationship of fluoride level and the number of caries? (A scatter plot shows points going from left to right in a downward linear fashion.)
Strongly negative (r=0)
The EPA claims that fluoride in children's drinking water should be at a mean level of less than 1 ppm to reduce the number of dental cavities. A Type I error would be:
Support the claim u<1.2 when u=1.2 is true
A study associated the number of colon polyps and the mean grams of fiber consumed per day based on a standard food frequency questionnaire. The Pearson correlation coefficient was 0.9 with a p-value of 0.003 and the Spearman correlation coefficient was 0.28 and a p-value of 0.049. Which form of correlation would be more important to report?
The Spearman correlation results should be reported because at least one of the variables does not meet the distribution assumption required to use Pearson correlation
The frequency distribution of a data set is symmetric and the mean is 20. What is true about this data set?
The median is 20
What is true about hypotheses?
The null hypothesis is rejected if the alternative hypothesis is accepted
What do we mean by "regression toward the mean"?
The phenomenon that if a variable is extreme on its first measurement, it will tend to be closer to the average on a second measurement
In statistics, which quantity is denoted by sigma squared?
The population variance
An experiment was conducted to determine whether a certain treatment method was effective in reducing dizziness. A test statistic result produced a p-value of 0.5. What is true about this situation?
The probability that one would obtain such a test statistic value by chance alone is 50%
A study is conducted to determine if the patients who have one glass of green tea a day have a reduced healing time after a certain procedure. What would be a Type I error in this situation?
The study incorrectly concludes that the patients who have one glass of green tea a day have a reduced healing time
Conditions to use the Spearman correlation coefficient and not the Pearson correlation coefficient
The two variables do not have a linear relationship; one variable on the ordinal measurement scale and one is on the interval measurement scale; there are only 3 outliers; neither variable is normally distributed
A scatter plot shows points generally going from left to right in a seemingly upright direction, correlating children's mid-upper arm circumference and their mother's weight. How would you describe this correlation?
There is a positive correlation
A survey was conducted among women age 40 to 60 in which participants were asked how many hours per week they spent exercising on average. This information was correlated with the women's body mass index. The results are below. What conclusions can you draw? Sig. (2-tailed)=0.812, Exercise mean/BMI= -0.015
There is a weak, non-significant negative correlation between mean hours exercised and BMI
Why is it important for the nurse to use evidence-based practice guidelines in the clinical setting?
To improve patient health outcomes
A null hypothesis was not rejected, and later it was found that the results were false is what type of error?
Type II
A null hypothesis was not rejected, and later it was found that the results were false. This is an example of:
Type II error
An example of using inferential statistics
Which of the two cover designs will result in a higher percentage of non-subscriber sales?
Which element should an effective study plan include?
Why is the study important?
Data output for a simple linear regression of mortality vs. smoking rates show: coefficient = 1.08; Std Error = 0.22; t = 4.922; p-value = 0.000 Does an increase in the smoking rate significantly increase the mortality rate?
Yes, since the coefficient is 1.08 (>0) and the p-value is 0.000
You are reading a journal article and you see a p-value of 0.11. What is true?
You should determine to what hypotheses the p-value corresponds so that the result can be put into context; P-values are sensitive to sample size and thus you should determine upon what sample size the p-value is based
A potential mistake when interpreting the data is to reject the H0 when it is true. This is referred to as
a Type I error
A research project that follows the participants forward in time to identify future outcomes is referred to as:
a cohort study
In a study of the effect of smoking on lung cancer, it is estimated that the odds ratio (for a subj. that smokes relative to a subj. that does not) is 2.6. This means that:
a person who smokes is 2.6 times as likely to develop lung cancer as a person what does not smoke
Consider the relationship between two continuous variables and the two-dimensional scatterplot associated with these variables. If the correlation coefficient is -1, then:
all points lie in a straight line with an unknown negative slope
One of the important benefits of multivariate regression over many other statistical tests is that it:
allows you to adjust for potentially confounding variables
Confidence intervals can be computed around the population mean from a single simple mean using the:
central limit theorem
Data values that do not fit the pattern of the rest of the data are:
considered outliers
Simple numerical or graphical summaries are referred to as:
descriptive statistics
The _____ of a test is the probability that the test result and the diagnosis agrees
efficiency
A study that often attempts to understand how variables are related to each other is referred to as:
explanatory studies
A research study needs to be well planned before starting. A common mistake seen in research is:
failing to recognize approach limitations
Squaring the Pearson correlation coefficient (r^2) tells us that:
how much variance is shared by the two variables
One response to the nursing shortage has resulted in the recruitment of nurses with various education levels. The results of one research study found that the level of nursing education is critical in caring for certain patients. Therefore, we can conclude that:
increasing the number of nurses without concern for educational level has serious implications for critically ill patients
Techniques that allow conclusions to be drawn about the relationships found among different variables in a population sample are referred to as:
inferential statistics
Researchers conducting a study with ____ power have a ____ probability of committing a type ___ error
low; high; II
Statistics use distinct symbols to represent specific information. Parameters are usually represented by:
lowercase Greek letters
If a distribution is not symmetrical, which measure of central tendency is sensitive to outliers and skew-ness and thus, will not truly reflect the center of the data?
mean
A strong correlation (>0.85) between the independent variables that you want to include in one multivariate linear regression model is an indication that which assumption has been violated?
multicolinearity
The study plan hypotheses
must be very specific
When determining the class intervals in creating a relative frequency chart, it is important to remember each class must be:
mutually exclusive
Researchers articulate the expected relationships between the variables by the _______
null hypothesis
The _____ can be used to test whether the sample mean is significantly different from a population mean
one-sample z-test
The ____ of any statistical test represents the probability that the results were obtained by chance alone
p-value
A pediatrician will compare the 6-week-old infant with the accepted normal growth progress using the:
percentile rank
The set of probabilities associated with each possible outcome in the sample space is referred to as:
probability distribution
The probability that the laboratory test is positive when given to a group of patients who have the disease is referred to as
sensitivity
The hypotheses of the study should:
state the expected relationship between the variables
The alpha-level is defined by the researcher before any statistical tests are conducted. This specific level is defined as:
statistically significant
Health care practices have improved due in part to the use of:
systemic review of research evidence
The marginal probability is computed by:
the number of times the event occurred divided by the total number of times that it could have occurred
A local health dept is interested in determining if there is a difference in the incidence of childhood caries among children living in rural areas drinking untreated well water and children living in cities drinking fluorinated water. A null hypothesis could read
the oral health of the rural children will not differ from that of the city children
Researchers rely on _____ to assist them in drawing meaningful conclusions on data collected on a population through their research project.
the probability theory
In ______ probability, the distribution of events can be inferred without collecting data
theoretical
The first step to deciding which statistical technique to use is:
to identify the question to be answered
