Scribd
Upload
40 views2 pages

Stata Short Course Statistics

The document describes a randomized controlled trial that compared daily multiple micronutrients to standard prenatal iron and folic acid supplements in pregnant women in Burkina Faso to determine if micronutrients could increase birth weight; it provides details on variables in two datasets that need to be merged and analyzed to compare birth outcomes and characteristics between the control and intervention groups and determine if any differences are statistically significant.

Uploaded by

Pauly Escobar
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
40 views2 pages

Stata Short Course Statistics

The document describes a randomized controlled trial that compared daily multiple micronutrients to standard prenatal iron and folic acid supplements in pregnant women in Burkina Faso to determine if micronutrients could increase birth weight; it provides details on variables in two datasets that need to be merged and analyzed to compare birth outcomes and characteristics between the control and intervention groups and determine if any differences are statistically significant.

Uploaded by

Pauly Escobar
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Statistics tell if the difference found is by chance or it is real

Stata short course statistics: exercises


The data used for this exercise comes from a randomised controlled trial in Burkina Faso (Huybregts et al., 2009). The aim was to compare if daily multiple micronutrients could increase birth weight compared to standard prenatal iron+folic acid. For this purpose pregnant women from 2 health centers were included in the intervention study as early as possible. At inclusion women were randomised to belong to the control or intervention group. Following variables are available: The information is present in 2 datasets (misame1.csv) and misame2.csv. These two datasets need to be merged first. Following variables are given: In misame1.csv Vitrando (0 or 1) : this variable explains if a mother belonged to the control group (=0) or to the intervention group (=1) Env: randomisation/identification number Dob: date of birth of the infant Weightmother: body weight mother when she was included in the study (kg) Lengthmother: body length mother when she was included in the study (m) Gaincl: gestational age at inclusion (weeks) Bw: birth weight (g) Bl: birth length (mm) Primiparity: was the pregnancy primiparous (first pregnancy) or multiparous Ga: Gestational age at delivery (weeks) In misame2.csv Agemother: age of the mother at study inclusion( years) Schooling: school level of mother Health_centre: which health center zone (Karaba or Koho) Profession_husband: profession of the husband

Q1: merge misame1.csv with misame2.csv. Is the merge perfect? Q2: Explore the data, are there any missing birth weight values? Q3: Verify if the mothers between the control and intervention group are identical, weight, lenght and Body Mass Index (W/lenght2) Q4: Compare birth weight and birth length between control and intervention group. Are these differences statistically significant? Q5: make a histogram of birth weight by intervention group (control and intervention)

Q7: Compare the mean ga between both groups, is it balanced? Adjust the analysis of the intervention on bw an bl for ga. Q8: Check if maternal BMI at earry pregnancy predicts bw, ga and Bl. Use a regression model that adjusts for vitrando.

Do the ttest for women in the following different groups BMI < 18.5 (unnourished) BMI > 18.5 (non-unnourished)

You might also like