Handling Missing Data in Single-Case Experimental Design

Handling Missing Data in Single-Case Experimental Design#

The fill_missing function provides a way to handle missing values in single-case experimental design (SCED) datasets. It ensures that missing values are interpolated without adding new time points.

Filling Missing Values with fill_missing#

The fill_missing function fills missing values in a single-case dataset using linear interpolation. It does not introduce new time points, ensuring that the original structure of the dataset is preserved.

Required Arguments:#

  • data: A Pandas DataFrame containing SCED data.

Optional Arguments:#

  • dvar: The column name of the dependent variable (default "values").

  • mvar: The column name representing measurement time (default "mt").

  • na_rm: If True, explicitly removes missing values before interpolation.

The function processes each case separately and interpolates missing values based on existing time points.

import scia as sc

📖 scia 1.101.0.dev6 - For Documentation, visit: https://ahsankhodami.github.io/scia/intro.html

Example 1: Filling Missing Values in a Dataset#

This example demonstrates how missing values in the dependent variable column (values) are automatically filled.

import pandas as pd
import numpy as np

# Create a sample dataset with missing values
df = pd.DataFrame({
    "case": ["A", "A", "A", "A", "B", "B", "B", "B"],
    "mt": [1, 2, 3, 4, 1, 2, 3, 4],
    "values": [2, np.nan, 5, 6, 1, np.nan, np.nan, 4]
})

# Fill missing values
df_filled = sc.fill_missing(df)
print(df_filled)

  case  mt  values
0    A   1     2.0
1    A   2     3.5
2    A   3     5.0
3    A   4     6.0
4    B   1     1.0
5    B   2     2.0
6    B   3     3.0
7    B   4     4.0

Example 2: Keeping Explicit NA Values#

By setting na_rm=False, explicit NaN values are retained before interpolation.

df_filled = sc.fill_missing(df, na_rm=False)
print(df_filled)

  case  mt  values
0    A   1     2.0
1    A   2     3.5
2    A   3     5.0
3    A   4     6.0
4    B   1     1.0
5    B   2     2.0
6    B   3     3.0
7    B   4     4.0
Contents