Scribd
Upload
2 views2 pages

Statistical Test Selection Guide

The document is a Statistical Test Selection Guide that assists in choosing appropriate statistical tests based on data type, research objectives, and assumptions. It includes various tests such as t-tests, ANOVA, chi-square tests, and regression analyses, along with their purposes and conditions for use. This guide is particularly beneficial for research in accounting, finance, and business studies.

Uploaded by

Dinesh Vaghela
Copyright
© All Rights Reserved
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
2 views2 pages

Statistical Test Selection Guide

The document is a Statistical Test Selection Guide that assists in choosing appropriate statistical tests based on data type, research objectives, and assumptions. It includes various tests such as t-tests, ANOVA, chi-square tests, and regression analyses, along with their purposes and conditions for use. This guide is particularly beneficial for research in accounting, finance, and business studies.

Uploaded by

Dinesh Vaghela
Copyright
© All Rights Reserved
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

Statistical Test Selection Guide

This table provides a quick reference for selecting statistical tests based on the type of data,
research objective, and assumptions. It is particularly useful for research in accounting,
finance, and business studies.

Type of Test Purpose / When to Use Data Type Assumption


Usefulness
Descriptive Summarize First step in all Numeric None
Statistics data (mean, SD, data analysis
etc.)
One-Sample t- Compare Avg ROA vs Numeric (1 Normality
Test sample mean to industry group)
known value average
Independent t- Compare two Profitability: Numeric (2 Normality,
Test independent small vs large groups) equal variances
group means firms
Paired t-Test Compare two Pre/Post audit Numeric Normality
related samples reform (paired)
ANOVA Compare ROA across Numeric (3+ Normality,
means of 3+ sectors groups) equal variances
groups
Chi-Square Test Association Firm type vs tax Categorical Large sample
between compliance size
categories
Pearson Measure Leverage vs Numeric Linear
Correlation strength of ROE relationship
linear
relationship
Simple Predict ROA from Numeric Linearity,
Regression dependent liquidity normality
using one
predictor
Multiple Use multiple Profitability Numeric No
Regression predictors from size, multicollinearit
leverage y
Logistic Binary outcome Bankruptcy Binary Dep. Logistic
Regression prediction prediction Var. distribution
Mann-Whitney Compare ROE: public vs Ordinal/ Non-normal
U Test medians of 2 private Numeric data
independent
groups
Wilcoxon Compare Return Ordinal/ Non-normal
Signed-Rank medians of before/after Numeric paired data
Test paired data acquisition
Kruskal-Wallis ANOVA Liquidity across Ordinal/ Non-normal
Test alternative for sectors Numeric data
non-normal
data
Z-Test Compare Large-sample Numeric Large n or
means (large ROA vs known variance
sample or benchmark
known
variance)
ADF Test Test for Check stock Time series No
stationarity return trend/stationar
stationarity ity
Granger Forecasting GDP growth -> Time series Stationarity
Causality Test relationship in stock returns
time series
Factor Analysis Identify Group financial Numeric Correlated
underlying ratios (multivariable) variables
factors
PCA Data reduction Portfolio risk Numeric Large dataset
simplification
Durbin-Watson Test Regression Time series No
Test autocorrelation with time- autocorrelation
in regression series data
Breusch-Pagan Test for Regression Regression Constant
Test heteroskedastic model residuals variance
ity validation
VIF Test for Before Regression VIF < 10
multicollinearit regression variables recommended
y interpretation

You might also like