# Quantitative Methods for Evaluating HealthCare Practices, Coursework Example

**Explain how inferential statistics are used in the quantitative research studies.**

Inferential statistics are used in quantitative research studies by analyzing data in way that determines the probability that a particular theory is not wrong. Once researchers formulate a hypothesis, they word it in terms of its opposite called H-null. For example, say a theorist hypothesizes that it is more likely to rain the warmer the weather. He or she would formulate H-null which would state it is NOT more likely to rain the warmer it is or the cooler it is the more likely it is to rain. Researchers would then gather a statistically significant number of temperatures and precipitation measures and analyze the resultant data using appropriate statistical methods to determine the likelihood that H-null is not true.

**Explain why a random sample is important when applying inferential statistics. **

Random sampling is important for at least two reasons. The first reason is a guard against confirmation bias. People tend to verify their own beliefs about a particular topic. Using a random sample helps mitigate this tendency. Another reason has to do with statistical analysis itself. Because it is inferential by nature, we cannot assume any causal logic between variables. Often the best we can do is to say that based on statistical analysis the H-null is probably not attributable to random probability. By implementing random sampling methods, we have a randomized baseline from which to measure.

**Why is the inclusion of parameter estimates becoming more common in nursing research reports?**

When there is a regression analysis, certain parameters such as y-intercepts cause a redundancy in the results because variances are ultimately dependent on said variable. Parameter estimates are a way for controlling for the effects of redundancy based upon the degrees of freedom of the variable effect. This is important to nursing for at least two reasons. One is that it provides a sort of baseline type range. Another is that it more specifically determines if a given patient is at risk for certain conditions based upon the results of certain tests.

**When conducting significance testing, what does it mean when one says the null hypothesis has been accepted (i.e., retained)?**

When conducting significance testing when it is said that the null hypothesis has been accepted it means that H-null seems to be true. In other words, it looks like the opposite of the hypothesis seems to be correct or the original hypothesis is false. It means what we thought does not seem to be true based on the study conducted.

**Using SPSS****, provide descriptive statistics for the ADHD continuous measure (adhd) at baseline. Requested descriptive statistics are: N, mean, standard deviation (SD), standard error of the mean (SEM), and lower and upper limits of the 95% confidence interval (CI) for the mean. **

Descriptives |
||||

Statistic | Std. Error | |||

adhd | Mean | 18.72 | .605 | |

95% Confidence Interval for Mean | Lower Bound | 17.53 | ||

Upper Bound | 19.91 | |||

5% Trimmed Mean | 18.69 | |||

Median | 19.00 | |||

Variance | 75.814 | |||

Std. Deviation | 8.707 | |||

Minimum | 0 | |||

Maximum | 36 | |||

Range | 36 | |||

Interquartile Range | 13 | |||

Skewness | .105 | .169 | ||

Kurtosis | -.787 | .337 |

**Explain the connection between SD, SEM, and sample size. Hint: Be sure to define SD and SEM, and then explain how SD is related to SEM, and how each is affected by sample size.**

Standard deviation is the average distance from the mean of all data points. SEM is the standard deviation of the mean. SEM is the standard deviation divided by N. The greater the sample size the lower either standard deviation or SEM.

**Interpret the 95% CI for the ADHD mean. That is, explain what the 95% CI indicates.**

The 95% CI (confidence interval) for the ADHD mean (18.72) means that there is 95% probability that a random participant will score between 17.53 and 19.91.

**Explain the difference between a Type I error and Type II error.**

These are two errors to be careful of. A Type I error is when the test statistic falsely rejects H-null. Another way of saying it is that what we thought was true actually isn’t but analysis shows it is. A Type II error is when the test statistic falsely fails to reject H-null. Another way of saying it is that what we thought was true seems to be so based on the analysis but actually isn’t.

**What does p < .05 indicate when conducting a two-tailed significance test?**

It means that based on the analysis researchers may be 95% confident that the results are true within a particular data range.

**List the five critical steps in statistical significance testing**

- Formulate hypothesis.
- State H-null
- Select alpha significance
- Apply appropriate test statistic
- Interpret findings

Time is precious

don’t waste it!

Plagiarism-free

guarantee

Privacy

guarantee

Secure

checkout

Money back

guarantee