**Research Design and Statistics**

Research Design and Statistics

**A.**

Write a **short** (max 1 page) report, answering the following questions:

- Please describe the type of research study used (e.g. randomised trial, observational, case-control, survey…)
- What is the population of interest?
- How was the sample selected?
- Is the sample representative and unbiased?

Upload the report for assessment.

**B.**

Please download the dataset: Assignment1.xlsx

- Input the data into SPSS and complete the data key
- Write a
**short**report on the data screening, including: - A histogram of gender
- A boxplot of age, milk consumption and energy intake
- A table with n, mean, median, minimum, maximum and standard deviation for age, milk consumption and energy intake.
- Comment on data screening and any errors/outliers detected

Upload the SPSS data file and the report for assessment.

**Solution**** **

**A.**

**1**.

The research study used here is a randomized trial study where the 214 sample subjects were randomized into one of the 3 groups:

76 subjects were randomized to receive an OGTT and an OLTT on two separate clinical visits

69 subjects were randomized to receive an OGTT on two separate clinical visits

69 subjects were randomized to receive an OLTT on two separate clinical visits

**2.**

The population of interest is adults (aged 18-60).

**3.**

A sample of 214 individuals aged 18-60 (adults) were recruited to undergo tests in the form of OLTT and OGTT.

Detailed biochemical parameters, body composition and fitness tests of the 214 samples were recorded. (This included evaluation of parameters like fasting glucose, triacylglycerols, HDL, LDL and hemoglobin concentrations.)

Mixed model clustering was employed to define 4 metabotypes consisting of 4 different responses to an OGTT.

**4**.

The sample is representative and unbiased.** **

**PART B**

2.

a)

b)

Boxplot of age

Boxplot of milk consumption

Boxplot of energy intake

c)

Statistics |
||||

Age | Milk consumption | Total energy consumption | ||

N | Valid | 96 | 96 | 95 |

Missing | 0 | 0 | 1 | |

Mean | 31.0009 | 307.90 | 1995.97 | |

Median | 28.5200 | 293.00 | 1921.00 | |

Std. Deviation | 10.71497 | 202.053 | 720.530 | |

Minimum | 2.45 | 0 | 824 | |

Maximum | 60.46 | 732 | 3978 |

d)

There are 43 males and 53 females in the data.

The age of the respondent varies from 2.45 years to 60.46 years with mean age of 31 years.

However, the observation no. 13 with age 2.45 years is an outlier for age since all the other persons have age more than 18 years.

There are about 9 other outliers with ages more than 47 years according to the boxplot diagram.

There is no missing value or outliers in the milk consumption.

The milk consumption varies from 0 g per day to 732 g per day with mean milk consumption being 307.9 g per day.

The total energy consumption varies from 824 kcal per day to 3978 kcal per day with mean total energy consumption being 1995.97 kcal per day.

However, according to the boxplot diagram, there are 2 outlier observations in the total energy consumption: observation no. 36 with total energy consumption 3978 kcal per day and observation no. 88 with total energy consumption 3930 kcal per day.

There is 1 missing value in the total energy consumption (Observation no. 21).

** **