Author Archives: Joanna Diong

Research concepts: Overview

An important part of conducting sound science involves interpreting data correctly. Unfortunately, we don’t do that very well. For example, we are fooled by regression to the mean, we report findings when there are none, and we are overconfident about statistical power and significance. As scientists and lay persons, we want to be certain about research findings. But statistics only

Read more

Differences between cohort studies of aetiology and prognosis

Many medical and scientific questions are the sort that cannot be answered using randomised study designs. For example, Does cigarette smoking cause lung cancer?, What is the risk hip fracture in adults?, and Do rats indirectly destroy coral reefs? Scientists often use observational cohort studies to answer these types of questions. In cohort studies, (1) a sample of subjects or

Read more

Exploring the metrics and incentives of scientific productivity

The pressure to publish and current incentives that reward highly-cited discoveries leads to research findings that are not reproducible and inadvertently results in the natural selection of bad science. It is difficult to encourage scientists to take effort in conducting reproducible and rigorous research without better incentives. What kinds of metrics and incentives might reward scientists for conducting sound science?

Read more

Fitting polynomial or exponential curves to biological data in Python

Raw data are not always pretty. Data can have different patterns, be noisy, and vary from trial to trial. We usually collect data to measure, or more accurately, estimate an effect or phenomenon. At times, it is necessary to fit a mathematical expression to raw data in order to estimate the underlying effect or phenomenon. We can then use this

Read more

Statistics you are interested in: simple linear regression – part 3

In the first and second posts of this series, we performed simple linear regression of a continuous outcome on a single continuous predictor, but we also learned it is possible to include binary or categorical predictors in such regression models. How is this be done? The hsb2.csv dataset we have been using also contains the variable female where male participants

Read more

Statistics you are interested in: simple linear regression – part 2

In the previous post, we performed simple linear regression of science scores on reading scores from 200 students using ordinary least squares (OLS) estimation. This was done using Python’s Statsmodels package. What does the OLS output show and how should it be interpreted? Here is the figure of the individual subject data and the line of best fit, as well

Read more
« Older Entries