In a one tailed test of significance, The researcher is interested in extreme scores in only one tail of the distribution The hypothesis is nondirectional The possibility of rejecting the hypothesis is lower The 5% of statistical values that are considered statistically significant according to decision theory must be distributed between the two extremes of the curve
DNP-816: Analysis & Applic of Health Data for ANP
STATISTICS QUIZ 2
- In a sample of 50 pregnant women, only 5 women end up having their baby more than 1 week after the due date, while 10 are delivered at least 1 week prior to the due date. What is the probability in this sample that a woman will deliver within 1 week of the due date?
.7 or 70%
10% or .1
.2 or 20%
80% or .8
- If you are conducting a study to examine relationships or predict an event, your study is based on which of the following theories?
Probablility
Decision
Causality
Power
No answer text provided.
- What is the median for the following set of cases?
6, 7, 9, 10, 10, 11, 12, 13, 15, 16
10.5
10.9
10
11.2
- According to Polit and Beck (2017), what is the best way to handle Likert scales when conducting research?
Use the total score of the questionnaire used in order to consider it interval level of measurement.
Because intervals between responses have not been shown to be equal, using Likert scales is not recommended
Use parametric statistics as Likert scales are not dependable.
Likert scales are considered nominal data and should not be used for statistical analysis.
- Why is the level of measurement of variables important in a statistical analysis?
It affects what you can do with the data
It determines the direction of the relationship
It affects the power of a study
It determines the power of a study
- Which example is below would be the best way to measure the variable- weight?
Weight in pounds
Weight in three groups: under 125 lbs, 126 to 175 lbs and 176 lbs +
Nnormal weight or overweight
BMI score below 17, between 19 and 24 , above 25
- Why is it important to measure variables at the highest level of measurement that is congruent with the concept being measured?
Data from a higher level of measurement can be converted to lower- level measurement, but lower level measurement can not be converted to higher level data
Each statistical analysis requires specified levels of measurement
More mathematical operations are possible with variables measured at the interval and ratio levels of measurement
All answers are correct.
- A grouped frequency distribution:
Results in loss of information
Is seldom used with continous data
Provides more information as the number of groups decreases
Should avoid group definitions used in previous studies
- Scatterplots are often used to visualize the relationship between two variables. Which of the following is true about these plots?
In correlation analysis, the line of best fit may be included on the plot
They give little information about the strength of a relationship
They give little information about the directionality of a relationship
Scatterplots reveal relationships only when the researcher has specified them in advance.
- Which of the following is not trueconcerning the use of descriptive statistics?
Provides a mechanism for drawing conclusions about a population using a sample
They are used in every research study, qualitative as well as quantitative
They are used to identify patterns in data
They are used to address objectives of some studies
- Which of the following is true about the mean?
It is the mathematical average of a set of scores
It is a measure reflecting the way a set of scores is spread out
It is unaffected by outlier or extreme scores
It represents the most frequently occurring score in set of scores
- According to the theoretical normal curve, what percent of the scores in a data set are within one standard deviation (above and below) the mean?
68%
50%
95%
99%
- A researcher is conducting a study on the effectiveness of different methods of test review on test scores based on the NCLEX test plan. Which of the variables is the independent variable?
Methods of test review
Test scores
NCLEX test plan
The researcher
- What does it mean when calculating a confidence interval that the confidence interval includes the number 1?
It means that there is not a significant p value.
It means there is a statistically significant result
It means that the statistics were not calculated correctly
It means that the sample size is too small
- What is the best way to determine how well the sample statistic represents the unknown population parameter?
Calculate a Confidence interval
Determine central tendency
Determine variability
Calculate probability
STATISTICS QUIZ 3
- In a study examining the relationship between a participant’s age and number of friends, a Pearson r = -.62 was computed. Which of the following best describes this finding?
As age increases the number of friends decreases
As age increases, the number of friends increase
As age decreases, the number of friends decreases
As age increases, the number of friends stays the same.
- Many researchers become excited when they identify statistically significant relationships between variables and may interpret this to mean that the relationship is very important. However, when the percentage of variance explained is calculated, the picture becomes less rosy. Which of the following is true about the percentage of variance explained?
All of the answers are correct
It is calculated by squaring the r value
The obtained value will be lower than the r value unless there is a perfect correlation
A correlation of .40 would explain only 16% of variance, leaving 84% unexplained
- Which of the following is true about correlational analyses?
All of the data should come from a single population
Data must be measured at the ratio level for these analyses to be valid
The range of values should be truncated or shortened in order for these statistical procedures to work
Data from groups that are different in some way are preferred in these analyses
- Below is a correlation matrix for four variables (A, B, C, D). Which value in the matrix indicates the strongest relationship?
| A | B | C | D | |
| A | ||||
| B | .62 | |||
| C | -.59 | .45 | ||
| D | -.65 | .52 | -.27 |
-.65
-.59
.52
.62
- A correlation of +0.80 has been found between impulsivity and number of offenses committed in a group of young men. How much variance in impulsivity can be explained by number of offenses committed in percentage terms?
64%
20%
36%
84%
- The most common purpose for a Pearson’s correlation is to examine:
Relationships between two variables
Relationships among groups
Differences between variables
Differences between two or more groups
- A nurse researcher wants to describe the relationship between marital status (married vs unmarried) and having a diagnosis of postpartum depression (yes vs no). Which of the following would the researcher use for the analysis?
A crosstabs table
Pearson’s produce-moment correlation coefficient
A scatter plot
Spearman’s rho
- A nurse researcher wants to describe the relationship between clients’ age and their scores on a 20 item social support scale. Which of the following would the researcher use to present the results of the analysis graphically?
A scatter plot
A crosstabs table
A correlation matrix
A histogram
- Match the following statistical tests with the level of measurement or other requirement required for each analysis.
Group of answer choices
Pearson r
[ Choose ] Nominal data Ordinal data Ordinal, very small group size Interval or ratio data
Spearman ‘s Rank Order (rho)
[ Choose ] Nominal data Ordinal data Ordinal, very small group size Interval or ratio data
Kendall’s Tau
[ Choose ] Nominal data Ordinal data Ordinal, very small group size Interval or ratio data
Chi Square
[ Choose ] Nominal data Ordinal data Ordinal, very small group size Interval or ratio data
- What is a major weakness of correlational studies?
They are vulnerable to self-selection bias
They tend to be expensive
They tend to be artificial.
They are complex
- What is a central feature of non-experimental research?
The researcher does not manipulate the independent variable
The researcher manipulates the dependent variable.
Data are collected through the observation of participants’ behaviors.
The strength lies in their ability to elucidate cause-and-effect relationships.
- In a one tailed test of significance,
The researcher is interested in extreme scores in only one tail of the distribution
The hypothesis is nondirectional
The possibility of rejecting the hypothesis is lower
The 5% of statistical values that are considered statistically significant according to decision theory must be distributed between the two extremes of the curve
- If the null hypothesis was rejected and there was only 1 chance out of 100 that the decision was wrong, what was the alpha level in the study?
.01
.05
.10
.001
- What is a Type I error?
When we reject the null hypothesis when it is true
Obtaining a non-significant result by sampling error alone
Obtaining a non-significant result when it should be significant
Accepting the null hypothesis when in it is false
- A Type I error occurs when:
The results indicate a statistically significant difference, when in reality, there is no significant difference
The results are not statistically significant
The wrong statistical procedures are used
The data were not measure at the interval level
STATISTICS QUIZ 4
- When the results of an experiment can confidently be attributed to the effect of the independent variable, the experiment is said to have
Construct validity
External validity
Statistical conclusion validity
Internal validity
- What does inferential statistics permit researchers to do?
Describe information from an emprirical observation.
Intepret descriptive statistics
Draw conclusions about a population based on data from a sample
Reject the null hypothesis
- What type of statistics are used to infer that the results from a sample are reflective of the true population scores?
Regression
Correlated statistics
Descriptive
Inferential
- A researcher tests the hypothesis that men and women differ in the amount of time (number of hours) they spend exercising weekly. Which statistical test might the researcher use, assuming a reasonable normal distribution of values?
Mann-Whitney U test
A chi-squared test
A paired t test
Independent groups t test
- Of the examples below, which one is describing a within group design?
A study is conducted to examine the difference in reading ability in 6 year old children compared with children who are 8 years old.
The researcher conducts a study to examine the difference in coping style between engineering students and biology students.
A study is conducted to see if there is a statistically significant difference in anger expression between cat owners and dog owners.
A group of participants are tested on their recall of a list of words. They are tested immediately, 10 minutes later, 2 hours later and 24 hours later to determine how their scores differ between the three tests
- Which statistical test would you choose for the following hypothesis? “There will be a difference in attitude towards good dietary practice in individuals whose hobby is athletics as compared to individuals whose hobby is model aircraft assembly”.
Pearson product moment correlation
Independent t test
Linear regression
Dependent t test
- The level of measurement for the dependent variable (DV) in an ANOVA should be:
Nominal
Categorical
Ordinal
Interval or higher
- When analyzing data to determine differences between groups, it is important that the researcher know if the data sets are independent or dependent on one another and make any needed adjustments in statistical calculations. An example of independent groups is:
Comparison of pretest and post-test groups.
Comparison of mother and daughter groups in relation to premenstrual symptoms
Intervention and control group made of different subject who were randomly assigned to groups
Matched pairs of subjects used for the control and treatment groups
- Which tool is useful for understanding the precision of results?
Confidence intervals
Significance levels
Effect size indexes
Type I error rates
- A researcher tested the hypothesis that a person’s perceived risk for colorectal cancer was related to his or her cancer screening behavior. With alpha = .05, the hypothesis was not supported. What might be a cause of this result?
A nonparametric test was inappropriately used
The test was underpowered
Too many degrees of freedom
The alpha level was too conservative
- Consider the following hypothesis: The amount of daylight is unrelated to levels of depression in older adults. What type of hypothesis is this?
Nonsignificant hypothesis
Research hypothesis
Alternative hypothesis
Null
- You want to compare the average heart rate of infants, children, teens and adults. You will need to do multiple two sample t tests for this research. Why is the use of t tests inappropriate in this situation?
T tests should be used in this situation, knowing that the result may have false positives
Correlation is a more appropriate statistic in this situation
When there are multiple tests with multiple dependent variables, the Type I error increases
Regression is the appropriate statistic as it enables prediction
- If you decided to make the critical p-value or alpha for significance as 0.001 as opposed to the conventional 0.05, what would the consequences be?
There would be fewer instances when the null hypothesis would be rejected
You would be more likely to make a Type II error
All of the answers
You would be less likely to make a Type I error
- A researcher wants to compare the entrance test scores on XYZ admission test by nursing students at his/her program to national data available on this same admission test. What is the best statistical test to find out whether the program mean admission test score differs significantly from the average national admission test score?
ANOVA
One sample t test
ANCOVA
Chi square test
- Which of the following is the correct way to report the results of a dependent sample t test?
The high school GPA statistically predicted college mathematics performance, R squared = .12, F (1,148) = 20.18, p < .001
t = 9.42, p = .001
The t test was significantly different between group one and group two
On average, the sample glucose level after the new diet (M=132.7, SE = 0.43) was significantly lower than that before the new diet (M= 155.7, SE = 0.46), t (35) = 8.38, p = .001.
